Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+adapter/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

Modelfile

@@ -0,0 +1,8 @@
+# ollama modelfile auto-generated by llamafactory
+
+FROM .
+
+TEMPLATE """{{ if .System }}{{ .System }}{{ end }}{{ range .Messages }}{{ if eq .Role "user" }}<｜User｜>{{ .Content }}{{ else if eq .Role "assistant" }}<｜Assistant｜>{{ .Content }}<｜end▁of▁sentence｜>{{ end }}{{ end }}"""
+
+PARAMETER stop "<｜end▁of▁sentence｜>"
+PARAMETER num_ctx 4096

adapter/README.md

@@ -0,0 +1,60 @@
+---
+library_name: peft
+license: other
+base_model: unsloth/DeepSeek-R1-Distill-Qwen-7B-bnb-4bit
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: llama3_lora
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# llama3_lora
+
+This model is a fine-tuned version of [unsloth/DeepSeek-R1-Distill-Qwen-7B-bnb-4bit](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-7B-bnb-4bit) on the limo_restructured dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 3
+- total_train_batch_size: 3
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.48.3
+- Pytorch 2.6.0+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

adapter/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/DeepSeek-R1-Distill-Qwen-7B-bnb-4bit",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "o_proj",
+    "up_proj",
+    "down_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2200f16a85bf5e7003d7119c6a2134b6662b23e25e041b437e2351fd8a83b8e6
+size 80792096

adapter/all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9987760097919217,
+    "total_flos": 1.7184161279184077e+17,
+    "train_loss": 0.49135432271834684,
+    "train_runtime": 6097.9323,
+    "train_samples_per_second": 0.134,
+    "train_steps_per_second": 0.045
+}

adapter/special_tokens_map.json

@@ -0,0 +1,32 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|vision_pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

adapter/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778

adapter/tokenizer_config.json

@@ -0,0 +1,200 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<｜User｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151645": {
+      "content": "<｜Assistant｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151646": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151648": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151649": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<｜end▁of▁sentence｜>"
+  ],
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\\n'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 6144,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

adapter/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9987760097919217,
+    "total_flos": 1.7184161279184077e+17,
+    "train_loss": 0.49135432271834684,
+    "train_runtime": 6097.9323,
+    "train_samples_per_second": 0.134,
+    "train_steps_per_second": 0.045
+}

adapter/trainer_log.jsonl

@@ -0,0 +1,279 @@
+{"current_steps": 5, "total_steps": 186, "loss": 0.6061, "lr": 7.894736842105262e-05, "epoch": 0.08, "percentage": 2.69, "elapsed_time": "0:01:42", "remaining_time": "1:01:51"}
+{"current_steps": 10, "total_steps": 186, "loss": 0.6024, "lr": 0.00015789473684210524, "epoch": 0.16, "percentage": 5.38, "elapsed_time": "0:03:24", "remaining_time": "0:59:57"}
+{"current_steps": 5, "total_steps": 1500, "loss": 0.5642, "lr": 3.3333333333333333e-06, "epoch": 0.01, "percentage": 0.33, "elapsed_time": "0:00:37", "remaining_time": "3:04:24"}
+{"current_steps": 5, "total_steps": 1500, "loss": 0.5647, "lr": 3.3333333333333333e-06, "epoch": 0.01, "percentage": 0.33, "elapsed_time": "0:00:39", "remaining_time": "3:17:51"}
+{"current_steps": 5, "total_steps": 1500, "loss": 0.5647, "lr": 3.3333333333333333e-06, "epoch": 0.01, "percentage": 0.33, "elapsed_time": "0:00:37", "remaining_time": "3:07:18"}
+{"current_steps": 10, "total_steps": 1500, "loss": 0.5811, "lr": 6.666666666666667e-06, "epoch": 0.02, "percentage": 0.67, "elapsed_time": "0:01:20", "remaining_time": "3:19:02"}
+{"current_steps": 1, "total_steps": 272, "loss": 0.4568, "lr": 3.5714285714285714e-06, "epoch": 0.0036719706242350062, "percentage": 0.37, "elapsed_time": "0:00:24", "remaining_time": "1:50:28"}
+{"current_steps": 2, "total_steps": 272, "loss": 0.7457, "lr": 7.142857142857143e-06, "epoch": 0.0073439412484700125, "percentage": 0.74, "elapsed_time": "0:00:48", "remaining_time": "1:48:44"}
+{"current_steps": 3, "total_steps": 272, "loss": 0.3669, "lr": 1.0714285714285714e-05, "epoch": 0.011015911872705019, "percentage": 1.1, "elapsed_time": "0:01:13", "remaining_time": "1:49:28"}
+{"current_steps": 4, "total_steps": 272, "loss": 0.4611, "lr": 1.4285714285714285e-05, "epoch": 0.014687882496940025, "percentage": 1.47, "elapsed_time": "0:01:33", "remaining_time": "1:44:23"}
+{"current_steps": 5, "total_steps": 272, "loss": 0.3727, "lr": 1.785714285714286e-05, "epoch": 0.01835985312117503, "percentage": 1.84, "elapsed_time": "0:01:51", "remaining_time": "1:39:05"}
+{"current_steps": 6, "total_steps": 272, "loss": 0.3609, "lr": 2.1428571428571428e-05, "epoch": 0.022031823745410038, "percentage": 2.21, "elapsed_time": "0:02:15", "remaining_time": "1:40:18"}
+{"current_steps": 7, "total_steps": 272, "loss": 0.8697, "lr": 2.5e-05, "epoch": 0.025703794369645042, "percentage": 2.57, "elapsed_time": "0:02:39", "remaining_time": "1:40:54"}
+{"current_steps": 8, "total_steps": 272, "loss": 0.521, "lr": 2.857142857142857e-05, "epoch": 0.02937576499388005, "percentage": 2.94, "elapsed_time": "0:02:57", "remaining_time": "1:37:23"}
+{"current_steps": 9, "total_steps": 272, "loss": 0.676, "lr": 3.2142857142857144e-05, "epoch": 0.033047735618115054, "percentage": 3.31, "elapsed_time": "0:03:23", "remaining_time": "1:39:05"}
+{"current_steps": 10, "total_steps": 272, "loss": 0.306, "lr": 3.571428571428572e-05, "epoch": 0.03671970624235006, "percentage": 3.68, "elapsed_time": "0:03:45", "remaining_time": "1:38:39"}
+{"current_steps": 11, "total_steps": 272, "loss": 0.5941, "lr": 3.928571428571429e-05, "epoch": 0.04039167686658507, "percentage": 4.04, "elapsed_time": "0:04:07", "remaining_time": "1:38:02"}
+{"current_steps": 12, "total_steps": 272, "loss": 0.412, "lr": 4.2857142857142856e-05, "epoch": 0.044063647490820076, "percentage": 4.41, "elapsed_time": "0:04:32", "remaining_time": "1:38:21"}
+{"current_steps": 13, "total_steps": 272, "loss": 0.4988, "lr": 4.642857142857143e-05, "epoch": 0.04773561811505508, "percentage": 4.78, "elapsed_time": "0:04:52", "remaining_time": "1:37:07"}
+{"current_steps": 14, "total_steps": 272, "loss": 0.3337, "lr": 5e-05, "epoch": 0.051407588739290085, "percentage": 5.15, "elapsed_time": "0:05:16", "remaining_time": "1:37:06"}
+{"current_steps": 15, "total_steps": 272, "loss": 0.424, "lr": 5.3571428571428575e-05, "epoch": 0.05507955936352509, "percentage": 5.51, "elapsed_time": "0:05:40", "remaining_time": "1:37:15"}
+{"current_steps": 16, "total_steps": 272, "loss": 0.3674, "lr": 5.714285714285714e-05, "epoch": 0.0587515299877601, "percentage": 5.88, "elapsed_time": "0:06:10", "remaining_time": "1:38:44"}
+{"current_steps": 17, "total_steps": 272, "loss": 0.4244, "lr": 6.0714285714285715e-05, "epoch": 0.06242350061199511, "percentage": 6.25, "elapsed_time": "0:06:33", "remaining_time": "1:38:15"}
+{"current_steps": 18, "total_steps": 272, "loss": 0.3832, "lr": 6.428571428571429e-05, "epoch": 0.06609547123623011, "percentage": 6.62, "elapsed_time": "0:06:55", "remaining_time": "1:37:43"}
+{"current_steps": 19, "total_steps": 272, "loss": 0.7971, "lr": 6.785714285714286e-05, "epoch": 0.06976744186046512, "percentage": 6.99, "elapsed_time": "0:07:18", "remaining_time": "1:37:22"}
+{"current_steps": 20, "total_steps": 272, "loss": 0.267, "lr": 7.142857142857143e-05, "epoch": 0.07343941248470012, "percentage": 7.35, "elapsed_time": "0:07:35", "remaining_time": "1:35:39"}
+{"current_steps": 21, "total_steps": 272, "loss": 0.4959, "lr": 7.500000000000001e-05, "epoch": 0.07711138310893513, "percentage": 7.72, "elapsed_time": "0:08:00", "remaining_time": "1:35:45"}
+{"current_steps": 22, "total_steps": 272, "loss": 0.6555, "lr": 7.857142857142858e-05, "epoch": 0.08078335373317014, "percentage": 8.09, "elapsed_time": "0:08:25", "remaining_time": "1:35:41"}
+{"current_steps": 23, "total_steps": 272, "loss": 0.365, "lr": 8.214285714285714e-05, "epoch": 0.08445532435740515, "percentage": 8.46, "elapsed_time": "0:08:49", "remaining_time": "1:35:33"}
+{"current_steps": 24, "total_steps": 272, "loss": 0.3245, "lr": 8.571428571428571e-05, "epoch": 0.08812729498164015, "percentage": 8.82, "elapsed_time": "0:09:13", "remaining_time": "1:35:15"}
+{"current_steps": 25, "total_steps": 272, "loss": 0.7651, "lr": 8.92857142857143e-05, "epoch": 0.09179926560587515, "percentage": 9.19, "elapsed_time": "0:09:35", "remaining_time": "1:34:45"}
+{"current_steps": 26, "total_steps": 272, "loss": 0.4515, "lr": 9.285714285714286e-05, "epoch": 0.09547123623011015, "percentage": 9.56, "elapsed_time": "0:10:01", "remaining_time": "1:34:51"}
+{"current_steps": 27, "total_steps": 272, "loss": 0.853, "lr": 9.642857142857143e-05, "epoch": 0.09914320685434516, "percentage": 9.93, "elapsed_time": "0:10:21", "remaining_time": "1:34:01"}
+{"current_steps": 28, "total_steps": 272, "loss": 0.5184, "lr": 0.0001, "epoch": 0.10281517747858017, "percentage": 10.29, "elapsed_time": "0:10:50", "remaining_time": "1:34:24"}
+{"current_steps": 29, "total_steps": 272, "loss": 0.4656, "lr": 9.999585567217439e-05, "epoch": 0.10648714810281518, "percentage": 10.66, "elapsed_time": "0:11:10", "remaining_time": "1:33:35"}
+{"current_steps": 30, "total_steps": 272, "loss": 1.1901, "lr": 9.998342337571565e-05, "epoch": 0.11015911872705018, "percentage": 11.03, "elapsed_time": "0:11:33", "remaining_time": "1:33:10"}
+{"current_steps": 31, "total_steps": 272, "loss": 0.3506, "lr": 9.99627051715643e-05, "epoch": 0.11383108935128519, "percentage": 11.4, "elapsed_time": "0:11:57", "remaining_time": "1:32:57"}
+{"current_steps": 32, "total_steps": 272, "loss": 0.3324, "lr": 9.993370449424153e-05, "epoch": 0.1175030599755202, "percentage": 11.76, "elapsed_time": "0:12:16", "remaining_time": "1:32:05"}
+{"current_steps": 33, "total_steps": 272, "loss": 0.2745, "lr": 9.98964261512799e-05, "epoch": 0.1211750305997552, "percentage": 12.13, "elapsed_time": "0:12:38", "remaining_time": "1:31:34"}
+{"current_steps": 34, "total_steps": 272, "loss": 0.5225, "lr": 9.985087632242633e-05, "epoch": 0.12484700122399021, "percentage": 12.5, "elapsed_time": "0:13:00", "remaining_time": "1:31:00"}
+{"current_steps": 35, "total_steps": 272, "loss": 0.3213, "lr": 9.97970625586178e-05, "epoch": 0.12851897184822522, "percentage": 12.87, "elapsed_time": "0:13:19", "remaining_time": "1:30:15"}
+{"current_steps": 36, "total_steps": 272, "loss": 0.3551, "lr": 9.973499378072945e-05, "epoch": 0.13219094247246022, "percentage": 13.24, "elapsed_time": "0:13:45", "remaining_time": "1:30:14"}
+{"current_steps": 37, "total_steps": 272, "loss": 0.3264, "lr": 9.966468027809582e-05, "epoch": 0.13586291309669524, "percentage": 13.6, "elapsed_time": "0:14:02", "remaining_time": "1:29:10"}
+{"current_steps": 38, "total_steps": 272, "loss": 0.397, "lr": 9.958613370680507e-05, "epoch": 0.13953488372093023, "percentage": 13.97, "elapsed_time": "0:14:31", "remaining_time": "1:29:25"}
+{"current_steps": 39, "total_steps": 272, "loss": 0.9732, "lr": 9.949936708776691e-05, "epoch": 0.14320685434516525, "percentage": 14.34, "elapsed_time": "0:14:51", "remaining_time": "1:28:44"}
+{"current_steps": 40, "total_steps": 272, "loss": 0.3739, "lr": 9.940439480455386e-05, "epoch": 0.14687882496940025, "percentage": 14.71, "elapsed_time": "0:15:12", "remaining_time": "1:28:13"}
+{"current_steps": 41, "total_steps": 272, "loss": 0.3762, "lr": 9.930123260101696e-05, "epoch": 0.15055079559363524, "percentage": 15.07, "elapsed_time": "0:15:34", "remaining_time": "1:27:42"}
+{"current_steps": 42, "total_steps": 272, "loss": 0.4278, "lr": 9.918989757867583e-05, "epoch": 0.15422276621787026, "percentage": 15.44, "elapsed_time": "0:16:01", "remaining_time": "1:27:45"}
+{"current_steps": 43, "total_steps": 272, "loss": 0.478, "lr": 9.907040819388371e-05, "epoch": 0.15789473684210525, "percentage": 15.81, "elapsed_time": "0:16:26", "remaining_time": "1:27:31"}
+{"current_steps": 44, "total_steps": 272, "loss": 0.3133, "lr": 9.89427842547679e-05, "epoch": 0.16156670746634028, "percentage": 16.18, "elapsed_time": "0:16:50", "remaining_time": "1:27:17"}
+{"current_steps": 45, "total_steps": 272, "loss": 0.4275, "lr": 9.880704691794608e-05, "epoch": 0.16523867809057527, "percentage": 16.54, "elapsed_time": "0:17:12", "remaining_time": "1:26:47"}
+{"current_steps": 46, "total_steps": 272, "loss": 0.7791, "lr": 9.866321868501914e-05, "epoch": 0.1689106487148103, "percentage": 16.91, "elapsed_time": "0:17:41", "remaining_time": "1:26:57"}
+{"current_steps": 47, "total_steps": 272, "loss": 0.6251, "lr": 9.851132339884096e-05, "epoch": 0.17258261933904528, "percentage": 17.28, "elapsed_time": "0:18:04", "remaining_time": "1:26:31"}
+{"current_steps": 48, "total_steps": 272, "loss": 0.4439, "lr": 9.835138623956603e-05, "epoch": 0.1762545899632803, "percentage": 17.65, "elapsed_time": "0:18:28", "remaining_time": "1:26:14"}
+{"current_steps": 49, "total_steps": 272, "loss": 0.2853, "lr": 9.81834337204751e-05, "epoch": 0.1799265605875153, "percentage": 18.01, "elapsed_time": "0:18:43", "remaining_time": "1:25:12"}
+{"current_steps": 50, "total_steps": 272, "loss": 0.5243, "lr": 9.800749368358009e-05, "epoch": 0.1835985312117503, "percentage": 18.38, "elapsed_time": "0:19:02", "remaining_time": "1:24:33"}
+{"current_steps": 51, "total_steps": 272, "loss": 0.6096, "lr": 9.782359529500867e-05, "epoch": 0.18727050183598531, "percentage": 18.75, "elapsed_time": "0:19:20", "remaining_time": "1:23:50"}
+{"current_steps": 52, "total_steps": 272, "loss": 0.4799, "lr": 9.763176904016913e-05, "epoch": 0.1909424724602203, "percentage": 19.12, "elapsed_time": "0:19:39", "remaining_time": "1:23:09"}
+{"current_steps": 53, "total_steps": 272, "loss": 0.6377, "lr": 9.743204671869694e-05, "epoch": 0.19461444308445533, "percentage": 19.49, "elapsed_time": "0:19:54", "remaining_time": "1:22:14"}
+{"current_steps": 54, "total_steps": 272, "loss": 0.5388, "lr": 9.722446143918306e-05, "epoch": 0.19828641370869032, "percentage": 19.85, "elapsed_time": "0:20:13", "remaining_time": "1:21:38"}
+{"current_steps": 55, "total_steps": 272, "loss": 0.5875, "lr": 9.70090476136855e-05, "epoch": 0.20195838433292534, "percentage": 20.22, "elapsed_time": "0:20:34", "remaining_time": "1:21:11"}
+{"current_steps": 56, "total_steps": 272, "loss": 0.3805, "lr": 9.678584095202468e-05, "epoch": 0.20563035495716034, "percentage": 20.59, "elapsed_time": "0:20:56", "remaining_time": "1:20:45"}
+{"current_steps": 57, "total_steps": 272, "loss": 0.5034, "lr": 9.655487845586377e-05, "epoch": 0.20930232558139536, "percentage": 20.96, "elapsed_time": "0:21:11", "remaining_time": "1:19:54"}
+{"current_steps": 58, "total_steps": 272, "loss": 0.4465, "lr": 9.631619841257476e-05, "epoch": 0.21297429620563035, "percentage": 21.32, "elapsed_time": "0:21:27", "remaining_time": "1:19:09"}
+{"current_steps": 59, "total_steps": 272, "loss": 0.3717, "lr": 9.60698403888914e-05, "epoch": 0.21664626682986537, "percentage": 21.69, "elapsed_time": "0:21:46", "remaining_time": "1:18:35"}
+{"current_steps": 60, "total_steps": 272, "loss": 0.5679, "lr": 9.581584522435024e-05, "epoch": 0.22031823745410037, "percentage": 22.06, "elapsed_time": "0:22:10", "remaining_time": "1:18:21"}
+{"current_steps": 61, "total_steps": 272, "loss": 0.3083, "lr": 9.555425502452038e-05, "epoch": 0.22399020807833536, "percentage": 22.43, "elapsed_time": "0:22:28", "remaining_time": "1:17:45"}
+{"current_steps": 62, "total_steps": 272, "loss": 0.575, "lr": 9.528511315402358e-05, "epoch": 0.22766217870257038, "percentage": 22.79, "elapsed_time": "0:22:52", "remaining_time": "1:17:27"}
+{"current_steps": 63, "total_steps": 272, "loss": 0.5254, "lr": 9.500846422934557e-05, "epoch": 0.23133414932680538, "percentage": 23.16, "elapsed_time": "0:23:15", "remaining_time": "1:17:10"}
+{"current_steps": 64, "total_steps": 272, "loss": 0.7045, "lr": 9.472435411143978e-05, "epoch": 0.2350061199510404, "percentage": 23.53, "elapsed_time": "0:23:36", "remaining_time": "1:16:43"}
+{"current_steps": 65, "total_steps": 272, "loss": 0.6068, "lr": 9.443282989812495e-05, "epoch": 0.2386780905752754, "percentage": 23.9, "elapsed_time": "0:23:58", "remaining_time": "1:16:21"}
+{"current_steps": 66, "total_steps": 272, "loss": 0.8401, "lr": 9.413393991627737e-05, "epoch": 0.2423500611995104, "percentage": 24.26, "elapsed_time": "0:24:19", "remaining_time": "1:15:56"}
+{"current_steps": 67, "total_steps": 272, "loss": 0.425, "lr": 9.382773371381985e-05, "epoch": 0.2460220318237454, "percentage": 24.63, "elapsed_time": "0:24:40", "remaining_time": "1:15:30"}
+{"current_steps": 68, "total_steps": 272, "loss": 0.5221, "lr": 9.351426205150777e-05, "epoch": 0.24969400244798043, "percentage": 25.0, "elapsed_time": "0:25:09", "remaining_time": "1:15:28"}
+{"current_steps": 69, "total_steps": 272, "loss": 0.5302, "lr": 9.319357689451443e-05, "epoch": 0.2533659730722154, "percentage": 25.37, "elapsed_time": "0:25:31", "remaining_time": "1:15:04"}
+{"current_steps": 70, "total_steps": 272, "loss": 0.3575, "lr": 9.286573140381662e-05, "epoch": 0.25703794369645044, "percentage": 25.74, "elapsed_time": "0:25:52", "remaining_time": "1:14:39"}
+{"current_steps": 71, "total_steps": 272, "loss": 0.7181, "lr": 9.253077992738192e-05, "epoch": 0.2607099143206854, "percentage": 26.1, "elapsed_time": "0:26:16", "remaining_time": "1:14:23"}
+{"current_steps": 72, "total_steps": 272, "loss": 0.5156, "lr": 9.218877799115928e-05, "epoch": 0.26438188494492043, "percentage": 26.47, "elapsed_time": "0:26:41", "remaining_time": "1:14:09"}
+{"current_steps": 73, "total_steps": 272, "loss": 0.3, "lr": 9.183978228987436e-05, "epoch": 0.26805385556915545, "percentage": 26.84, "elapsed_time": "0:26:58", "remaining_time": "1:13:31"}
+{"current_steps": 74, "total_steps": 272, "loss": 0.4198, "lr": 9.148385067763095e-05, "epoch": 0.2717258261933905, "percentage": 27.21, "elapsed_time": "0:27:20", "remaining_time": "1:13:09"}
+{"current_steps": 75, "total_steps": 272, "loss": 0.3915, "lr": 9.112104215832047e-05, "epoch": 0.27539779681762544, "percentage": 27.57, "elapsed_time": "0:27:47", "remaining_time": "1:12:59"}
+{"current_steps": 76, "total_steps": 272, "loss": 0.2867, "lr": 9.075141687584057e-05, "epoch": 0.27906976744186046, "percentage": 27.94, "elapsed_time": "0:28:07", "remaining_time": "1:12:31"}
+{"current_steps": 77, "total_steps": 272, "loss": 0.4824, "lr": 9.037503610412501e-05, "epoch": 0.2827417380660955, "percentage": 28.31, "elapsed_time": "0:28:34", "remaining_time": "1:12:22"}
+{"current_steps": 78, "total_steps": 272, "loss": 0.3936, "lr": 8.999196223698599e-05, "epoch": 0.2864137086903305, "percentage": 28.68, "elapsed_time": "0:28:59", "remaining_time": "1:12:06"}
+{"current_steps": 79, "total_steps": 272, "loss": 0.4454, "lr": 8.960225877777095e-05, "epoch": 0.29008567931456547, "percentage": 29.04, "elapsed_time": "0:29:24", "remaining_time": "1:11:50"}
+{"current_steps": 80, "total_steps": 272, "loss": 0.2931, "lr": 8.920599032883554e-05, "epoch": 0.2937576499388005, "percentage": 29.41, "elapsed_time": "0:29:44", "remaining_time": "1:11:22"}
+{"current_steps": 81, "total_steps": 272, "loss": 0.4871, "lr": 8.880322258083408e-05, "epoch": 0.2974296205630355, "percentage": 29.78, "elapsed_time": "0:30:10", "remaining_time": "1:11:09"}
+{"current_steps": 82, "total_steps": 272, "loss": 0.3048, "lr": 8.839402230183e-05, "epoch": 0.3011015911872705, "percentage": 30.15, "elapsed_time": "0:30:30", "remaining_time": "1:10:41"}
+{"current_steps": 83, "total_steps": 272, "loss": 0.4948, "lr": 8.797845732622743e-05, "epoch": 0.3047735618115055, "percentage": 30.51, "elapsed_time": "0:30:51", "remaining_time": "1:10:15"}
+{"current_steps": 84, "total_steps": 272, "loss": 0.6406, "lr": 8.755659654352599e-05, "epoch": 0.3084455324357405, "percentage": 30.88, "elapsed_time": "0:31:06", "remaining_time": "1:09:37"}
+{"current_steps": 85, "total_steps": 272, "loss": 0.362, "lr": 8.712850988690093e-05, "epoch": 0.31211750305997554, "percentage": 31.25, "elapsed_time": "0:31:23", "remaining_time": "1:09:04"}
+{"current_steps": 86, "total_steps": 272, "loss": 0.2735, "lr": 8.669426832160996e-05, "epoch": 0.3157894736842105, "percentage": 31.62, "elapsed_time": "0:31:51", "remaining_time": "1:08:53"}
+{"current_steps": 87, "total_steps": 272, "loss": 0.6501, "lr": 8.625394383322914e-05, "epoch": 0.31946144430844553, "percentage": 31.99, "elapsed_time": "0:32:12", "remaining_time": "1:08:29"}
+{"current_steps": 88, "total_steps": 272, "loss": 0.4452, "lr": 8.580760941571967e-05, "epoch": 0.32313341493268055, "percentage": 32.35, "elapsed_time": "0:32:37", "remaining_time": "1:08:12"}
+{"current_steps": 89, "total_steps": 272, "loss": 0.3644, "lr": 8.535533905932738e-05, "epoch": 0.3268053855569155, "percentage": 32.72, "elapsed_time": "0:32:55", "remaining_time": "1:07:42"}
+{"current_steps": 90, "total_steps": 272, "loss": 0.632, "lr": 8.489720773831717e-05, "epoch": 0.33047735618115054, "percentage": 33.09, "elapsed_time": "0:33:23", "remaining_time": "1:07:30"}
+{"current_steps": 91, "total_steps": 272, "loss": 0.5625, "lr": 8.443329139854433e-05, "epoch": 0.33414932680538556, "percentage": 33.46, "elapsed_time": "0:33:47", "remaining_time": "1:07:12"}
+{"current_steps": 92, "total_steps": 272, "loss": 0.3207, "lr": 8.396366694486466e-05, "epoch": 0.3378212974296206, "percentage": 33.82, "elapsed_time": "0:34:06", "remaining_time": "1:06:43"}
+{"current_steps": 93, "total_steps": 272, "loss": 0.5898, "lr": 8.34884122283858e-05, "epoch": 0.34149326805385555, "percentage": 34.19, "elapsed_time": "0:34:22", "remaining_time": "1:06:10"}
+{"current_steps": 94, "total_steps": 272, "loss": 0.4658, "lr": 8.300760603356159e-05, "epoch": 0.34516523867809057, "percentage": 34.56, "elapsed_time": "0:34:39", "remaining_time": "1:05:38"}
+{"current_steps": 95, "total_steps": 272, "loss": 0.4421, "lr": 8.25213280651317e-05, "epoch": 0.3488372093023256, "percentage": 34.93, "elapsed_time": "0:35:00", "remaining_time": "1:05:13"}
+{"current_steps": 96, "total_steps": 272, "loss": 0.2782, "lr": 8.202965893490878e-05, "epoch": 0.3525091799265606, "percentage": 35.29, "elapsed_time": "0:35:25", "remaining_time": "1:04:55"}
+{"current_steps": 97, "total_steps": 272, "loss": 0.4888, "lr": 8.153268014841506e-05, "epoch": 0.3561811505507956, "percentage": 35.66, "elapsed_time": "0:35:50", "remaining_time": "1:04:39"}
+{"current_steps": 98, "total_steps": 272, "loss": 0.7807, "lr": 8.103047409137114e-05, "epoch": 0.3598531211750306, "percentage": 36.03, "elapsed_time": "0:36:09", "remaining_time": "1:04:11"}
+{"current_steps": 99, "total_steps": 272, "loss": 0.6298, "lr": 8.052312401603847e-05, "epoch": 0.3635250917992656, "percentage": 36.4, "elapsed_time": "0:36:29", "remaining_time": "1:03:46"}
+{"current_steps": 100, "total_steps": 272, "loss": 0.8064, "lr": 8.001071402741842e-05, "epoch": 0.3671970624235006, "percentage": 36.76, "elapsed_time": "0:36:54", "remaining_time": "1:03:28"}
+{"current_steps": 101, "total_steps": 272, "loss": 0.3406, "lr": 7.949332906930995e-05, "epoch": 0.3708690330477356, "percentage": 37.13, "elapsed_time": "0:37:19", "remaining_time": "1:03:12"}
+{"current_steps": 102, "total_steps": 272, "loss": 0.579, "lr": 7.897105491022818e-05, "epoch": 0.37454100367197063, "percentage": 37.5, "elapsed_time": "0:37:45", "remaining_time": "1:02:55"}
+{"current_steps": 103, "total_steps": 272, "loss": 0.3489, "lr": 7.844397812918635e-05, "epoch": 0.37821297429620565, "percentage": 37.87, "elapsed_time": "0:38:09", "remaining_time": "1:02:36"}
+{"current_steps": 104, "total_steps": 272, "loss": 0.4151, "lr": 7.791218610134323e-05, "epoch": 0.3818849449204406, "percentage": 38.24, "elapsed_time": "0:38:27", "remaining_time": "1:02:07"}
+{"current_steps": 105, "total_steps": 272, "loss": 1.1401, "lr": 7.737576698351878e-05, "epoch": 0.38555691554467564, "percentage": 38.6, "elapsed_time": "0:38:55", "remaining_time": "1:01:55"}
+{"current_steps": 106, "total_steps": 272, "loss": 0.3091, "lr": 7.683480969958004e-05, "epoch": 0.38922888616891066, "percentage": 38.97, "elapsed_time": "0:39:12", "remaining_time": "1:01:24"}
+{"current_steps": 107, "total_steps": 272, "loss": 0.4951, "lr": 7.628940392569994e-05, "epoch": 0.3929008567931457, "percentage": 39.34, "elapsed_time": "0:39:36", "remaining_time": "1:01:04"}
+{"current_steps": 108, "total_steps": 272, "loss": 0.4025, "lr": 7.573964007549155e-05, "epoch": 0.39657282741738065, "percentage": 39.71, "elapsed_time": "0:39:56", "remaining_time": "1:00:39"}
+{"current_steps": 109, "total_steps": 272, "loss": 0.4147, "lr": 7.518560928501969e-05, "epoch": 0.40024479804161567, "percentage": 40.07, "elapsed_time": "0:40:21", "remaining_time": "1:00:20"}
+{"current_steps": 110, "total_steps": 272, "loss": 0.5981, "lr": 7.462740339769324e-05, "epoch": 0.4039167686658507, "percentage": 40.44, "elapsed_time": "0:40:46", "remaining_time": "1:00:03"}
+{"current_steps": 111, "total_steps": 272, "loss": 0.4219, "lr": 7.406511494903982e-05, "epoch": 0.40758873929008566, "percentage": 40.81, "elapsed_time": "0:41:08", "remaining_time": "0:59:40"}
+{"current_steps": 112, "total_steps": 272, "loss": 0.4379, "lr": 7.3498837151366e-05, "epoch": 0.4112607099143207, "percentage": 41.18, "elapsed_time": "0:41:28", "remaining_time": "0:59:15"}
+{"current_steps": 113, "total_steps": 272, "loss": 0.3631, "lr": 7.292866387830514e-05, "epoch": 0.4149326805385557, "percentage": 41.54, "elapsed_time": "0:41:48", "remaining_time": "0:58:49"}
+{"current_steps": 114, "total_steps": 272, "loss": 0.6605, "lr": 7.23546896492557e-05, "epoch": 0.4186046511627907, "percentage": 41.91, "elapsed_time": "0:42:11", "remaining_time": "0:58:28"}
+{"current_steps": 115, "total_steps": 272, "loss": 0.5364, "lr": 7.177700961371239e-05, "epoch": 0.4222766217870257, "percentage": 42.28, "elapsed_time": "0:42:36", "remaining_time": "0:58:09"}
+{"current_steps": 116, "total_steps": 272, "loss": 0.3387, "lr": 7.119571953549305e-05, "epoch": 0.4259485924112607, "percentage": 42.65, "elapsed_time": "0:42:58", "remaining_time": "0:57:48"}
+{"current_steps": 117, "total_steps": 272, "loss": 0.5689, "lr": 7.06109157768635e-05, "epoch": 0.42962056303549573, "percentage": 43.01, "elapsed_time": "0:43:23", "remaining_time": "0:57:28"}
+{"current_steps": 118, "total_steps": 272, "loss": 0.4366, "lr": 7.002269528256334e-05, "epoch": 0.43329253365973075, "percentage": 43.38, "elapsed_time": "0:43:50", "remaining_time": "0:57:12"}
+{"current_steps": 119, "total_steps": 272, "loss": 0.3186, "lr": 6.943115556373502e-05, "epoch": 0.4369645042839657, "percentage": 43.75, "elapsed_time": "0:44:10", "remaining_time": "0:56:47"}
+{"current_steps": 120, "total_steps": 272, "loss": 0.3786, "lr": 6.883639468175927e-05, "epoch": 0.44063647490820074, "percentage": 44.12, "elapsed_time": "0:44:36", "remaining_time": "0:56:29"}
+{"current_steps": 121, "total_steps": 272, "loss": 0.3527, "lr": 6.823851123199893e-05, "epoch": 0.44430844553243576, "percentage": 44.49, "elapsed_time": "0:45:02", "remaining_time": "0:56:12"}
+{"current_steps": 122, "total_steps": 272, "loss": 0.4314, "lr": 6.763760432745475e-05, "epoch": 0.4479804161566707, "percentage": 44.85, "elapsed_time": "0:45:20", "remaining_time": "0:55:45"}
+{"current_steps": 123, "total_steps": 272, "loss": 0.2977, "lr": 6.703377358233489e-05, "epoch": 0.45165238678090575, "percentage": 45.22, "elapsed_time": "0:45:40", "remaining_time": "0:55:20"}
+{"current_steps": 124, "total_steps": 272, "loss": 0.3244, "lr": 6.642711909554174e-05, "epoch": 0.45532435740514077, "percentage": 45.59, "elapsed_time": "0:45:56", "remaining_time": "0:54:50"}
+{"current_steps": 125, "total_steps": 272, "loss": 0.4996, "lr": 6.58177414340781e-05, "epoch": 0.4589963280293758, "percentage": 45.96, "elapsed_time": "0:46:22", "remaining_time": "0:54:32"}
+{"current_steps": 126, "total_steps": 272, "loss": 0.555, "lr": 6.52057416163759e-05, "epoch": 0.46266829865361075, "percentage": 46.32, "elapsed_time": "0:46:42", "remaining_time": "0:54:06"}
+{"current_steps": 127, "total_steps": 272, "loss": 0.2582, "lr": 6.45912210955501e-05, "epoch": 0.4663402692778458, "percentage": 46.69, "elapsed_time": "0:46:59", "remaining_time": "0:53:39"}
+{"current_steps": 128, "total_steps": 272, "loss": 0.5315, "lr": 6.397428174258047e-05, "epoch": 0.4700122399020808, "percentage": 47.06, "elapsed_time": "0:47:31", "remaining_time": "0:53:27"}
+{"current_steps": 129, "total_steps": 272, "loss": 0.489, "lr": 6.335502582942408e-05, "epoch": 0.47368421052631576, "percentage": 47.43, "elapsed_time": "0:47:46", "remaining_time": "0:52:57"}
+{"current_steps": 130, "total_steps": 272, "loss": 0.456, "lr": 6.273355601206144e-05, "epoch": 0.4773561811505508, "percentage": 47.79, "elapsed_time": "0:48:06", "remaining_time": "0:52:33"}
+{"current_steps": 131, "total_steps": 272, "loss": 0.3459, "lr": 6.210997531347878e-05, "epoch": 0.4810281517747858, "percentage": 48.16, "elapsed_time": "0:48:30", "remaining_time": "0:52:13"}
+{"current_steps": 132, "total_steps": 272, "loss": 0.5545, "lr": 6.14843871065898e-05, "epoch": 0.4847001223990208, "percentage": 48.53, "elapsed_time": "0:48:48", "remaining_time": "0:51:46"}
+{"current_steps": 133, "total_steps": 272, "loss": 0.3225, "lr": 6.0856895097098934e-05, "epoch": 0.4883720930232558, "percentage": 48.9, "elapsed_time": "0:49:15", "remaining_time": "0:51:29"}
+{"current_steps": 134, "total_steps": 272, "loss": 0.4317, "lr": 6.022760330631005e-05, "epoch": 0.4920440636474908, "percentage": 49.26, "elapsed_time": "0:49:44", "remaining_time": "0:51:13"}
+{"current_steps": 135, "total_steps": 272, "loss": 0.3251, "lr": 5.9596616053882295e-05, "epoch": 0.49571603427172584, "percentage": 49.63, "elapsed_time": "0:50:07", "remaining_time": "0:50:51"}
+{"current_steps": 136, "total_steps": 272, "loss": 0.63, "lr": 5.896403794053679e-05, "epoch": 0.49938800489596086, "percentage": 50.0, "elapsed_time": "0:50:32", "remaining_time": "0:50:32"}
+{"current_steps": 137, "total_steps": 272, "loss": 0.481, "lr": 5.83299738307166e-05, "epoch": 0.5030599755201959, "percentage": 50.37, "elapsed_time": "0:50:55", "remaining_time": "0:50:10"}
+{"current_steps": 138, "total_steps": 272, "loss": 0.4922, "lr": 5.76945288352031e-05, "epoch": 0.5067319461444308, "percentage": 50.74, "elapsed_time": "0:51:21", "remaining_time": "0:49:51"}
+{"current_steps": 139, "total_steps": 272, "loss": 0.381, "lr": 5.70578082936913e-05, "epoch": 0.5104039167686658, "percentage": 51.1, "elapsed_time": "0:51:46", "remaining_time": "0:49:32"}
+{"current_steps": 140, "total_steps": 272, "loss": 0.5921, "lr": 5.6419917757327555e-05, "epoch": 0.5140758873929009, "percentage": 51.47, "elapsed_time": "0:52:06", "remaining_time": "0:49:07"}
+{"current_steps": 141, "total_steps": 272, "loss": 0.6962, "lr": 5.5780962971211795e-05, "epoch": 0.5177478580171359, "percentage": 51.84, "elapsed_time": "0:52:31", "remaining_time": "0:48:47"}
+{"current_steps": 142, "total_steps": 272, "loss": 0.6109, "lr": 5.514104985686802e-05, "epoch": 0.5214198286413708, "percentage": 52.21, "elapsed_time": "0:52:45", "remaining_time": "0:48:17"}
+{"current_steps": 143, "total_steps": 272, "loss": 0.2542, "lr": 5.450028449468527e-05, "epoch": 0.5250917992656059, "percentage": 52.57, "elapsed_time": "0:53:14", "remaining_time": "0:48:01"}
+{"current_steps": 144, "total_steps": 272, "loss": 0.6507, "lr": 5.385877310633233e-05, "epoch": 0.5287637698898409, "percentage": 52.94, "elapsed_time": "0:53:40", "remaining_time": "0:47:42"}
+{"current_steps": 145, "total_steps": 272, "loss": 0.399, "lr": 5.321662203714909e-05, "epoch": 0.5324357405140759, "percentage": 53.31, "elapsed_time": "0:53:58", "remaining_time": "0:47:16"}
+{"current_steps": 146, "total_steps": 272, "loss": 0.4017, "lr": 5.257393773851733e-05, "epoch": 0.5361077111383109, "percentage": 53.68, "elapsed_time": "0:54:21", "remaining_time": "0:46:54"}
+{"current_steps": 147, "total_steps": 272, "loss": 0.3849, "lr": 5.193082675021392e-05, "epoch": 0.5397796817625459, "percentage": 54.04, "elapsed_time": "0:54:45", "remaining_time": "0:46:33"}
+{"current_steps": 148, "total_steps": 272, "loss": 0.5905, "lr": 5.128739568274944e-05, "epoch": 0.543451652386781, "percentage": 54.41, "elapsed_time": "0:55:05", "remaining_time": "0:46:09"}
+{"current_steps": 149, "total_steps": 272, "loss": 0.2895, "lr": 5.064375119969491e-05, "epoch": 0.5471236230110159, "percentage": 54.78, "elapsed_time": "0:55:25", "remaining_time": "0:45:45"}
+{"current_steps": 150, "total_steps": 272, "loss": 0.3632, "lr": 5e-05, "epoch": 0.5507955936352509, "percentage": 55.15, "elapsed_time": "0:55:52", "remaining_time": "0:45:26"}
+{"current_steps": 151, "total_steps": 272, "loss": 0.7068, "lr": 4.9356248800305106e-05, "epoch": 0.554467564259486, "percentage": 55.51, "elapsed_time": "0:56:19", "remaining_time": "0:45:07"}
+{"current_steps": 152, "total_steps": 272, "loss": 0.3605, "lr": 4.8712604317250576e-05, "epoch": 0.5581395348837209, "percentage": 55.88, "elapsed_time": "0:56:39", "remaining_time": "0:44:43"}
+{"current_steps": 153, "total_steps": 272, "loss": 0.2476, "lr": 4.806917324978608e-05, "epoch": 0.5618115055079559, "percentage": 56.25, "elapsed_time": "0:56:52", "remaining_time": "0:44:14"}
+{"current_steps": 154, "total_steps": 272, "loss": 0.5039, "lr": 4.7426062261482675e-05, "epoch": 0.565483476132191, "percentage": 56.62, "elapsed_time": "0:57:16", "remaining_time": "0:43:53"}
+{"current_steps": 155, "total_steps": 272, "loss": 0.5615, "lr": 4.678337796285092e-05, "epoch": 0.5691554467564259, "percentage": 56.99, "elapsed_time": "0:57:49", "remaining_time": "0:43:38"}
+{"current_steps": 156, "total_steps": 272, "loss": 0.6, "lr": 4.6141226893667684e-05, "epoch": 0.572827417380661, "percentage": 57.35, "elapsed_time": "0:58:13", "remaining_time": "0:43:17"}
+{"current_steps": 157, "total_steps": 272, "loss": 0.4833, "lr": 4.5499715505314745e-05, "epoch": 0.576499388004896, "percentage": 57.72, "elapsed_time": "0:58:41", "remaining_time": "0:42:59"}
+{"current_steps": 158, "total_steps": 272, "loss": 0.5044, "lr": 4.4858950143131975e-05, "epoch": 0.5801713586291309, "percentage": 58.09, "elapsed_time": "0:59:04", "remaining_time": "0:42:37"}
+{"current_steps": 159, "total_steps": 272, "loss": 0.6077, "lr": 4.4219037028788216e-05, "epoch": 0.583843329253366, "percentage": 58.46, "elapsed_time": "0:59:28", "remaining_time": "0:42:16"}
+{"current_steps": 160, "total_steps": 272, "loss": 0.2877, "lr": 4.358008224267245e-05, "epoch": 0.587515299877601, "percentage": 58.82, "elapsed_time": "0:59:44", "remaining_time": "0:41:49"}
+{"current_steps": 161, "total_steps": 272, "loss": 0.4462, "lr": 4.29421917063087e-05, "epoch": 0.591187270501836, "percentage": 59.19, "elapsed_time": "1:00:07", "remaining_time": "0:41:27"}
+{"current_steps": 162, "total_steps": 272, "loss": 0.3803, "lr": 4.2305471164796905e-05, "epoch": 0.594859241126071, "percentage": 59.56, "elapsed_time": "1:00:32", "remaining_time": "0:41:06"}
+{"current_steps": 163, "total_steps": 272, "loss": 0.4625, "lr": 4.167002616928341e-05, "epoch": 0.598531211750306, "percentage": 59.93, "elapsed_time": "1:00:47", "remaining_time": "0:40:39"}
+{"current_steps": 164, "total_steps": 272, "loss": 0.615, "lr": 4.103596205946323e-05, "epoch": 0.602203182374541, "percentage": 60.29, "elapsed_time": "1:01:15", "remaining_time": "0:40:20"}
+{"current_steps": 165, "total_steps": 272, "loss": 0.6253, "lr": 4.0403383946117717e-05, "epoch": 0.605875152998776, "percentage": 60.66, "elapsed_time": "1:01:37", "remaining_time": "0:39:58"}
+{"current_steps": 166, "total_steps": 272, "loss": 0.4052, "lr": 3.977239669368997e-05, "epoch": 0.609547123623011, "percentage": 61.03, "elapsed_time": "1:01:59", "remaining_time": "0:39:35"}
+{"current_steps": 167, "total_steps": 272, "loss": 0.9142, "lr": 3.9143104902901085e-05, "epoch": 0.6132190942472461, "percentage": 61.4, "elapsed_time": "1:02:19", "remaining_time": "0:39:11"}
+{"current_steps": 168, "total_steps": 272, "loss": 0.4136, "lr": 3.851561289341023e-05, "epoch": 0.616891064871481, "percentage": 61.76, "elapsed_time": "1:02:44", "remaining_time": "0:38:50"}
+{"current_steps": 169, "total_steps": 272, "loss": 0.5657, "lr": 3.789002468652121e-05, "epoch": 0.620563035495716, "percentage": 62.13, "elapsed_time": "1:03:09", "remaining_time": "0:38:29"}
+{"current_steps": 170, "total_steps": 272, "loss": 0.3279, "lr": 3.726644398793857e-05, "epoch": 0.6242350061199511, "percentage": 62.5, "elapsed_time": "1:03:36", "remaining_time": "0:38:09"}
+{"current_steps": 171, "total_steps": 272, "loss": 0.62, "lr": 3.664497417057591e-05, "epoch": 0.627906976744186, "percentage": 62.87, "elapsed_time": "1:03:55", "remaining_time": "0:37:45"}
+{"current_steps": 172, "total_steps": 272, "loss": 0.8179, "lr": 3.602571825741953e-05, "epoch": 0.631578947368421, "percentage": 63.24, "elapsed_time": "1:04:20", "remaining_time": "0:37:24"}
+{"current_steps": 173, "total_steps": 272, "loss": 0.5163, "lr": 3.540877890444989e-05, "epoch": 0.6352509179926561, "percentage": 63.6, "elapsed_time": "1:04:42", "remaining_time": "0:37:01"}
+{"current_steps": 174, "total_steps": 272, "loss": 0.4173, "lr": 3.4794258383624114e-05, "epoch": 0.6389228886168911, "percentage": 63.97, "elapsed_time": "1:04:59", "remaining_time": "0:36:36"}
+{"current_steps": 175, "total_steps": 272, "loss": 0.5455, "lr": 3.4182258565921934e-05, "epoch": 0.642594859241126, "percentage": 64.34, "elapsed_time": "1:05:27", "remaining_time": "0:36:16"}
+{"current_steps": 176, "total_steps": 272, "loss": 0.5327, "lr": 3.357288090445827e-05, "epoch": 0.6462668298653611, "percentage": 64.71, "elapsed_time": "1:05:47", "remaining_time": "0:35:53"}
+{"current_steps": 177, "total_steps": 272, "loss": 0.5541, "lr": 3.296622641766512e-05, "epoch": 0.6499388004895961, "percentage": 65.07, "elapsed_time": "1:06:07", "remaining_time": "0:35:29"}
+{"current_steps": 178, "total_steps": 272, "loss": 0.4312, "lr": 3.236239567254526e-05, "epoch": 0.653610771113831, "percentage": 65.44, "elapsed_time": "1:06:30", "remaining_time": "0:35:07"}
+{"current_steps": 179, "total_steps": 272, "loss": 0.8246, "lr": 3.1761488768001085e-05, "epoch": 0.6572827417380661, "percentage": 65.81, "elapsed_time": "1:06:52", "remaining_time": "0:34:44"}
+{"current_steps": 180, "total_steps": 272, "loss": 0.5633, "lr": 3.116360531824074e-05, "epoch": 0.6609547123623011, "percentage": 66.18, "elapsed_time": "1:07:16", "remaining_time": "0:34:23"}
+{"current_steps": 181, "total_steps": 272, "loss": 0.6657, "lr": 3.056884443626499e-05, "epoch": 0.6646266829865362, "percentage": 66.54, "elapsed_time": "1:07:36", "remaining_time": "0:33:59"}
+{"current_steps": 182, "total_steps": 272, "loss": 0.6332, "lr": 2.9977304717436672e-05, "epoch": 0.6682986536107711, "percentage": 66.91, "elapsed_time": "1:08:01", "remaining_time": "0:33:38"}
+{"current_steps": 183, "total_steps": 272, "loss": 0.4556, "lr": 2.938908422313652e-05, "epoch": 0.6719706242350061, "percentage": 67.28, "elapsed_time": "1:08:22", "remaining_time": "0:33:15"}
+{"current_steps": 184, "total_steps": 272, "loss": 0.3345, "lr": 2.8804280464506973e-05, "epoch": 0.6756425948592412, "percentage": 67.65, "elapsed_time": "1:08:41", "remaining_time": "0:32:51"}
+{"current_steps": 185, "total_steps": 272, "loss": 0.4235, "lr": 2.8222990386287617e-05, "epoch": 0.6793145654834761, "percentage": 68.01, "elapsed_time": "1:09:05", "remaining_time": "0:32:29"}
+{"current_steps": 186, "total_steps": 272, "loss": 0.485, "lr": 2.7645310350744297e-05, "epoch": 0.6829865361077111, "percentage": 68.38, "elapsed_time": "1:09:28", "remaining_time": "0:32:07"}
+{"current_steps": 187, "total_steps": 272, "loss": 0.3384, "lr": 2.7071336121694858e-05, "epoch": 0.6866585067319462, "percentage": 68.75, "elapsed_time": "1:09:52", "remaining_time": "0:31:45"}
+{"current_steps": 188, "total_steps": 272, "loss": 0.9103, "lr": 2.650116284863402e-05, "epoch": 0.6903304773561811, "percentage": 69.12, "elapsed_time": "1:10:19", "remaining_time": "0:31:25"}
+{"current_steps": 189, "total_steps": 272, "loss": 0.5258, "lr": 2.5934885050960182e-05, "epoch": 0.6940024479804161, "percentage": 69.49, "elapsed_time": "1:10:45", "remaining_time": "0:31:04"}
+{"current_steps": 190, "total_steps": 272, "loss": 0.4817, "lr": 2.5372596602306786e-05, "epoch": 0.6976744186046512, "percentage": 69.85, "elapsed_time": "1:11:09", "remaining_time": "0:30:42"}
+{"current_steps": 191, "total_steps": 272, "loss": 0.4289, "lr": 2.4814390714980325e-05, "epoch": 0.7013463892288861, "percentage": 70.22, "elapsed_time": "1:11:29", "remaining_time": "0:30:19"}
+{"current_steps": 192, "total_steps": 272, "loss": 0.4383, "lr": 2.426035992450848e-05, "epoch": 0.7050183598531212, "percentage": 70.59, "elapsed_time": "1:11:53", "remaining_time": "0:29:57"}
+{"current_steps": 193, "total_steps": 272, "loss": 0.7566, "lr": 2.3710596074300045e-05, "epoch": 0.7086903304773562, "percentage": 70.96, "elapsed_time": "1:12:17", "remaining_time": "0:29:35"}
+{"current_steps": 194, "total_steps": 272, "loss": 0.4648, "lr": 2.316519030041998e-05, "epoch": 0.7123623011015912, "percentage": 71.32, "elapsed_time": "1:12:41", "remaining_time": "0:29:13"}
+{"current_steps": 195, "total_steps": 272, "loss": 0.668, "lr": 2.262423301648122e-05, "epoch": 0.7160342717258262, "percentage": 71.69, "elapsed_time": "1:12:58", "remaining_time": "0:28:49"}
+{"current_steps": 196, "total_steps": 272, "loss": 0.4397, "lr": 2.2087813898656774e-05, "epoch": 0.7197062423500612, "percentage": 72.06, "elapsed_time": "1:13:17", "remaining_time": "0:28:24"}
+{"current_steps": 197, "total_steps": 272, "loss": 0.685, "lr": 2.1556021870813654e-05, "epoch": 0.7233782129742962, "percentage": 72.43, "elapsed_time": "1:13:36", "remaining_time": "0:28:01"}
+{"current_steps": 198, "total_steps": 272, "loss": 0.2627, "lr": 2.102894508977182e-05, "epoch": 0.7270501835985312, "percentage": 72.79, "elapsed_time": "1:13:48", "remaining_time": "0:27:35"}
+{"current_steps": 199, "total_steps": 272, "loss": 0.3164, "lr": 2.0506670930690074e-05, "epoch": 0.7307221542227662, "percentage": 73.16, "elapsed_time": "1:14:13", "remaining_time": "0:27:13"}
+{"current_steps": 200, "total_steps": 272, "loss": 0.4444, "lr": 1.9989285972581595e-05, "epoch": 0.7343941248470012, "percentage": 73.53, "elapsed_time": "1:14:37", "remaining_time": "0:26:51"}
+{"current_steps": 201, "total_steps": 272, "loss": 0.8168, "lr": 1.947687598396154e-05, "epoch": 0.7380660954712362, "percentage": 73.9, "elapsed_time": "1:15:00", "remaining_time": "0:26:29"}
+{"current_steps": 202, "total_steps": 272, "loss": 0.3696, "lr": 1.896952590862886e-05, "epoch": 0.7417380660954712, "percentage": 74.26, "elapsed_time": "1:15:19", "remaining_time": "0:26:06"}
+{"current_steps": 203, "total_steps": 272, "loss": 0.3903, "lr": 1.8467319851584954e-05, "epoch": 0.7454100367197063, "percentage": 74.63, "elapsed_time": "1:15:39", "remaining_time": "0:25:42"}
+{"current_steps": 204, "total_steps": 272, "loss": 0.5486, "lr": 1.7970341065091245e-05, "epoch": 0.7490820073439413, "percentage": 75.0, "elapsed_time": "1:16:01", "remaining_time": "0:25:20"}
+{"current_steps": 205, "total_steps": 272, "loss": 0.4969, "lr": 1.7478671934868302e-05, "epoch": 0.7527539779681762, "percentage": 75.37, "elapsed_time": "1:16:22", "remaining_time": "0:24:57"}
+{"current_steps": 206, "total_steps": 272, "loss": 0.6211, "lr": 1.6992393966438407e-05, "epoch": 0.7564259485924113, "percentage": 75.74, "elapsed_time": "1:16:47", "remaining_time": "0:24:36"}
+{"current_steps": 207, "total_steps": 272, "loss": 0.3785, "lr": 1.6511587771614205e-05, "epoch": 0.7600979192166463, "percentage": 76.1, "elapsed_time": "1:17:11", "remaining_time": "0:24:14"}
+{"current_steps": 208, "total_steps": 272, "loss": 0.4173, "lr": 1.6036333055135344e-05, "epoch": 0.7637698898408812, "percentage": 76.47, "elapsed_time": "1:17:36", "remaining_time": "0:23:52"}
+{"current_steps": 209, "total_steps": 272, "loss": 0.7029, "lr": 1.556670860145567e-05, "epoch": 0.7674418604651163, "percentage": 76.84, "elapsed_time": "1:17:54", "remaining_time": "0:23:29"}
+{"current_steps": 210, "total_steps": 272, "loss": 0.4614, "lr": 1.5102792261682813e-05, "epoch": 0.7711138310893513, "percentage": 77.21, "elapsed_time": "1:18:09", "remaining_time": "0:23:04"}
+{"current_steps": 211, "total_steps": 272, "loss": 0.8333, "lr": 1.4644660940672627e-05, "epoch": 0.7747858017135862, "percentage": 77.57, "elapsed_time": "1:18:34", "remaining_time": "0:22:42"}
+{"current_steps": 212, "total_steps": 272, "loss": 0.3017, "lr": 1.4192390584280346e-05, "epoch": 0.7784577723378213, "percentage": 77.94, "elapsed_time": "1:18:55", "remaining_time": "0:22:20"}
+{"current_steps": 213, "total_steps": 272, "loss": 0.304, "lr": 1.374605616677087e-05, "epoch": 0.7821297429620563, "percentage": 78.31, "elapsed_time": "1:19:15", "remaining_time": "0:21:57"}
+{"current_steps": 214, "total_steps": 272, "loss": 0.4155, "lr": 1.3305731678390048e-05, "epoch": 0.7858017135862914, "percentage": 78.68, "elapsed_time": "1:19:37", "remaining_time": "0:21:34"}
+{"current_steps": 215, "total_steps": 272, "loss": 0.7763, "lr": 1.2871490113099066e-05, "epoch": 0.7894736842105263, "percentage": 79.04, "elapsed_time": "1:20:05", "remaining_time": "0:21:13"}
+{"current_steps": 216, "total_steps": 272, "loss": 0.5421, "lr": 1.2443403456474017e-05, "epoch": 0.7931456548347613, "percentage": 79.41, "elapsed_time": "1:20:20", "remaining_time": "0:20:49"}
+{"current_steps": 217, "total_steps": 272, "loss": 0.3638, "lr": 1.2021542673772585e-05, "epoch": 0.7968176254589964, "percentage": 79.78, "elapsed_time": "1:20:50", "remaining_time": "0:20:29"}
+{"current_steps": 218, "total_steps": 272, "loss": 0.5641, "lr": 1.1605977698170001e-05, "epoch": 0.8004895960832313, "percentage": 80.15, "elapsed_time": "1:21:14", "remaining_time": "0:20:07"}
+{"current_steps": 219, "total_steps": 272, "loss": 0.407, "lr": 1.1196777419165927e-05, "epoch": 0.8041615667074663, "percentage": 80.51, "elapsed_time": "1:21:40", "remaining_time": "0:19:45"}
+{"current_steps": 220, "total_steps": 272, "loss": 0.8802, "lr": 1.0794009671164484e-05, "epoch": 0.8078335373317014, "percentage": 80.88, "elapsed_time": "1:22:05", "remaining_time": "0:19:24"}
+{"current_steps": 221, "total_steps": 272, "loss": 0.5714, "lr": 1.0397741222229057e-05, "epoch": 0.8115055079559363, "percentage": 81.25, "elapsed_time": "1:22:25", "remaining_time": "0:19:01"}
+{"current_steps": 222, "total_steps": 272, "loss": 0.4146, "lr": 1.0008037763014032e-05, "epoch": 0.8151774785801713, "percentage": 81.62, "elapsed_time": "1:22:47", "remaining_time": "0:18:38"}
+{"current_steps": 223, "total_steps": 272, "loss": 0.4979, "lr": 9.624963895874994e-06, "epoch": 0.8188494492044064, "percentage": 81.99, "elapsed_time": "1:23:07", "remaining_time": "0:18:16"}
+{"current_steps": 224, "total_steps": 272, "loss": 0.7919, "lr": 9.248583124159438e-06, "epoch": 0.8225214198286414, "percentage": 82.35, "elapsed_time": "1:23:34", "remaining_time": "0:17:54"}
+{"current_steps": 225, "total_steps": 272, "loss": 0.4572, "lr": 8.878957841679541e-06, "epoch": 0.8261933904528764, "percentage": 82.72, "elapsed_time": "1:23:52", "remaining_time": "0:17:31"}
+{"current_steps": 226, "total_steps": 272, "loss": 0.3024, "lr": 8.516149322369054e-06, "epoch": 0.8298653610771114, "percentage": 83.09, "elapsed_time": "1:24:10", "remaining_time": "0:17:07"}
+{"current_steps": 227, "total_steps": 272, "loss": 0.5087, "lr": 8.160217710125662e-06, "epoch": 0.8335373317013464, "percentage": 83.46, "elapsed_time": "1:24:33", "remaining_time": "0:16:45"}
+{"current_steps": 228, "total_steps": 272, "loss": 0.4048, "lr": 7.81122200884072e-06, "epoch": 0.8372093023255814, "percentage": 83.82, "elapsed_time": "1:24:48", "remaining_time": "0:16:22"}
+{"current_steps": 229, "total_steps": 272, "loss": 0.4902, "lr": 7.469220072618094e-06, "epoch": 0.8408812729498164, "percentage": 84.19, "elapsed_time": "1:25:07", "remaining_time": "0:15:59"}
+{"current_steps": 230, "total_steps": 272, "loss": 0.2719, "lr": 7.13426859618338e-06, "epoch": 0.8445532435740514, "percentage": 84.56, "elapsed_time": "1:25:27", "remaining_time": "0:15:36"}
+{"current_steps": 231, "total_steps": 272, "loss": 0.3147, "lr": 6.806423105485577e-06, "epoch": 0.8482252141982864, "percentage": 84.93, "elapsed_time": "1:25:47", "remaining_time": "0:15:13"}
+{"current_steps": 232, "total_steps": 272, "loss": 0.5688, "lr": 6.4857379484922375e-06, "epoch": 0.8518971848225214, "percentage": 85.29, "elapsed_time": "1:26:11", "remaining_time": "0:14:51"}
+{"current_steps": 233, "total_steps": 272, "loss": 0.3724, "lr": 6.1722662861801614e-06, "epoch": 0.8555691554467564, "percentage": 85.66, "elapsed_time": "1:26:39", "remaining_time": "0:14:30"}
+{"current_steps": 234, "total_steps": 272, "loss": 0.6448, "lr": 5.866060083722624e-06, "epoch": 0.8592411260709915, "percentage": 86.03, "elapsed_time": "1:27:05", "remaining_time": "0:14:08"}
+{"current_steps": 235, "total_steps": 272, "loss": 0.7383, "lr": 5.5671701018750745e-06, "epoch": 0.8629130966952264, "percentage": 86.4, "elapsed_time": "1:27:29", "remaining_time": "0:13:46"}
+{"current_steps": 236, "total_steps": 272, "loss": 0.3452, "lr": 5.275645888560232e-06, "epoch": 0.8665850673194615, "percentage": 86.76, "elapsed_time": "1:27:45", "remaining_time": "0:13:23"}
+{"current_steps": 237, "total_steps": 272, "loss": 0.3893, "lr": 4.9915357706544485e-06, "epoch": 0.8702570379436965, "percentage": 87.13, "elapsed_time": "1:28:10", "remaining_time": "0:13:01"}
+{"current_steps": 238, "total_steps": 272, "loss": 0.2986, "lr": 4.714886845976429e-06, "epoch": 0.8739290085679314, "percentage": 87.5, "elapsed_time": "1:28:35", "remaining_time": "0:12:39"}
+{"current_steps": 239, "total_steps": 272, "loss": 0.4395, "lr": 4.445744975479626e-06, "epoch": 0.8776009791921665, "percentage": 87.87, "elapsed_time": "1:28:59", "remaining_time": "0:12:17"}
+{"current_steps": 240, "total_steps": 272, "loss": 0.2981, "lr": 4.184154775649768e-06, "epoch": 0.8812729498164015, "percentage": 88.24, "elapsed_time": "1:29:22", "remaining_time": "0:11:55"}
+{"current_steps": 241, "total_steps": 272, "loss": 0.5546, "lr": 3.9301596111086025e-06, "epoch": 0.8849449204406364, "percentage": 88.6, "elapsed_time": "1:29:45", "remaining_time": "0:11:32"}
+{"current_steps": 242, "total_steps": 272, "loss": 0.4488, "lr": 3.683801587425251e-06, "epoch": 0.8886168910648715, "percentage": 88.97, "elapsed_time": "1:30:06", "remaining_time": "0:11:10"}
+{"current_steps": 243, "total_steps": 272, "loss": 0.5273, "lr": 3.4451215441362263e-06, "epoch": 0.8922888616891065, "percentage": 89.34, "elapsed_time": "1:30:32", "remaining_time": "0:10:48"}
+{"current_steps": 244, "total_steps": 272, "loss": 0.6317, "lr": 3.2141590479753236e-06, "epoch": 0.8959608323133414, "percentage": 89.71, "elapsed_time": "1:30:58", "remaining_time": "0:10:26"}
+{"current_steps": 245, "total_steps": 272, "loss": 0.5092, "lr": 2.990952386314505e-06, "epoch": 0.8996328029375765, "percentage": 90.07, "elapsed_time": "1:31:23", "remaining_time": "0:10:04"}
+{"current_steps": 246, "total_steps": 272, "loss": 0.5734, "lr": 2.775538560816937e-06, "epoch": 0.9033047735618115, "percentage": 90.44, "elapsed_time": "1:31:41", "remaining_time": "0:09:41"}
+{"current_steps": 247, "total_steps": 272, "loss": 0.535, "lr": 2.5679532813030596e-06, "epoch": 0.9069767441860465, "percentage": 90.81, "elapsed_time": "1:32:06", "remaining_time": "0:09:19"}
+{"current_steps": 248, "total_steps": 272, "loss": 0.5474, "lr": 2.3682309598308747e-06, "epoch": 0.9106487148102815, "percentage": 91.18, "elapsed_time": "1:32:38", "remaining_time": "0:08:57"}
+{"current_steps": 249, "total_steps": 272, "loss": 0.3862, "lr": 2.1764047049913527e-06, "epoch": 0.9143206854345165, "percentage": 91.54, "elapsed_time": "1:33:02", "remaining_time": "0:08:35"}
+{"current_steps": 250, "total_steps": 272, "loss": 0.3631, "lr": 1.992506316419912e-06, "epoch": 0.9179926560587516, "percentage": 91.91, "elapsed_time": "1:33:21", "remaining_time": "0:08:12"}
+{"current_steps": 251, "total_steps": 272, "loss": 0.2861, "lr": 1.8165662795249172e-06, "epoch": 0.9216646266829865, "percentage": 92.28, "elapsed_time": "1:33:42", "remaining_time": "0:07:50"}
+{"current_steps": 252, "total_steps": 272, "loss": 0.6115, "lr": 1.6486137604339813e-06, "epoch": 0.9253365973072215, "percentage": 92.65, "elapsed_time": "1:34:03", "remaining_time": "0:07:27"}
+{"current_steps": 253, "total_steps": 272, "loss": 0.6009, "lr": 1.4886766011590448e-06, "epoch": 0.9290085679314566, "percentage": 93.01, "elapsed_time": "1:34:24", "remaining_time": "0:07:05"}
+{"current_steps": 254, "total_steps": 272, "loss": 0.5147, "lr": 1.3367813149808729e-06, "epoch": 0.9326805385556916, "percentage": 93.38, "elapsed_time": "1:34:46", "remaining_time": "0:06:42"}
+{"current_steps": 255, "total_steps": 272, "loss": 0.3699, "lr": 1.1929530820539269e-06, "epoch": 0.9363525091799265, "percentage": 93.75, "elapsed_time": "1:35:11", "remaining_time": "0:06:20"}
+{"current_steps": 256, "total_steps": 272, "loss": 0.4612, "lr": 1.0572157452321097e-06, "epoch": 0.9400244798041616, "percentage": 94.12, "elapsed_time": "1:35:37", "remaining_time": "0:05:58"}
+{"current_steps": 257, "total_steps": 272, "loss": 0.3989, "lr": 9.295918061163033e-07, "epoch": 0.9436964504283966, "percentage": 94.49, "elapsed_time": "1:36:09", "remaining_time": "0:05:36"}
+{"current_steps": 258, "total_steps": 272, "loss": 0.7361, "lr": 8.101024213241826e-07, "epoch": 0.9473684210526315, "percentage": 94.85, "elapsed_time": "1:36:28", "remaining_time": "0:05:14"}
+{"current_steps": 259, "total_steps": 272, "loss": 0.356, "lr": 6.987673989830523e-07, "epoch": 0.9510403916768666, "percentage": 95.22, "elapsed_time": "1:36:53", "remaining_time": "0:04:51"}
+{"current_steps": 260, "total_steps": 272, "loss": 0.5988, "lr": 5.956051954461472e-07, "epoch": 0.9547123623011016, "percentage": 95.59, "elapsed_time": "1:37:10", "remaining_time": "0:04:29"}
+{"current_steps": 261, "total_steps": 272, "loss": 0.6091, "lr": 5.006329122330899e-07, "epoch": 0.9583843329253366, "percentage": 95.96, "elapsed_time": "1:37:34", "remaining_time": "0:04:06"}
+{"current_steps": 262, "total_steps": 272, "loss": 0.5726, "lr": 4.1386629319492556e-07, "epoch": 0.9620563035495716, "percentage": 96.32, "elapsed_time": "1:37:57", "remaining_time": "0:03:44"}
+{"current_steps": 263, "total_steps": 272, "loss": 0.2667, "lr": 3.3531972190419815e-07, "epoch": 0.9657282741738066, "percentage": 96.69, "elapsed_time": "1:38:11", "remaining_time": "0:03:21"}
+{"current_steps": 264, "total_steps": 272, "loss": 0.2876, "lr": 2.6500621927054715e-07, "epoch": 0.9694002447980417, "percentage": 97.06, "elapsed_time": "1:38:31", "remaining_time": "0:02:59"}
+{"current_steps": 265, "total_steps": 272, "loss": 0.3169, "lr": 2.0293744138219495e-07, "epoch": 0.9730722154222766, "percentage": 97.43, "elapsed_time": "1:38:47", "remaining_time": "0:02:36"}
+{"current_steps": 266, "total_steps": 272, "loss": 0.3369, "lr": 1.4912367757366487e-07, "epoch": 0.9767441860465116, "percentage": 97.79, "elapsed_time": "1:39:08", "remaining_time": "0:02:14"}
+{"current_steps": 267, "total_steps": 272, "loss": 0.2544, "lr": 1.0357384872011766e-07, "epoch": 0.9804161566707467, "percentage": 98.16, "elapsed_time": "1:39:28", "remaining_time": "0:01:51"}
+{"current_steps": 268, "total_steps": 272, "loss": 0.9444, "lr": 6.629550575847354e-08, "epoch": 0.9840881272949816, "percentage": 98.53, "elapsed_time": "1:39:58", "remaining_time": "0:01:29"}
+{"current_steps": 269, "total_steps": 272, "loss": 0.5641, "lr": 3.729482843569665e-08, "epoch": 0.9877600979192166, "percentage": 98.9, "elapsed_time": "1:40:24", "remaining_time": "0:01:07"}
+{"current_steps": 270, "total_steps": 272, "loss": 0.3192, "lr": 1.6576624284347918e-08, "epoch": 0.9914320685434517, "percentage": 99.26, "elapsed_time": "1:40:51", "remaining_time": "0:00:44"}
+{"current_steps": 271, "total_steps": 272, "loss": 0.6975, "lr": 4.1443278256170226e-09, "epoch": 0.9951040391676866, "percentage": 99.63, "elapsed_time": "1:41:14", "remaining_time": "0:00:22"}
+{"current_steps": 272, "total_steps": 272, "loss": 0.4445, "lr": 0.0, "epoch": 0.9987760097919217, "percentage": 100.0, "elapsed_time": "1:41:37", "remaining_time": "0:00:00"}
+{"current_steps": 272, "total_steps": 272, "epoch": 0.9987760097919217, "percentage": 100.0, "elapsed_time": "1:41:37", "remaining_time": "0:00:00"}

adapter/trainer_state.json

@@ -0,0 +1,1946 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9987760097919217,
+  "eval_steps": 500,
+  "global_step": 272,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0036719706242350062,
+      "grad_norm": 0.03811819851398468,
+      "learning_rate": 3.5714285714285714e-06,
+      "loss": 0.4568,
+      "step": 1
+    },
+    {
+      "epoch": 0.0073439412484700125,
+      "grad_norm": 0.037763386964797974,
+      "learning_rate": 7.142857142857143e-06,
+      "loss": 0.7457,
+      "step": 2
+    },
+    {
+      "epoch": 0.011015911872705019,
+      "grad_norm": 0.03825872391462326,
+      "learning_rate": 1.0714285714285714e-05,
+      "loss": 0.3669,
+      "step": 3
+    },
+    {
+      "epoch": 0.014687882496940025,
+      "grad_norm": 0.03575674816966057,
+      "learning_rate": 1.4285714285714285e-05,
+      "loss": 0.4611,
+      "step": 4
+    },
+    {
+      "epoch": 0.01835985312117503,
+      "grad_norm": 0.048165928572416306,
+      "learning_rate": 1.785714285714286e-05,
+      "loss": 0.3727,
+      "step": 5
+    },
+    {
+      "epoch": 0.022031823745410038,
+      "grad_norm": 0.042961642146110535,
+      "learning_rate": 2.1428571428571428e-05,
+      "loss": 0.3609,
+      "step": 6
+    },
+    {
+      "epoch": 0.025703794369645042,
+      "grad_norm": 0.10260031372308731,
+      "learning_rate": 2.5e-05,
+      "loss": 0.8697,
+      "step": 7
+    },
+    {
+      "epoch": 0.02937576499388005,
+      "grad_norm": 0.06274840980768204,
+      "learning_rate": 2.857142857142857e-05,
+      "loss": 0.521,
+      "step": 8
+    },
+    {
+      "epoch": 0.033047735618115054,
+      "grad_norm": 0.10686090588569641,
+      "learning_rate": 3.2142857142857144e-05,
+      "loss": 0.676,
+      "step": 9
+    },
+    {
+      "epoch": 0.03671970624235006,
+      "grad_norm": 0.05962346866726875,
+      "learning_rate": 3.571428571428572e-05,
+      "loss": 0.306,
+      "step": 10
+    },
+    {
+      "epoch": 0.04039167686658507,
+      "grad_norm": 0.07848496735095978,
+      "learning_rate": 3.928571428571429e-05,
+      "loss": 0.5941,
+      "step": 11
+    },
+    {
+      "epoch": 0.044063647490820076,
+      "grad_norm": 0.042250536382198334,
+      "learning_rate": 4.2857142857142856e-05,
+      "loss": 0.412,
+      "step": 12
+    },
+    {
+      "epoch": 0.04773561811505508,
+      "grad_norm": 0.07003479450941086,
+      "learning_rate": 4.642857142857143e-05,
+      "loss": 0.4988,
+      "step": 13
+    },
+    {
+      "epoch": 0.051407588739290085,
+      "grad_norm": 0.05183990299701691,
+      "learning_rate": 5e-05,
+      "loss": 0.3337,
+      "step": 14
+    },
+    {
+      "epoch": 0.05507955936352509,
+      "grad_norm": 0.04867109656333923,
+      "learning_rate": 5.3571428571428575e-05,
+      "loss": 0.424,
+      "step": 15
+    },
+    {
+      "epoch": 0.0587515299877601,
+      "grad_norm": 0.04919494688510895,
+      "learning_rate": 5.714285714285714e-05,
+      "loss": 0.3674,
+      "step": 16
+    },
+    {
+      "epoch": 0.06242350061199511,
+      "grad_norm": 0.07788144797086716,
+      "learning_rate": 6.0714285714285715e-05,
+      "loss": 0.4244,
+      "step": 17
+    },
+    {
+      "epoch": 0.06609547123623011,
+      "grad_norm": 0.08719762414693832,
+      "learning_rate": 6.428571428571429e-05,
+      "loss": 0.3832,
+      "step": 18
+    },
+    {
+      "epoch": 0.06976744186046512,
+      "grad_norm": 0.16575194895267487,
+      "learning_rate": 6.785714285714286e-05,
+      "loss": 0.7971,
+      "step": 19
+    },
+    {
+      "epoch": 0.07343941248470012,
+      "grad_norm": 0.08812964707612991,
+      "learning_rate": 7.142857142857143e-05,
+      "loss": 0.267,
+      "step": 20
+    },
+    {
+      "epoch": 0.07711138310893513,
+      "grad_norm": 0.20091792941093445,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.4959,
+      "step": 21
+    },
+    {
+      "epoch": 0.08078335373317014,
+      "grad_norm": 0.30549925565719604,
+      "learning_rate": 7.857142857142858e-05,
+      "loss": 0.6555,
+      "step": 22
+    },
+    {
+      "epoch": 0.08445532435740515,
+      "grad_norm": 0.05145212262868881,
+      "learning_rate": 8.214285714285714e-05,
+      "loss": 0.365,
+      "step": 23
+    },
+    {
+      "epoch": 0.08812729498164015,
+      "grad_norm": 0.04592301696538925,
+      "learning_rate": 8.571428571428571e-05,
+      "loss": 0.3245,
+      "step": 24
+    },
+    {
+      "epoch": 0.09179926560587515,
+      "grad_norm": 0.13516275584697723,
+      "learning_rate": 8.92857142857143e-05,
+      "loss": 0.7651,
+      "step": 25
+    },
+    {
+      "epoch": 0.09547123623011015,
+      "grad_norm": 0.10254071652889252,
+      "learning_rate": 9.285714285714286e-05,
+      "loss": 0.4515,
+      "step": 26
+    },
+    {
+      "epoch": 0.09914320685434516,
+      "grad_norm": 0.10743008553981781,
+      "learning_rate": 9.642857142857143e-05,
+      "loss": 0.853,
+      "step": 27
+    },
+    {
+      "epoch": 0.10281517747858017,
+      "grad_norm": 0.06928564608097076,
+      "learning_rate": 0.0001,
+      "loss": 0.5184,
+      "step": 28
+    },
+    {
+      "epoch": 0.10648714810281518,
+      "grad_norm": 0.11129824072122574,
+      "learning_rate": 9.999585567217439e-05,
+      "loss": 0.4656,
+      "step": 29
+    },
+    {
+      "epoch": 0.11015911872705018,
+      "grad_norm": 0.0913616195321083,
+      "learning_rate": 9.998342337571565e-05,
+      "loss": 1.1901,
+      "step": 30
+    },
+    {
+      "epoch": 0.11383108935128519,
+      "grad_norm": 0.08568678051233292,
+      "learning_rate": 9.99627051715643e-05,
+      "loss": 0.3506,
+      "step": 31
+    },
+    {
+      "epoch": 0.1175030599755202,
+      "grad_norm": 0.07405232638120651,
+      "learning_rate": 9.993370449424153e-05,
+      "loss": 0.3324,
+      "step": 32
+    },
+    {
+      "epoch": 0.1211750305997552,
+      "grad_norm": 0.07847411185503006,
+      "learning_rate": 9.98964261512799e-05,
+      "loss": 0.2745,
+      "step": 33
+    },
+    {
+      "epoch": 0.12484700122399021,
+      "grad_norm": 0.07299336791038513,
+      "learning_rate": 9.985087632242633e-05,
+      "loss": 0.5225,
+      "step": 34
+    },
+    {
+      "epoch": 0.12851897184822522,
+      "grad_norm": 0.0863344594836235,
+      "learning_rate": 9.97970625586178e-05,
+      "loss": 0.3213,
+      "step": 35
+    },
+    {
+      "epoch": 0.13219094247246022,
+      "grad_norm": 0.05981218069791794,
+      "learning_rate": 9.973499378072945e-05,
+      "loss": 0.3551,
+      "step": 36
+    },
+    {
+      "epoch": 0.13586291309669524,
+      "grad_norm": 0.07763096690177917,
+      "learning_rate": 9.966468027809582e-05,
+      "loss": 0.3264,
+      "step": 37
+    },
+    {
+      "epoch": 0.13953488372093023,
+      "grad_norm": 0.0758497565984726,
+      "learning_rate": 9.958613370680507e-05,
+      "loss": 0.397,
+      "step": 38
+    },
+    {
+      "epoch": 0.14320685434516525,
+      "grad_norm": 0.3360985517501831,
+      "learning_rate": 9.949936708776691e-05,
+      "loss": 0.9732,
+      "step": 39
+    },
+    {
+      "epoch": 0.14687882496940025,
+      "grad_norm": 0.07008073478937149,
+      "learning_rate": 9.940439480455386e-05,
+      "loss": 0.3739,
+      "step": 40
+    },
+    {
+      "epoch": 0.15055079559363524,
+      "grad_norm": 0.07435714453458786,
+      "learning_rate": 9.930123260101696e-05,
+      "loss": 0.3762,
+      "step": 41
+    },
+    {
+      "epoch": 0.15422276621787026,
+      "grad_norm": 0.3299938142299652,
+      "learning_rate": 9.918989757867583e-05,
+      "loss": 0.4278,
+      "step": 42
+    },
+    {
+      "epoch": 0.15789473684210525,
+      "grad_norm": 0.27187252044677734,
+      "learning_rate": 9.907040819388371e-05,
+      "loss": 0.478,
+      "step": 43
+    },
+    {
+      "epoch": 0.16156670746634028,
+      "grad_norm": 0.059857387095689774,
+      "learning_rate": 9.89427842547679e-05,
+      "loss": 0.3133,
+      "step": 44
+    },
+    {
+      "epoch": 0.16523867809057527,
+      "grad_norm": 0.07612061500549316,
+      "learning_rate": 9.880704691794608e-05,
+      "loss": 0.4275,
+      "step": 45
+    },
+    {
+      "epoch": 0.1689106487148103,
+      "grad_norm": 0.19199877977371216,
+      "learning_rate": 9.866321868501914e-05,
+      "loss": 0.7791,
+      "step": 46
+    },
+    {
+      "epoch": 0.17258261933904528,
+      "grad_norm": 0.1403833031654358,
+      "learning_rate": 9.851132339884096e-05,
+      "loss": 0.6251,
+      "step": 47
+    },
+    {
+      "epoch": 0.1762545899632803,
+      "grad_norm": 0.09072674065828323,
+      "learning_rate": 9.835138623956603e-05,
+      "loss": 0.4439,
+      "step": 48
+    },
+    {
+      "epoch": 0.1799265605875153,
+      "grad_norm": 0.08053342252969742,
+      "learning_rate": 9.81834337204751e-05,
+      "loss": 0.2853,
+      "step": 49
+    },
+    {
+      "epoch": 0.1835985312117503,
+      "grad_norm": 0.15429392457008362,
+      "learning_rate": 9.800749368358009e-05,
+      "loss": 0.5243,
+      "step": 50
+    },
+    {
+      "epoch": 0.18727050183598531,
+      "grad_norm": 0.10327895730733871,
+      "learning_rate": 9.782359529500867e-05,
+      "loss": 0.6096,
+      "step": 51
+    },
+    {
+      "epoch": 0.1909424724602203,
+      "grad_norm": 0.07972899079322815,
+      "learning_rate": 9.763176904016913e-05,
+      "loss": 0.4799,
+      "step": 52
+    },
+    {
+      "epoch": 0.19461444308445533,
+      "grad_norm": 0.16347306966781616,
+      "learning_rate": 9.743204671869694e-05,
+      "loss": 0.6377,
+      "step": 53
+    },
+    {
+      "epoch": 0.19828641370869032,
+      "grad_norm": 0.10270920395851135,
+      "learning_rate": 9.722446143918306e-05,
+      "loss": 0.5388,
+      "step": 54
+    },
+    {
+      "epoch": 0.20195838433292534,
+      "grad_norm": 0.08964154124259949,
+      "learning_rate": 9.70090476136855e-05,
+      "loss": 0.5875,
+      "step": 55
+    },
+    {
+      "epoch": 0.20563035495716034,
+      "grad_norm": 0.18301688134670258,
+      "learning_rate": 9.678584095202468e-05,
+      "loss": 0.3805,
+      "step": 56
+    },
+    {
+      "epoch": 0.20930232558139536,
+      "grad_norm": 0.11658929288387299,
+      "learning_rate": 9.655487845586377e-05,
+      "loss": 0.5034,
+      "step": 57
+    },
+    {
+      "epoch": 0.21297429620563035,
+      "grad_norm": 0.10647784918546677,
+      "learning_rate": 9.631619841257476e-05,
+      "loss": 0.4465,
+      "step": 58
+    },
+    {
+      "epoch": 0.21664626682986537,
+      "grad_norm": 0.08420727401971817,
+      "learning_rate": 9.60698403888914e-05,
+      "loss": 0.3717,
+      "step": 59
+    },
+    {
+      "epoch": 0.22031823745410037,
+      "grad_norm": 0.14984101057052612,
+      "learning_rate": 9.581584522435024e-05,
+      "loss": 0.5679,
+      "step": 60
+    },
+    {
+      "epoch": 0.22399020807833536,
+      "grad_norm": 0.07012059539556503,
+      "learning_rate": 9.555425502452038e-05,
+      "loss": 0.3083,
+      "step": 61
+    },
+    {
+      "epoch": 0.22766217870257038,
+      "grad_norm": 0.14937996864318848,
+      "learning_rate": 9.528511315402358e-05,
+      "loss": 0.575,
+      "step": 62
+    },
+    {
+      "epoch": 0.23133414932680538,
+      "grad_norm": 0.08581522852182388,
+      "learning_rate": 9.500846422934557e-05,
+      "loss": 0.5254,
+      "step": 63
+    },
+    {
+      "epoch": 0.2350061199510404,
+      "grad_norm": 0.21604809165000916,
+      "learning_rate": 9.472435411143978e-05,
+      "loss": 0.7045,
+      "step": 64
+    },
+    {
+      "epoch": 0.2386780905752754,
+      "grad_norm": 0.1742328703403473,
+      "learning_rate": 9.443282989812495e-05,
+      "loss": 0.6068,
+      "step": 65
+    },
+    {
+      "epoch": 0.2423500611995104,
+      "grad_norm": 0.24800752103328705,
+      "learning_rate": 9.413393991627737e-05,
+      "loss": 0.8401,
+      "step": 66
+    },
+    {
+      "epoch": 0.2460220318237454,
+      "grad_norm": 0.10994048416614532,
+      "learning_rate": 9.382773371381985e-05,
+      "loss": 0.425,
+      "step": 67
+    },
+    {
+      "epoch": 0.24969400244798043,
+      "grad_norm": 0.15951792895793915,
+      "learning_rate": 9.351426205150777e-05,
+      "loss": 0.5221,
+      "step": 68
+    },
+    {
+      "epoch": 0.2533659730722154,
+      "grad_norm": 0.20339590311050415,
+      "learning_rate": 9.319357689451443e-05,
+      "loss": 0.5302,
+      "step": 69
+    },
+    {
+      "epoch": 0.25703794369645044,
+      "grad_norm": 0.09229890257120132,
+      "learning_rate": 9.286573140381662e-05,
+      "loss": 0.3575,
+      "step": 70
+    },
+    {
+      "epoch": 0.2607099143206854,
+      "grad_norm": 0.2451619654893875,
+      "learning_rate": 9.253077992738192e-05,
+      "loss": 0.7181,
+      "step": 71
+    },
+    {
+      "epoch": 0.26438188494492043,
+      "grad_norm": 0.12739384174346924,
+      "learning_rate": 9.218877799115928e-05,
+      "loss": 0.5156,
+      "step": 72
+    },
+    {
+      "epoch": 0.26805385556915545,
+      "grad_norm": 0.08134493976831436,
+      "learning_rate": 9.183978228987436e-05,
+      "loss": 0.3,
+      "step": 73
+    },
+    {
+      "epoch": 0.2717258261933905,
+      "grad_norm": 0.11099664121866226,
+      "learning_rate": 9.148385067763095e-05,
+      "loss": 0.4198,
+      "step": 74
+    },
+    {
+      "epoch": 0.27539779681762544,
+      "grad_norm": 0.07188478857278824,
+      "learning_rate": 9.112104215832047e-05,
+      "loss": 0.3915,
+      "step": 75
+    },
+    {
+      "epoch": 0.27906976744186046,
+      "grad_norm": 0.06322924792766571,
+      "learning_rate": 9.075141687584057e-05,
+      "loss": 0.2867,
+      "step": 76
+    },
+    {
+      "epoch": 0.2827417380660955,
+      "grad_norm": 0.07251914590597153,
+      "learning_rate": 9.037503610412501e-05,
+      "loss": 0.4824,
+      "step": 77
+    },
+    {
+      "epoch": 0.2864137086903305,
+      "grad_norm": 0.2195172756910324,
+      "learning_rate": 8.999196223698599e-05,
+      "loss": 0.3936,
+      "step": 78
+    },
+    {
+      "epoch": 0.29008567931456547,
+      "grad_norm": 0.21877703070640564,
+      "learning_rate": 8.960225877777095e-05,
+      "loss": 0.4454,
+      "step": 79
+    },
+    {
+      "epoch": 0.2937576499388005,
+      "grad_norm": 0.08352579921483994,
+      "learning_rate": 8.920599032883554e-05,
+      "loss": 0.2931,
+      "step": 80
+    },
+    {
+      "epoch": 0.2974296205630355,
+      "grad_norm": 0.09364911168813705,
+      "learning_rate": 8.880322258083408e-05,
+      "loss": 0.4871,
+      "step": 81
+    },
+    {
+      "epoch": 0.3011015911872705,
+      "grad_norm": 0.07338505238294601,
+      "learning_rate": 8.839402230183e-05,
+      "loss": 0.3048,
+      "step": 82
+    },
+    {
+      "epoch": 0.3047735618115055,
+      "grad_norm": 0.1507229208946228,
+      "learning_rate": 8.797845732622743e-05,
+      "loss": 0.4948,
+      "step": 83
+    },
+    {
+      "epoch": 0.3084455324357405,
+      "grad_norm": 0.19068707525730133,
+      "learning_rate": 8.755659654352599e-05,
+      "loss": 0.6406,
+      "step": 84
+    },
+    {
+      "epoch": 0.31211750305997554,
+      "grad_norm": 0.1288161277770996,
+      "learning_rate": 8.712850988690093e-05,
+      "loss": 0.362,
+      "step": 85
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 0.07310109585523605,
+      "learning_rate": 8.669426832160996e-05,
+      "loss": 0.2735,
+      "step": 86
+    },
+    {
+      "epoch": 0.31946144430844553,
+      "grad_norm": 0.2170391082763672,
+      "learning_rate": 8.625394383322914e-05,
+      "loss": 0.6501,
+      "step": 87
+    },
+    {
+      "epoch": 0.32313341493268055,
+      "grad_norm": 0.13086941838264465,
+      "learning_rate": 8.580760941571967e-05,
+      "loss": 0.4452,
+      "step": 88
+    },
+    {
+      "epoch": 0.3268053855569155,
+      "grad_norm": 0.08146587759256363,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.3644,
+      "step": 89
+    },
+    {
+      "epoch": 0.33047735618115054,
+      "grad_norm": 0.1446744054555893,
+      "learning_rate": 8.489720773831717e-05,
+      "loss": 0.632,
+      "step": 90
+    },
+    {
+      "epoch": 0.33414932680538556,
+      "grad_norm": 0.08141674101352692,
+      "learning_rate": 8.443329139854433e-05,
+      "loss": 0.5625,
+      "step": 91
+    },
+    {
+      "epoch": 0.3378212974296206,
+      "grad_norm": 0.07421129941940308,
+      "learning_rate": 8.396366694486466e-05,
+      "loss": 0.3207,
+      "step": 92
+    },
+    {
+      "epoch": 0.34149326805385555,
+      "grad_norm": 0.345011830329895,
+      "learning_rate": 8.34884122283858e-05,
+      "loss": 0.5898,
+      "step": 93
+    },
+    {
+      "epoch": 0.34516523867809057,
+      "grad_norm": 0.12236194312572479,
+      "learning_rate": 8.300760603356159e-05,
+      "loss": 0.4658,
+      "step": 94
+    },
+    {
+      "epoch": 0.3488372093023256,
+      "grad_norm": 0.10392044484615326,
+      "learning_rate": 8.25213280651317e-05,
+      "loss": 0.4421,
+      "step": 95
+    },
+    {
+      "epoch": 0.3525091799265606,
+      "grad_norm": 0.0597870871424675,
+      "learning_rate": 8.202965893490878e-05,
+      "loss": 0.2782,
+      "step": 96
+    },
+    {
+      "epoch": 0.3561811505507956,
+      "grad_norm": 0.2009837031364441,
+      "learning_rate": 8.153268014841506e-05,
+      "loss": 0.4888,
+      "step": 97
+    },
+    {
+      "epoch": 0.3598531211750306,
+      "grad_norm": 0.24240681529045105,
+      "learning_rate": 8.103047409137114e-05,
+      "loss": 0.7807,
+      "step": 98
+    },
+    {
+      "epoch": 0.3635250917992656,
+      "grad_norm": 0.0845351368188858,
+      "learning_rate": 8.052312401603847e-05,
+      "loss": 0.6298,
+      "step": 99
+    },
+    {
+      "epoch": 0.3671970624235006,
+      "grad_norm": 0.11193636804819107,
+      "learning_rate": 8.001071402741842e-05,
+      "loss": 0.8064,
+      "step": 100
+    },
+    {
+      "epoch": 0.3708690330477356,
+      "grad_norm": 0.0703149363398552,
+      "learning_rate": 7.949332906930995e-05,
+      "loss": 0.3406,
+      "step": 101
+    },
+    {
+      "epoch": 0.37454100367197063,
+      "grad_norm": 0.1298230141401291,
+      "learning_rate": 7.897105491022818e-05,
+      "loss": 0.579,
+      "step": 102
+    },
+    {
+      "epoch": 0.37821297429620565,
+      "grad_norm": 0.07925601303577423,
+      "learning_rate": 7.844397812918635e-05,
+      "loss": 0.3489,
+      "step": 103
+    },
+    {
+      "epoch": 0.3818849449204406,
+      "grad_norm": 0.12708668410778046,
+      "learning_rate": 7.791218610134323e-05,
+      "loss": 0.4151,
+      "step": 104
+    },
+    {
+      "epoch": 0.38555691554467564,
+      "grad_norm": 0.2936255931854248,
+      "learning_rate": 7.737576698351878e-05,
+      "loss": 1.1401,
+      "step": 105
+    },
+    {
+      "epoch": 0.38922888616891066,
+      "grad_norm": 0.07473833113908768,
+      "learning_rate": 7.683480969958004e-05,
+      "loss": 0.3091,
+      "step": 106
+    },
+    {
+      "epoch": 0.3929008567931457,
+      "grad_norm": 0.1253412663936615,
+      "learning_rate": 7.628940392569994e-05,
+      "loss": 0.4951,
+      "step": 107
+    },
+    {
+      "epoch": 0.39657282741738065,
+      "grad_norm": 0.08265762031078339,
+      "learning_rate": 7.573964007549155e-05,
+      "loss": 0.4025,
+      "step": 108
+    },
+    {
+      "epoch": 0.40024479804161567,
+      "grad_norm": 0.11429966986179352,
+      "learning_rate": 7.518560928501969e-05,
+      "loss": 0.4147,
+      "step": 109
+    },
+    {
+      "epoch": 0.4039167686658507,
+      "grad_norm": 0.25090694427490234,
+      "learning_rate": 7.462740339769324e-05,
+      "loss": 0.5981,
+      "step": 110
+    },
+    {
+      "epoch": 0.40758873929008566,
+      "grad_norm": 0.17391008138656616,
+      "learning_rate": 7.406511494903982e-05,
+      "loss": 0.4219,
+      "step": 111
+    },
+    {
+      "epoch": 0.4112607099143207,
+      "grad_norm": 0.06932790577411652,
+      "learning_rate": 7.3498837151366e-05,
+      "loss": 0.4379,
+      "step": 112
+    },
+    {
+      "epoch": 0.4149326805385557,
+      "grad_norm": 0.08115310966968536,
+      "learning_rate": 7.292866387830514e-05,
+      "loss": 0.3631,
+      "step": 113
+    },
+    {
+      "epoch": 0.4186046511627907,
+      "grad_norm": 0.11411315202713013,
+      "learning_rate": 7.23546896492557e-05,
+      "loss": 0.6605,
+      "step": 114
+    },
+    {
+      "epoch": 0.4222766217870257,
+      "grad_norm": 0.12723813951015472,
+      "learning_rate": 7.177700961371239e-05,
+      "loss": 0.5364,
+      "step": 115
+    },
+    {
+      "epoch": 0.4259485924112607,
+      "grad_norm": 0.08049023896455765,
+      "learning_rate": 7.119571953549305e-05,
+      "loss": 0.3387,
+      "step": 116
+    },
+    {
+      "epoch": 0.42962056303549573,
+      "grad_norm": 0.07781126350164413,
+      "learning_rate": 7.06109157768635e-05,
+      "loss": 0.5689,
+      "step": 117
+    },
+    {
+      "epoch": 0.43329253365973075,
+      "grad_norm": 0.14163357019424438,
+      "learning_rate": 7.002269528256334e-05,
+      "loss": 0.4366,
+      "step": 118
+    },
+    {
+      "epoch": 0.4369645042839657,
+      "grad_norm": 0.07881614565849304,
+      "learning_rate": 6.943115556373502e-05,
+      "loss": 0.3186,
+      "step": 119
+    },
+    {
+      "epoch": 0.44063647490820074,
+      "grad_norm": 0.08862645924091339,
+      "learning_rate": 6.883639468175927e-05,
+      "loss": 0.3786,
+      "step": 120
+    },
+    {
+      "epoch": 0.44430844553243576,
+      "grad_norm": 0.08052200824022293,
+      "learning_rate": 6.823851123199893e-05,
+      "loss": 0.3527,
+      "step": 121
+    },
+    {
+      "epoch": 0.4479804161566707,
+      "grad_norm": 0.11888729780912399,
+      "learning_rate": 6.763760432745475e-05,
+      "loss": 0.4314,
+      "step": 122
+    },
+    {
+      "epoch": 0.45165238678090575,
+      "grad_norm": 0.06493515521287918,
+      "learning_rate": 6.703377358233489e-05,
+      "loss": 0.2977,
+      "step": 123
+    },
+    {
+      "epoch": 0.45532435740514077,
+      "grad_norm": 0.10048846155405045,
+      "learning_rate": 6.642711909554174e-05,
+      "loss": 0.3244,
+      "step": 124
+    },
+    {
+      "epoch": 0.4589963280293758,
+      "grad_norm": 0.10203630477190018,
+      "learning_rate": 6.58177414340781e-05,
+      "loss": 0.4996,
+      "step": 125
+    },
+    {
+      "epoch": 0.46266829865361075,
+      "grad_norm": 0.2413017451763153,
+      "learning_rate": 6.52057416163759e-05,
+      "loss": 0.555,
+      "step": 126
+    },
+    {
+      "epoch": 0.4663402692778458,
+      "grad_norm": 0.08983640372753143,
+      "learning_rate": 6.45912210955501e-05,
+      "loss": 0.2582,
+      "step": 127
+    },
+    {
+      "epoch": 0.4700122399020808,
+      "grad_norm": 0.21270190179347992,
+      "learning_rate": 6.397428174258047e-05,
+      "loss": 0.5315,
+      "step": 128
+    },
+    {
+      "epoch": 0.47368421052631576,
+      "grad_norm": 0.12013928592205048,
+      "learning_rate": 6.335502582942408e-05,
+      "loss": 0.489,
+      "step": 129
+    },
+    {
+      "epoch": 0.4773561811505508,
+      "grad_norm": 0.1020718440413475,
+      "learning_rate": 6.273355601206144e-05,
+      "loss": 0.456,
+      "step": 130
+    },
+    {
+      "epoch": 0.4810281517747858,
+      "grad_norm": 0.08006691932678223,
+      "learning_rate": 6.210997531347878e-05,
+      "loss": 0.3459,
+      "step": 131
+    },
+    {
+      "epoch": 0.4847001223990208,
+      "grad_norm": 0.10623283684253693,
+      "learning_rate": 6.14843871065898e-05,
+      "loss": 0.5545,
+      "step": 132
+    },
+    {
+      "epoch": 0.4883720930232558,
+      "grad_norm": 0.0730510801076889,
+      "learning_rate": 6.0856895097098934e-05,
+      "loss": 0.3225,
+      "step": 133
+    },
+    {
+      "epoch": 0.4920440636474908,
+      "grad_norm": 0.09953512251377106,
+      "learning_rate": 6.022760330631005e-05,
+      "loss": 0.4317,
+      "step": 134
+    },
+    {
+      "epoch": 0.49571603427172584,
+      "grad_norm": 0.0781313106417656,
+      "learning_rate": 5.9596616053882295e-05,
+      "loss": 0.3251,
+      "step": 135
+    },
+    {
+      "epoch": 0.49938800489596086,
+      "grad_norm": 0.11223123967647552,
+      "learning_rate": 5.896403794053679e-05,
+      "loss": 0.63,
+      "step": 136
+    },
+    {
+      "epoch": 0.5030599755201959,
+      "grad_norm": 0.10512508451938629,
+      "learning_rate": 5.83299738307166e-05,
+      "loss": 0.481,
+      "step": 137
+    },
+    {
+      "epoch": 0.5067319461444308,
+      "grad_norm": 0.08379629254341125,
+      "learning_rate": 5.76945288352031e-05,
+      "loss": 0.4922,
+      "step": 138
+    },
+    {
+      "epoch": 0.5104039167686658,
+      "grad_norm": 0.08486858010292053,
+      "learning_rate": 5.70578082936913e-05,
+      "loss": 0.381,
+      "step": 139
+    },
+    {
+      "epoch": 0.5140758873929009,
+      "grad_norm": 0.14607948064804077,
+      "learning_rate": 5.6419917757327555e-05,
+      "loss": 0.5921,
+      "step": 140
+    },
+    {
+      "epoch": 0.5177478580171359,
+      "grad_norm": 0.1181630790233612,
+      "learning_rate": 5.5780962971211795e-05,
+      "loss": 0.6962,
+      "step": 141
+    },
+    {
+      "epoch": 0.5214198286413708,
+      "grad_norm": 0.17947016656398773,
+      "learning_rate": 5.514104985686802e-05,
+      "loss": 0.6109,
+      "step": 142
+    },
+    {
+      "epoch": 0.5250917992656059,
+      "grad_norm": 0.06438343226909637,
+      "learning_rate": 5.450028449468527e-05,
+      "loss": 0.2542,
+      "step": 143
+    },
+    {
+      "epoch": 0.5287637698898409,
+      "grad_norm": 0.09820745885372162,
+      "learning_rate": 5.385877310633233e-05,
+      "loss": 0.6507,
+      "step": 144
+    },
+    {
+      "epoch": 0.5324357405140759,
+      "grad_norm": 0.09040407836437225,
+      "learning_rate": 5.321662203714909e-05,
+      "loss": 0.399,
+      "step": 145
+    },
+    {
+      "epoch": 0.5361077111383109,
+      "grad_norm": 0.2683495283126831,
+      "learning_rate": 5.257393773851733e-05,
+      "loss": 0.4017,
+      "step": 146
+    },
+    {
+      "epoch": 0.5397796817625459,
+      "grad_norm": 0.1613844335079193,
+      "learning_rate": 5.193082675021392e-05,
+      "loss": 0.3849,
+      "step": 147
+    },
+    {
+      "epoch": 0.543451652386781,
+      "grad_norm": 0.12207731604576111,
+      "learning_rate": 5.128739568274944e-05,
+      "loss": 0.5905,
+      "step": 148
+    },
+    {
+      "epoch": 0.5471236230110159,
+      "grad_norm": 0.0870044156908989,
+      "learning_rate": 5.064375119969491e-05,
+      "loss": 0.2895,
+      "step": 149
+    },
+    {
+      "epoch": 0.5507955936352509,
+      "grad_norm": 0.08491414785385132,
+      "learning_rate": 5e-05,
+      "loss": 0.3632,
+      "step": 150
+    },
+    {
+      "epoch": 0.554467564259486,
+      "grad_norm": 0.11790735274553299,
+      "learning_rate": 4.9356248800305106e-05,
+      "loss": 0.7068,
+      "step": 151
+    },
+    {
+      "epoch": 0.5581395348837209,
+      "grad_norm": 0.19284167885780334,
+      "learning_rate": 4.8712604317250576e-05,
+      "loss": 0.3605,
+      "step": 152
+    },
+    {
+      "epoch": 0.5618115055079559,
+      "grad_norm": 0.09215154498815536,
+      "learning_rate": 4.806917324978608e-05,
+      "loss": 0.2476,
+      "step": 153
+    },
+    {
+      "epoch": 0.565483476132191,
+      "grad_norm": 0.12108391523361206,
+      "learning_rate": 4.7426062261482675e-05,
+      "loss": 0.5039,
+      "step": 154
+    },
+    {
+      "epoch": 0.5691554467564259,
+      "grad_norm": 0.14685741066932678,
+      "learning_rate": 4.678337796285092e-05,
+      "loss": 0.5615,
+      "step": 155
+    },
+    {
+      "epoch": 0.572827417380661,
+      "grad_norm": 0.09982460737228394,
+      "learning_rate": 4.6141226893667684e-05,
+      "loss": 0.6,
+      "step": 156
+    },
+    {
+      "epoch": 0.576499388004896,
+      "grad_norm": 0.10319037735462189,
+      "learning_rate": 4.5499715505314745e-05,
+      "loss": 0.4833,
+      "step": 157
+    },
+    {
+      "epoch": 0.5801713586291309,
+      "grad_norm": 0.0910174548625946,
+      "learning_rate": 4.4858950143131975e-05,
+      "loss": 0.5044,
+      "step": 158
+    },
+    {
+      "epoch": 0.583843329253366,
+      "grad_norm": 0.08110320568084717,
+      "learning_rate": 4.4219037028788216e-05,
+      "loss": 0.6077,
+      "step": 159
+    },
+    {
+      "epoch": 0.587515299877601,
+      "grad_norm": 0.0765228420495987,
+      "learning_rate": 4.358008224267245e-05,
+      "loss": 0.2877,
+      "step": 160
+    },
+    {
+      "epoch": 0.591187270501836,
+      "grad_norm": 0.16392959654331207,
+      "learning_rate": 4.29421917063087e-05,
+      "loss": 0.4462,
+      "step": 161
+    },
+    {
+      "epoch": 0.594859241126071,
+      "grad_norm": 0.09697830677032471,
+      "learning_rate": 4.2305471164796905e-05,
+      "loss": 0.3803,
+      "step": 162
+    },
+    {
+      "epoch": 0.598531211750306,
+      "grad_norm": 0.09458833932876587,
+      "learning_rate": 4.167002616928341e-05,
+      "loss": 0.4625,
+      "step": 163
+    },
+    {
+      "epoch": 0.602203182374541,
+      "grad_norm": 0.08443703502416611,
+      "learning_rate": 4.103596205946323e-05,
+      "loss": 0.615,
+      "step": 164
+    },
+    {
+      "epoch": 0.605875152998776,
+      "grad_norm": 0.10602038353681564,
+      "learning_rate": 4.0403383946117717e-05,
+      "loss": 0.6253,
+      "step": 165
+    },
+    {
+      "epoch": 0.609547123623011,
+      "grad_norm": 0.18194644153118134,
+      "learning_rate": 3.977239669368997e-05,
+      "loss": 0.4052,
+      "step": 166
+    },
+    {
+      "epoch": 0.6132190942472461,
+      "grad_norm": 0.1692446619272232,
+      "learning_rate": 3.9143104902901085e-05,
+      "loss": 0.9142,
+      "step": 167
+    },
+    {
+      "epoch": 0.616891064871481,
+      "grad_norm": 0.19827115535736084,
+      "learning_rate": 3.851561289341023e-05,
+      "loss": 0.4136,
+      "step": 168
+    },
+    {
+      "epoch": 0.620563035495716,
+      "grad_norm": 0.2976871132850647,
+      "learning_rate": 3.789002468652121e-05,
+      "loss": 0.5657,
+      "step": 169
+    },
+    {
+      "epoch": 0.6242350061199511,
+      "grad_norm": 0.07852277904748917,
+      "learning_rate": 3.726644398793857e-05,
+      "loss": 0.3279,
+      "step": 170
+    },
+    {
+      "epoch": 0.627906976744186,
+      "grad_norm": 0.12604489922523499,
+      "learning_rate": 3.664497417057591e-05,
+      "loss": 0.62,
+      "step": 171
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 0.22574089467525482,
+      "learning_rate": 3.602571825741953e-05,
+      "loss": 0.8179,
+      "step": 172
+    },
+    {
+      "epoch": 0.6352509179926561,
+      "grad_norm": 0.13447195291519165,
+      "learning_rate": 3.540877890444989e-05,
+      "loss": 0.5163,
+      "step": 173
+    },
+    {
+      "epoch": 0.6389228886168911,
+      "grad_norm": 0.11539029330015182,
+      "learning_rate": 3.4794258383624114e-05,
+      "loss": 0.4173,
+      "step": 174
+    },
+    {
+      "epoch": 0.642594859241126,
+      "grad_norm": 0.11384222656488419,
+      "learning_rate": 3.4182258565921934e-05,
+      "loss": 0.5455,
+      "step": 175
+    },
+    {
+      "epoch": 0.6462668298653611,
+      "grad_norm": 0.12927398085594177,
+      "learning_rate": 3.357288090445827e-05,
+      "loss": 0.5327,
+      "step": 176
+    },
+    {
+      "epoch": 0.6499388004895961,
+      "grad_norm": 0.16683682799339294,
+      "learning_rate": 3.296622641766512e-05,
+      "loss": 0.5541,
+      "step": 177
+    },
+    {
+      "epoch": 0.653610771113831,
+      "grad_norm": 0.09209699183702469,
+      "learning_rate": 3.236239567254526e-05,
+      "loss": 0.4312,
+      "step": 178
+    },
+    {
+      "epoch": 0.6572827417380661,
+      "grad_norm": 0.13782797753810883,
+      "learning_rate": 3.1761488768001085e-05,
+      "loss": 0.8246,
+      "step": 179
+    },
+    {
+      "epoch": 0.6609547123623011,
+      "grad_norm": 0.07543042302131653,
+      "learning_rate": 3.116360531824074e-05,
+      "loss": 0.5633,
+      "step": 180
+    },
+    {
+      "epoch": 0.6646266829865362,
+      "grad_norm": 0.14241543412208557,
+      "learning_rate": 3.056884443626499e-05,
+      "loss": 0.6657,
+      "step": 181
+    },
+    {
+      "epoch": 0.6682986536107711,
+      "grad_norm": 0.11854031682014465,
+      "learning_rate": 2.9977304717436672e-05,
+      "loss": 0.6332,
+      "step": 182
+    },
+    {
+      "epoch": 0.6719706242350061,
+      "grad_norm": 0.09301911294460297,
+      "learning_rate": 2.938908422313652e-05,
+      "loss": 0.4556,
+      "step": 183
+    },
+    {
+      "epoch": 0.6756425948592412,
+      "grad_norm": 0.08479209989309311,
+      "learning_rate": 2.8804280464506973e-05,
+      "loss": 0.3345,
+      "step": 184
+    },
+    {
+      "epoch": 0.6793145654834761,
+      "grad_norm": 0.08416282385587692,
+      "learning_rate": 2.8222990386287617e-05,
+      "loss": 0.4235,
+      "step": 185
+    },
+    {
+      "epoch": 0.6829865361077111,
+      "grad_norm": 0.29337114095687866,
+      "learning_rate": 2.7645310350744297e-05,
+      "loss": 0.485,
+      "step": 186
+    },
+    {
+      "epoch": 0.6866585067319462,
+      "grad_norm": 0.106132872402668,
+      "learning_rate": 2.7071336121694858e-05,
+      "loss": 0.3384,
+      "step": 187
+    },
+    {
+      "epoch": 0.6903304773561811,
+      "grad_norm": 0.08644799143075943,
+      "learning_rate": 2.650116284863402e-05,
+      "loss": 0.9103,
+      "step": 188
+    },
+    {
+      "epoch": 0.6940024479804161,
+      "grad_norm": 0.13192370533943176,
+      "learning_rate": 2.5934885050960182e-05,
+      "loss": 0.5258,
+      "step": 189
+    },
+    {
+      "epoch": 0.6976744186046512,
+      "grad_norm": 0.10062063485383987,
+      "learning_rate": 2.5372596602306786e-05,
+      "loss": 0.4817,
+      "step": 190
+    },
+    {
+      "epoch": 0.7013463892288861,
+      "grad_norm": 0.09146949648857117,
+      "learning_rate": 2.4814390714980325e-05,
+      "loss": 0.4289,
+      "step": 191
+    },
+    {
+      "epoch": 0.7050183598531212,
+      "grad_norm": 0.17095047235488892,
+      "learning_rate": 2.426035992450848e-05,
+      "loss": 0.4383,
+      "step": 192
+    },
+    {
+      "epoch": 0.7086903304773562,
+      "grad_norm": 0.2827148735523224,
+      "learning_rate": 2.3710596074300045e-05,
+      "loss": 0.7566,
+      "step": 193
+    },
+    {
+      "epoch": 0.7123623011015912,
+      "grad_norm": 0.09297563880681992,
+      "learning_rate": 2.316519030041998e-05,
+      "loss": 0.4648,
+      "step": 194
+    },
+    {
+      "epoch": 0.7160342717258262,
+      "grad_norm": 0.11713358759880066,
+      "learning_rate": 2.262423301648122e-05,
+      "loss": 0.668,
+      "step": 195
+    },
+    {
+      "epoch": 0.7197062423500612,
+      "grad_norm": 0.10133064538240433,
+      "learning_rate": 2.2087813898656774e-05,
+      "loss": 0.4397,
+      "step": 196
+    },
+    {
+      "epoch": 0.7233782129742962,
+      "grad_norm": 0.23745763301849365,
+      "learning_rate": 2.1556021870813654e-05,
+      "loss": 0.685,
+      "step": 197
+    },
+    {
+      "epoch": 0.7270501835985312,
+      "grad_norm": 0.11296797543764114,
+      "learning_rate": 2.102894508977182e-05,
+      "loss": 0.2627,
+      "step": 198
+    },
+    {
+      "epoch": 0.7307221542227662,
+      "grad_norm": 0.09247058629989624,
+      "learning_rate": 2.0506670930690074e-05,
+      "loss": 0.3164,
+      "step": 199
+    },
+    {
+      "epoch": 0.7343941248470012,
+      "grad_norm": 0.08100568503141403,
+      "learning_rate": 1.9989285972581595e-05,
+      "loss": 0.4444,
+      "step": 200
+    },
+    {
+      "epoch": 0.7380660954712362,
+      "grad_norm": 0.08765120804309845,
+      "learning_rate": 1.947687598396154e-05,
+      "loss": 0.8168,
+      "step": 201
+    },
+    {
+      "epoch": 0.7417380660954712,
+      "grad_norm": 0.11285313963890076,
+      "learning_rate": 1.896952590862886e-05,
+      "loss": 0.3696,
+      "step": 202
+    },
+    {
+      "epoch": 0.7454100367197063,
+      "grad_norm": 0.1029384583234787,
+      "learning_rate": 1.8467319851584954e-05,
+      "loss": 0.3903,
+      "step": 203
+    },
+    {
+      "epoch": 0.7490820073439413,
+      "grad_norm": 0.14774741232395172,
+      "learning_rate": 1.7970341065091245e-05,
+      "loss": 0.5486,
+      "step": 204
+    },
+    {
+      "epoch": 0.7527539779681762,
+      "grad_norm": 0.20584475994110107,
+      "learning_rate": 1.7478671934868302e-05,
+      "loss": 0.4969,
+      "step": 205
+    },
+    {
+      "epoch": 0.7564259485924113,
+      "grad_norm": 0.10497330129146576,
+      "learning_rate": 1.6992393966438407e-05,
+      "loss": 0.6211,
+      "step": 206
+    },
+    {
+      "epoch": 0.7600979192166463,
+      "grad_norm": 0.10213766247034073,
+      "learning_rate": 1.6511587771614205e-05,
+      "loss": 0.3785,
+      "step": 207
+    },
+    {
+      "epoch": 0.7637698898408812,
+      "grad_norm": 0.08263826370239258,
+      "learning_rate": 1.6036333055135344e-05,
+      "loss": 0.4173,
+      "step": 208
+    },
+    {
+      "epoch": 0.7674418604651163,
+      "grad_norm": 0.15048938989639282,
+      "learning_rate": 1.556670860145567e-05,
+      "loss": 0.7029,
+      "step": 209
+    },
+    {
+      "epoch": 0.7711138310893513,
+      "grad_norm": 0.09334007650613785,
+      "learning_rate": 1.5102792261682813e-05,
+      "loss": 0.4614,
+      "step": 210
+    },
+    {
+      "epoch": 0.7747858017135862,
+      "grad_norm": 0.15974034368991852,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.8333,
+      "step": 211
+    },
+    {
+      "epoch": 0.7784577723378213,
+      "grad_norm": 0.08053223788738251,
+      "learning_rate": 1.4192390584280346e-05,
+      "loss": 0.3017,
+      "step": 212
+    },
+    {
+      "epoch": 0.7821297429620563,
+      "grad_norm": 0.0834859237074852,
+      "learning_rate": 1.374605616677087e-05,
+      "loss": 0.304,
+      "step": 213
+    },
+    {
+      "epoch": 0.7858017135862914,
+      "grad_norm": 0.0708678588271141,
+      "learning_rate": 1.3305731678390048e-05,
+      "loss": 0.4155,
+      "step": 214
+    },
+    {
+      "epoch": 0.7894736842105263,
+      "grad_norm": 0.13682302832603455,
+      "learning_rate": 1.2871490113099066e-05,
+      "loss": 0.7763,
+      "step": 215
+    },
+    {
+      "epoch": 0.7931456548347613,
+      "grad_norm": 0.12170913815498352,
+      "learning_rate": 1.2443403456474017e-05,
+      "loss": 0.5421,
+      "step": 216
+    },
+    {
+      "epoch": 0.7968176254589964,
+      "grad_norm": 0.07957993447780609,
+      "learning_rate": 1.2021542673772585e-05,
+      "loss": 0.3638,
+      "step": 217
+    },
+    {
+      "epoch": 0.8004895960832313,
+      "grad_norm": 0.14521080255508423,
+      "learning_rate": 1.1605977698170001e-05,
+      "loss": 0.5641,
+      "step": 218
+    },
+    {
+      "epoch": 0.8041615667074663,
+      "grad_norm": 0.0813819020986557,
+      "learning_rate": 1.1196777419165927e-05,
+      "loss": 0.407,
+      "step": 219
+    },
+    {
+      "epoch": 0.8078335373317014,
+      "grad_norm": 0.12135583162307739,
+      "learning_rate": 1.0794009671164484e-05,
+      "loss": 0.8802,
+      "step": 220
+    },
+    {
+      "epoch": 0.8115055079559363,
+      "grad_norm": 0.1219213679432869,
+      "learning_rate": 1.0397741222229057e-05,
+      "loss": 0.5714,
+      "step": 221
+    },
+    {
+      "epoch": 0.8151774785801713,
+      "grad_norm": 0.08637195825576782,
+      "learning_rate": 1.0008037763014032e-05,
+      "loss": 0.4146,
+      "step": 222
+    },
+    {
+      "epoch": 0.8188494492044064,
+      "grad_norm": 0.22487489879131317,
+      "learning_rate": 9.624963895874994e-06,
+      "loss": 0.4979,
+      "step": 223
+    },
+    {
+      "epoch": 0.8225214198286414,
+      "grad_norm": 0.28123998641967773,
+      "learning_rate": 9.248583124159438e-06,
+      "loss": 0.7919,
+      "step": 224
+    },
+    {
+      "epoch": 0.8261933904528764,
+      "grad_norm": 0.14954394102096558,
+      "learning_rate": 8.878957841679541e-06,
+      "loss": 0.4572,
+      "step": 225
+    },
+    {
+      "epoch": 0.8298653610771114,
+      "grad_norm": 0.08152212202548981,
+      "learning_rate": 8.516149322369054e-06,
+      "loss": 0.3024,
+      "step": 226
+    },
+    {
+      "epoch": 0.8335373317013464,
+      "grad_norm": 0.08769659698009491,
+      "learning_rate": 8.160217710125662e-06,
+      "loss": 0.5087,
+      "step": 227
+    },
+    {
+      "epoch": 0.8372093023255814,
+      "grad_norm": 0.14432811737060547,
+      "learning_rate": 7.81122200884072e-06,
+      "loss": 0.4048,
+      "step": 228
+    },
+    {
+      "epoch": 0.8408812729498164,
+      "grad_norm": 0.2427009642124176,
+      "learning_rate": 7.469220072618094e-06,
+      "loss": 0.4902,
+      "step": 229
+    },
+    {
+      "epoch": 0.8445532435740514,
+      "grad_norm": 0.09131976217031479,
+      "learning_rate": 7.13426859618338e-06,
+      "loss": 0.2719,
+      "step": 230
+    },
+    {
+      "epoch": 0.8482252141982864,
+      "grad_norm": 0.0897597223520279,
+      "learning_rate": 6.806423105485577e-06,
+      "loss": 0.3147,
+      "step": 231
+    },
+    {
+      "epoch": 0.8518971848225214,
+      "grad_norm": 0.11949042230844498,
+      "learning_rate": 6.4857379484922375e-06,
+      "loss": 0.5688,
+      "step": 232
+    },
+    {
+      "epoch": 0.8555691554467564,
+      "grad_norm": 0.08959188312292099,
+      "learning_rate": 6.1722662861801614e-06,
+      "loss": 0.3724,
+      "step": 233
+    },
+    {
+      "epoch": 0.8592411260709915,
+      "grad_norm": 0.10583740472793579,
+      "learning_rate": 5.866060083722624e-06,
+      "loss": 0.6448,
+      "step": 234
+    },
+    {
+      "epoch": 0.8629130966952264,
+      "grad_norm": 0.1368107944726944,
+      "learning_rate": 5.5671701018750745e-06,
+      "loss": 0.7383,
+      "step": 235
+    },
+    {
+      "epoch": 0.8665850673194615,
+      "grad_norm": 0.07287576794624329,
+      "learning_rate": 5.275645888560232e-06,
+      "loss": 0.3452,
+      "step": 236
+    },
+    {
+      "epoch": 0.8702570379436965,
+      "grad_norm": 0.07863111793994904,
+      "learning_rate": 4.9915357706544485e-06,
+      "loss": 0.3893,
+      "step": 237
+    },
+    {
+      "epoch": 0.8739290085679314,
+      "grad_norm": 0.08062013983726501,
+      "learning_rate": 4.714886845976429e-06,
+      "loss": 0.2986,
+      "step": 238
+    },
+    {
+      "epoch": 0.8776009791921665,
+      "grad_norm": 0.07851500064134598,
+      "learning_rate": 4.445744975479626e-06,
+      "loss": 0.4395,
+      "step": 239
+    },
+    {
+      "epoch": 0.8812729498164015,
+      "grad_norm": 0.07426175475120544,
+      "learning_rate": 4.184154775649768e-06,
+      "loss": 0.2981,
+      "step": 240
+    },
+    {
+      "epoch": 0.8849449204406364,
+      "grad_norm": 0.10778014361858368,
+      "learning_rate": 3.9301596111086025e-06,
+      "loss": 0.5546,
+      "step": 241
+    },
+    {
+      "epoch": 0.8886168910648715,
+      "grad_norm": 0.23396329581737518,
+      "learning_rate": 3.683801587425251e-06,
+      "loss": 0.4488,
+      "step": 242
+    },
+    {
+      "epoch": 0.8922888616891065,
+      "grad_norm": 0.24511796236038208,
+      "learning_rate": 3.4451215441362263e-06,
+      "loss": 0.5273,
+      "step": 243
+    },
+    {
+      "epoch": 0.8959608323133414,
+      "grad_norm": 0.11425651609897614,
+      "learning_rate": 3.2141590479753236e-06,
+      "loss": 0.6317,
+      "step": 244
+    },
+    {
+      "epoch": 0.8996328029375765,
+      "grad_norm": 0.2402946650981903,
+      "learning_rate": 2.990952386314505e-06,
+      "loss": 0.5092,
+      "step": 245
+    },
+    {
+      "epoch": 0.9033047735618115,
+      "grad_norm": 0.12040656059980392,
+      "learning_rate": 2.775538560816937e-06,
+      "loss": 0.5734,
+      "step": 246
+    },
+    {
+      "epoch": 0.9069767441860465,
+      "grad_norm": 0.08450046181678772,
+      "learning_rate": 2.5679532813030596e-06,
+      "loss": 0.535,
+      "step": 247
+    },
+    {
+      "epoch": 0.9106487148102815,
+      "grad_norm": 0.08185907453298569,
+      "learning_rate": 2.3682309598308747e-06,
+      "loss": 0.5474,
+      "step": 248
+    },
+    {
+      "epoch": 0.9143206854345165,
+      "grad_norm": 0.08737199753522873,
+      "learning_rate": 2.1764047049913527e-06,
+      "loss": 0.3862,
+      "step": 249
+    },
+    {
+      "epoch": 0.9179926560587516,
+      "grad_norm": 0.0846424475312233,
+      "learning_rate": 1.992506316419912e-06,
+      "loss": 0.3631,
+      "step": 250
+    },
+    {
+      "epoch": 0.9216646266829865,
+      "grad_norm": 0.0750948116183281,
+      "learning_rate": 1.8165662795249172e-06,
+      "loss": 0.2861,
+      "step": 251
+    },
+    {
+      "epoch": 0.9253365973072215,
+      "grad_norm": 0.09620046615600586,
+      "learning_rate": 1.6486137604339813e-06,
+      "loss": 0.6115,
+      "step": 252
+    },
+    {
+      "epoch": 0.9290085679314566,
+      "grad_norm": 0.13249874114990234,
+      "learning_rate": 1.4886766011590448e-06,
+      "loss": 0.6009,
+      "step": 253
+    },
+    {
+      "epoch": 0.9326805385556916,
+      "grad_norm": 0.07768455892801285,
+      "learning_rate": 1.3367813149808729e-06,
+      "loss": 0.5147,
+      "step": 254
+    },
+    {
+      "epoch": 0.9363525091799265,
+      "grad_norm": 0.09131491929292679,
+      "learning_rate": 1.1929530820539269e-06,
+      "loss": 0.3699,
+      "step": 255
+    },
+    {
+      "epoch": 0.9400244798041616,
+      "grad_norm": 0.0973149985074997,
+      "learning_rate": 1.0572157452321097e-06,
+      "loss": 0.4612,
+      "step": 256
+    },
+    {
+      "epoch": 0.9436964504283966,
+      "grad_norm": 0.08338738232851028,
+      "learning_rate": 9.295918061163033e-07,
+      "loss": 0.3989,
+      "step": 257
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "grad_norm": 0.12276645749807358,
+      "learning_rate": 8.101024213241826e-07,
+      "loss": 0.7361,
+      "step": 258
+    },
+    {
+      "epoch": 0.9510403916768666,
+      "grad_norm": 0.07636597752571106,
+      "learning_rate": 6.987673989830523e-07,
+      "loss": 0.356,
+      "step": 259
+    },
+    {
+      "epoch": 0.9547123623011016,
+      "grad_norm": 0.0995926633477211,
+      "learning_rate": 5.956051954461472e-07,
+      "loss": 0.5988,
+      "step": 260
+    },
+    {
+      "epoch": 0.9583843329253366,
+      "grad_norm": 0.12855686247348785,
+      "learning_rate": 5.006329122330899e-07,
+      "loss": 0.6091,
+      "step": 261
+    },
+    {
+      "epoch": 0.9620563035495716,
+      "grad_norm": 0.10323388129472733,
+      "learning_rate": 4.1386629319492556e-07,
+      "loss": 0.5726,
+      "step": 262
+    },
+    {
+      "epoch": 0.9657282741738066,
+      "grad_norm": 0.07876481115818024,
+      "learning_rate": 3.3531972190419815e-07,
+      "loss": 0.2667,
+      "step": 263
+    },
+    {
+      "epoch": 0.9694002447980417,
+      "grad_norm": 0.08382689952850342,
+      "learning_rate": 2.6500621927054715e-07,
+      "loss": 0.2876,
+      "step": 264
+    },
+    {
+      "epoch": 0.9730722154222766,
+      "grad_norm": 0.08943753689527512,
+      "learning_rate": 2.0293744138219495e-07,
+      "loss": 0.3169,
+      "step": 265
+    },
+    {
+      "epoch": 0.9767441860465116,
+      "grad_norm": 0.07517411559820175,
+      "learning_rate": 1.4912367757366487e-07,
+      "loss": 0.3369,
+      "step": 266
+    },
+    {
+      "epoch": 0.9804161566707467,
+      "grad_norm": 0.08059985190629959,
+      "learning_rate": 1.0357384872011766e-07,
+      "loss": 0.2544,
+      "step": 267
+    },
+    {
+      "epoch": 0.9840881272949816,
+      "grad_norm": 0.15402479469776154,
+      "learning_rate": 6.629550575847354e-08,
+      "loss": 0.9444,
+      "step": 268
+    },
+    {
+      "epoch": 0.9877600979192166,
+      "grad_norm": 0.07759124785661697,
+      "learning_rate": 3.729482843569665e-08,
+      "loss": 0.5641,
+      "step": 269
+    },
+    {
+      "epoch": 0.9914320685434517,
+      "grad_norm": 0.08798715472221375,
+      "learning_rate": 1.6576624284347918e-08,
+      "loss": 0.3192,
+      "step": 270
+    },
+    {
+      "epoch": 0.9951040391676866,
+      "grad_norm": 0.09718140214681625,
+      "learning_rate": 4.1443278256170226e-09,
+      "loss": 0.6975,
+      "step": 271
+    },
+    {
+      "epoch": 0.9987760097919217,
+      "grad_norm": 0.09622414410114288,
+      "learning_rate": 0.0,
+      "loss": 0.4445,
+      "step": 272
+    },
+    {
+      "epoch": 0.9987760097919217,
+      "step": 272,
+      "total_flos": 1.7184161279184077e+17,
+      "train_loss": 0.49135432271834684,
+      "train_runtime": 6097.9323,
+      "train_samples_per_second": 0.134,
+      "train_steps_per_second": 0.045
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 272,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.7184161279184077e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

adapter/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:618a10066ad99aee6101b869563c15beecc2507eed315e176d466c190b27f089
+size 5624

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.3",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151646,
+  "do_sample": true,
+  "eos_token_id": 151643,
+  "temperature": 0.6,
+  "top_p": 0.95,
+  "transformers_version": "4.48.3"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2d56799efae4e3a03ae59aea8d85ece6886f779275de3162e53646a47133f6b
+size 3945426872

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c259eca7c611eea7e141ba89a2cddbcbcc6e9a74c00f0caaa8b6aee176f2c63
+size 3864726352

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:481e0d5c354080452f004b2e948e8faae2901db1a625dc66e1ba7c44fedb1676
+size 3864726408

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9efa574ac81d3036f7a90e76a0cc248c50f261a5608a9a0922301f56b9fd8b01
+size 3556392240

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,32 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778

tokenizer_config.json

@@ -0,0 +1,200 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<｜User｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151645": {
+      "content": "<｜Assistant｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151646": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151648": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151649": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<｜end▁of▁sentence｜>"
+  ],
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\\n'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}