Upload 12 files

README.md

@@ -1,3 +1,128 @@
 ---
+library_name: transformers
 license: mit
+base_model: BAAI/bge-small-en-v1.5
+dataset: agentlans/en-document-classification
+tags:
+- generated_from_trainer
+- text-classification
+- regression
+model-index:
+- name: bge-small-en-text-quality
+  results:
+  - task:
+      type: text-classification
+      name: Text Regression
+    dataset:
+      name: en-document-classification
+      type: agentlans/en-document-classification
+    metrics:
+    - name: MSE
+      type: mse
+      value: 0.1176
 ---
+# bge-small-en-text-quality
+
+This model evaluates English language text quality by mapping text inputs to a continuous quality score. 
+
+It is a fine-tuned version of [BAAI/bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5) optimized on the [agentlans/en-document-classification](https://huggingface.co/datasets/agentlans/en-document-classification) dataset for text quality regression.
+
+### Evaluation Performance
+* **Validation Loss:** 0.1176
+* **Mean Squared Error (MSE):** 0.1176 *(achieved at Epoch 2)*
+
+## Model Description
+
+This model acts as a scoring mechanism for the informational value and professional quality of English text. It outputs a single scalar value: higher scores generally indicate structured, formal, and high-information content (e.g., academic, technical, or well-structured reference text), while lower scores indicate spam, unverified chatter, or low-context snippets.
+
+### How to Use
+
+You can use this model directly with the Hugging Face `transformers` library for sequence classification/regression:
+
+```python
+import torch
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+
+# Load model and tokenizer
+model_name = "agentlans/bge-small-en-text-quality"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForSequenceClassification.from_pretrained(model_name)
+
+# Sample texts
+texts = [
+    "Original publication and designation: Decaisne, J. (1842). Essais sur une classification des algues...",
+    "Modern Action Figure Toys & Collectibles!! You've been outbid to E****y! to YOU!"
+]
+
+# Tokenize and predict
+inputs = tokenizer(texts, padding=True, truncation=True, return_tensors="pt")
+with torch.no_grad():
+    outputs = model(**inputs)
+    # The model outputs a single continuous value per text
+    scores = outputs.logits.squeeze(-1).tolist()
+
+for text, score in zip(texts, scores):
+    print(f"Score: {score:.4f} | Text: {text[:80]}...")
+
+```
+
+## Intended Uses & Limitations
+
+### Primary Use Cases
+
+* **Content Moderation:** A rapid, lightweight method to filter out spam, SEO filler, and corrupted web-scraped text.
+* **Data Filtering:** Sorting or ranking documents by informational value before using them for LLM pre-training or RAG (Retrieval-Augmented Generation) pipelines.
+
+### Known Limitations
+
+* **Genre Bias:** The model is heavily weighted toward structured, informative prose. Subjective, opinionated, or creative writing (e.g., personal blogs, fiction, entertainment reviews) will inherently score lower regardless of their actual artistic or human value.
+* **Lack of Explainability:** It returns a raw numerical score without indicating *why* a text was deemed high or low quality.
+* **No Fact-Checking Capability:** The model scores structural and stylistic indicators of quality. It cannot verify the objective accuracy or truthfulness of a statement; highly structured misinformation may still receive a high rating.
+
+## Training and Evaluation Data
+
+The model was trained and evaluated on the `agentlans/en-document-classification` dataset. Below is a sample of text inputs alongside their predicted scores versus their true dataset targets.
+
+### Sample Evaluation Results
+
+| Input Sample | Predicted Value | Actual Target |
+| --- | --- | --- |
+| Modern Action Figure Toys & Collectibles - Vintage, Rare and Hard to Find Toys including Convention and Store Exclusives! You've been outbid to E****y! to YOU! | **-1.6846** | -1.8808 |
+| Find 2 listings related to afterglow hair salon in Defuniak Springs on YP.com. See reviews, photos, directions, phone numbers and more for Afterglow Hair Salon... | **-1.6602** | -1.7688 |
+| We had a little bit of down time yesterday due to some technical difficulties. In other words Martin accidentally deleted the website! But while one hand destroys... | **-1.3730** | -1.4030 |
+| Should we talk with U.S. Congressmen who we know support campaign finance reform? Our Theory of Change only requires support from our State Legislators... | **-0.2137** | -0.6712 |
+| Sarah Hofstetter is the global CEO at 360i, the hotshot agency that’s behind some of the most buzzed-about work in the industry. The funny thing is... | **-0.3315** | -0.3483 |
+| LJW lawyers have extensive experience litigating commercial disputes on a broad range of issues and in a variety of forums. LJW's commercial practice includes... | **0.3911** | 0.3204 |
+| If you own a beautiful hand-knotted Oriental rug, you want to keep it looking beautiful forever. There are certain things that you can do that will help... | **0.9932** | 1.0737 |
+| Original publication and holotype designation: Decaisne, J. (1842). Essais sur une classification des algues et des polypiers calcifères de Lamouroux... | **1.6182** | 1.6823 |
+| Chemical additives are used in foodstuffs and sometimes it results into adulteration due to processing and hygiene aids. The discovery of an increasing number... | **2.4180** | 2.4192 |
+
+## Training Procedure
+
+### Training Hyperparameters
+
+* **Learning Rate:** 5e-05
+* **Train Batch Size:** 8
+* **Eval Batch Size:** 8
+* **Seed:** 42
+* **Optimizer:** AdamW (`adamw_torch_fused`) with $\beta_1 = 0.9$, $\beta_2 = 0.999$, and $\epsilon = 10^{-8}$
+* **Lr Scheduler Type:** Linear
+* **Num Epochs:** 3.0
+
+### Epoch-by-Epoch Progress
+
+| Training Loss | Epoch | Step | Validation Loss | Mse |
+| --- | --- | --- | --- | --- |
+| 0.1426 | 1.0 | 10000 | 0.1778 | 0.1778 |
+| 0.0895 | 2.0 | 20000 | **0.1176** | **0.1176** |
+| 0.0521 | 3.0 | 30000 | 0.1261 | 0.1261 |
+
+> **Note:** The model begins over-fitting slightly by Epoch 3; the checkpoint at Epoch 2 provides the lowest Validation Loss / MSE.
+
+### Framework Versions
+
+* Transformers 5.0.0.dev0
+* Pytorch 2.9.1+cu128
+* Datasets 4.4.1
+* Tokenizers 0.22.1
+

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.1175876185297966,
+    "eval_mse": 0.11758762182878052,
+    "eval_runtime": 11.4071,
+    "eval_samples": 20000,
+    "eval_samples_per_second": 1753.295,
+    "eval_steps_per_second": 219.162,
+    "total_flos": 3952243439859456.0,
+    "train_loss": 0.10308435103098551,
+    "train_runtime": 528.9789,
+    "train_samples": 79999,
+    "train_samples_per_second": 453.699,
+    "train_steps_per_second": 56.713
+}

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "finetuning_task": "text-classification",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "regression",
+  "transformers_version": "5.0.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": false,
+  "vocab_size": 30522
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.1175876185297966,
+    "eval_mse": 0.11758762182878052,
+    "eval_runtime": 11.4071,
+    "eval_samples": 20000,
+    "eval_samples_per_second": 1753.295,
+    "eval_steps_per_second": 219.162
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dc475a5c1e27cbd481ca7507df9c52555a8adedc9f72f3e91783410eb4831b0
+size 133464836

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 3952243439859456.0,
+    "train_loss": 0.10308435103098551,
+    "train_runtime": 528.9789,
+    "train_samples": 79999,
+    "train_samples_per_second": 453.699,
+    "train_steps_per_second": 56.713
+}

trainer_state.json

@@ -0,0 +1,490 @@
+{
+  "best_global_step": 20000,
+  "best_metric": 0.1175876185297966,
+  "best_model_checkpoint": "./bge-small-en-text-quality/checkpoint-20000",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 30000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "grad_norm": 3.9433600902557373,
+      "learning_rate": 4.9168333333333335e-05,
+      "loss": 0.2981,
+      "step": 500
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 3.3599181175231934,
+      "learning_rate": 4.8335000000000004e-05,
+      "loss": 0.2038,
+      "step": 1000
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 10.630352973937988,
+      "learning_rate": 4.7501666666666666e-05,
+      "loss": 0.1913,
+      "step": 1500
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 2.7322261333465576,
+      "learning_rate": 4.6668333333333335e-05,
+      "loss": 0.1819,
+      "step": 2000
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 3.438952922821045,
+      "learning_rate": 4.5835e-05,
+      "loss": 0.1678,
+      "step": 2500
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 6.013777732849121,
+      "learning_rate": 4.5001666666666666e-05,
+      "loss": 0.1635,
+      "step": 3000
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 3.261183977127075,
+      "learning_rate": 4.4168333333333335e-05,
+      "loss": 0.1564,
+      "step": 3500
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 4.93856954574585,
+      "learning_rate": 4.3335000000000004e-05,
+      "loss": 0.1555,
+      "step": 4000
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 1.6399900913238525,
+      "learning_rate": 4.2501666666666667e-05,
+      "loss": 0.1527,
+      "step": 4500
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 4.572032451629639,
+      "learning_rate": 4.1668333333333336e-05,
+      "loss": 0.1472,
+      "step": 5000
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 2.234090566635132,
+      "learning_rate": 4.0835e-05,
+      "loss": 0.1551,
+      "step": 5500
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 2.3441779613494873,
+      "learning_rate": 4.0001666666666674e-05,
+      "loss": 0.1435,
+      "step": 6000
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 3.1698434352874756,
+      "learning_rate": 3.9168333333333336e-05,
+      "loss": 0.1484,
+      "step": 6500
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 4.67405891418457,
+      "learning_rate": 3.8335000000000005e-05,
+      "loss": 0.1489,
+      "step": 7000
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 4.494452953338623,
+      "learning_rate": 3.750166666666667e-05,
+      "loss": 0.1376,
+      "step": 7500
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 8.088772773742676,
+      "learning_rate": 3.666833333333333e-05,
+      "loss": 0.1477,
+      "step": 8000
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 2.655813217163086,
+      "learning_rate": 3.5835000000000005e-05,
+      "loss": 0.1414,
+      "step": 8500
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 3.0818183422088623,
+      "learning_rate": 3.500166666666667e-05,
+      "loss": 0.1355,
+      "step": 9000
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 1.5601372718811035,
+      "learning_rate": 3.4168333333333336e-05,
+      "loss": 0.1364,
+      "step": 9500
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.5111470222473145,
+      "learning_rate": 3.3335e-05,
+      "loss": 0.1426,
+      "step": 10000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.1778368353843689,
+      "eval_mse": 0.1778368374988932,
+      "eval_runtime": 11.2433,
+      "eval_samples_per_second": 1778.834,
+      "eval_steps_per_second": 222.354,
+      "step": 10000
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 2.7848703861236572,
+      "learning_rate": 3.250166666666667e-05,
+      "loss": 0.0963,
+      "step": 10500
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 1.4169955253601074,
+      "learning_rate": 3.1668333333333336e-05,
+      "loss": 0.0937,
+      "step": 11000
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 1.4891533851623535,
+      "learning_rate": 3.0835000000000005e-05,
+      "loss": 0.0955,
+      "step": 11500
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 3.7263450622558594,
+      "learning_rate": 3.0001666666666668e-05,
+      "loss": 0.0925,
+      "step": 12000
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 2.7233424186706543,
+      "learning_rate": 2.9168333333333337e-05,
+      "loss": 0.0874,
+      "step": 12500
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 1.419253945350647,
+      "learning_rate": 2.8335e-05,
+      "loss": 0.0921,
+      "step": 13000
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 3.7091524600982666,
+      "learning_rate": 2.750166666666667e-05,
+      "loss": 0.0922,
+      "step": 13500
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 1.8904818296432495,
+      "learning_rate": 2.6668333333333334e-05,
+      "loss": 0.0893,
+      "step": 14000
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 2.954240322113037,
+      "learning_rate": 2.5835000000000003e-05,
+      "loss": 0.091,
+      "step": 14500
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 1.840616226196289,
+      "learning_rate": 2.5001666666666668e-05,
+      "loss": 0.0907,
+      "step": 15000
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 1.0130300521850586,
+      "learning_rate": 2.4168333333333334e-05,
+      "loss": 0.0941,
+      "step": 15500
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.8689394593238831,
+      "learning_rate": 2.3335000000000003e-05,
+      "loss": 0.0912,
+      "step": 16000
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 1.185209035873413,
+      "learning_rate": 2.250166666666667e-05,
+      "loss": 0.0913,
+      "step": 16500
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 1.7481811046600342,
+      "learning_rate": 2.1668333333333334e-05,
+      "loss": 0.0876,
+      "step": 17000
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 1.983954906463623,
+      "learning_rate": 2.0835000000000003e-05,
+      "loss": 0.0907,
+      "step": 17500
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 1.7682359218597412,
+      "learning_rate": 2.000166666666667e-05,
+      "loss": 0.0917,
+      "step": 18000
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 1.4291614294052124,
+      "learning_rate": 1.9168333333333334e-05,
+      "loss": 0.0889,
+      "step": 18500
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 2.0772218704223633,
+      "learning_rate": 1.8335000000000003e-05,
+      "loss": 0.0931,
+      "step": 19000
+    },
+    {
+      "epoch": 1.95,
+      "grad_norm": 4.12407922744751,
+      "learning_rate": 1.7501666666666665e-05,
+      "loss": 0.0922,
+      "step": 19500
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.343153476715088,
+      "learning_rate": 1.6668333333333334e-05,
+      "loss": 0.0895,
+      "step": 20000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.1175876185297966,
+      "eval_mse": 0.11758762182878052,
+      "eval_runtime": 11.2725,
+      "eval_samples_per_second": 1774.228,
+      "eval_steps_per_second": 221.779,
+      "step": 20000
+    },
+    {
+      "epoch": 2.05,
+      "grad_norm": 1.369104027748108,
+      "learning_rate": 1.5835e-05,
+      "loss": 0.0583,
+      "step": 20500
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 4.734041213989258,
+      "learning_rate": 1.5001666666666667e-05,
+      "loss": 0.0556,
+      "step": 21000
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 2.007387638092041,
+      "learning_rate": 1.4168333333333333e-05,
+      "loss": 0.0576,
+      "step": 21500
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 2.5438034534454346,
+      "learning_rate": 1.3335e-05,
+      "loss": 0.0564,
+      "step": 22000
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 4.6716132164001465,
+      "learning_rate": 1.2501666666666668e-05,
+      "loss": 0.0566,
+      "step": 22500
+    },
+    {
+      "epoch": 2.3,
+      "grad_norm": 3.9979987144470215,
+      "learning_rate": 1.1668333333333333e-05,
+      "loss": 0.0591,
+      "step": 23000
+    },
+    {
+      "epoch": 2.35,
+      "grad_norm": 2.851638078689575,
+      "learning_rate": 1.0835e-05,
+      "loss": 0.0582,
+      "step": 23500
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 2.4053075313568115,
+      "learning_rate": 1.0001666666666668e-05,
+      "loss": 0.0577,
+      "step": 24000
+    },
+    {
+      "epoch": 2.45,
+      "grad_norm": 2.3901314735412598,
+      "learning_rate": 9.168333333333335e-06,
+      "loss": 0.0543,
+      "step": 24500
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 1.9612762928009033,
+      "learning_rate": 8.334999999999999e-06,
+      "loss": 0.0522,
+      "step": 25000
+    },
+    {
+      "epoch": 2.55,
+      "grad_norm": 1.849785566329956,
+      "learning_rate": 7.501666666666666e-06,
+      "loss": 0.0518,
+      "step": 25500
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 2.1459758281707764,
+      "learning_rate": 6.668333333333334e-06,
+      "loss": 0.052,
+      "step": 26000
+    },
+    {
+      "epoch": 2.65,
+      "grad_norm": 1.2251453399658203,
+      "learning_rate": 5.835e-06,
+      "loss": 0.0546,
+      "step": 26500
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 2.3431410789489746,
+      "learning_rate": 5.001666666666667e-06,
+      "loss": 0.0571,
+      "step": 27000
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 2.283482074737549,
+      "learning_rate": 4.168333333333334e-06,
+      "loss": 0.053,
+      "step": 27500
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 1.6145457029342651,
+      "learning_rate": 3.335e-06,
+      "loss": 0.0538,
+      "step": 28000
+    },
+    {
+      "epoch": 2.85,
+      "grad_norm": 1.8216482400894165,
+      "learning_rate": 2.5016666666666667e-06,
+      "loss": 0.0535,
+      "step": 28500
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 1.7675800323486328,
+      "learning_rate": 1.6683333333333336e-06,
+      "loss": 0.0533,
+      "step": 29000
+    },
+    {
+      "epoch": 2.95,
+      "grad_norm": 1.378221869468689,
+      "learning_rate": 8.35e-07,
+      "loss": 0.0513,
+      "step": 29500
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.2478489875793457,
+      "learning_rate": 1.666666666666667e-09,
+      "loss": 0.0521,
+      "step": 30000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.12606243789196014,
+      "eval_mse": 0.12606243263783948,
+      "eval_runtime": 11.2592,
+      "eval_samples_per_second": 1776.328,
+      "eval_steps_per_second": 222.041,
+      "step": 30000
+    },
+    {
+      "epoch": 3.0,
+      "step": 30000,
+      "total_flos": 3952243439859456.0,
+      "train_loss": 0.10308435103098551,
+      "train_runtime": 528.9789,
+      "train_samples_per_second": 453.699,
+      "train_steps_per_second": 56.713
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 30000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3952243439859456.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d8dd202ded227543427b2893c75589574e6a44546b0deeef2de35e337715c16
+size 5201