File size: 97,854 Bytes
cc05668 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 | 1: W1124 00:08:17.923000 737761 torch/distributed/run.py:792]
1: W1124 00:08:17.923000 737761 torch/distributed/run.py:792] *****************************************
1: W1124 00:08:17.923000 737761 torch/distributed/run.py:792] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
1: W1124 00:08:17.923000 737761 torch/distributed/run.py:792] *****************************************
0: W1124 00:08:17.924000 3081902 torch/distributed/run.py:792]
0: W1124 00:08:17.924000 3081902 torch/distributed/run.py:792] *****************************************
0: W1124 00:08:17.924000 3081902 torch/distributed/run.py:792] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
0: W1124 00:08:17.924000 3081902 torch/distributed/run.py:792] *****************************************
2: W1124 00:08:17.928000 1779991 torch/distributed/run.py:792]
2: W1124 00:08:17.928000 1779991 torch/distributed/run.py:792] *****************************************
2: W1124 00:08:17.928000 1779991 torch/distributed/run.py:792] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
2: W1124 00:08:17.928000 1779991 torch/distributed/run.py:792] *****************************************
3: W1124 00:08:17.934000 3626745 torch/distributed/run.py:792]
3: W1124 00:08:17.934000 3626745 torch/distributed/run.py:792] *****************************************
3: W1124 00:08:17.934000 3626745 torch/distributed/run.py:792] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
3: W1124 00:08:17.934000 3626745 torch/distributed/run.py:792] *****************************************
2: [2025-11-24 00:08:36,323] [INFO] [axolotl.utils.schemas.validation.check_eval_packing:119] [PID:1780066] [RANK:0] explicitly setting `eval_sample_packing` to match `sample_packing`[39m
0: [2025-11-24 00:08:36,323] [INFO] [axolotl.utils.schemas.validation.check_eval_packing:119] [PID:3081979] [RANK:0] explicitly setting `eval_sample_packing` to match `sample_packing`[39m
2: [2025-11-24 00:08:36,323] [INFO] [axolotl.utils.schemas.validation.hint_sample_packing_padding:218] [PID:1780066] [RANK:0] Setting `pad_to_sequence_len: true` to prevent memory leaks when sample_packing[39m
0: [2025-11-24 00:08:36,323] [INFO] [axolotl.utils.schemas.validation.hint_sample_packing_padding:218] [PID:3081979] [RANK:0] Setting `pad_to_sequence_len: true` to prevent memory leaks when sample_packing[39m
3: [2025-11-24 00:08:36,434] [INFO] [axolotl.utils.schemas.validation.check_eval_packing:119] [PID:3626820] [RANK:0] explicitly setting `eval_sample_packing` to match `sample_packing`[39m
3: [2025-11-24 00:08:36,434] [INFO] [axolotl.utils.schemas.validation.hint_sample_packing_padding:218] [PID:3626820] [RANK:0] Setting `pad_to_sequence_len: true` to prevent memory leaks when sample_packing[39m
1: [2025-11-24 00:08:36,535] [INFO] [axolotl.utils.schemas.validation.check_eval_packing:119] [PID:737836] [RANK:0] explicitly setting `eval_sample_packing` to match `sample_packing`[39m
1: [2025-11-24 00:08:36,535] [INFO] [axolotl.utils.schemas.validation.hint_sample_packing_padding:218] [PID:737836] [RANK:0] Setting `pad_to_sequence_len: true` to prevent memory leaks when sample_packing[39m
0: [33m[2025-11-24 00:08:40,005] [WARNING] [axolotl.utils.config.normalize_config:139] [PID:3081979] [RANK:0] Invalid value for save_steps (1.6666666666666667) from saves_per_epoch and/or num_epochs. Saving at training end only.[39m
0: [2025-11-24 00:08:40,025] [INFO] [axolotl.cli.config.load_cfg:245] [PID:3081979] [RANK:0] config:
0: {
0: "activation_offloading": false,
0: "auto_resume_from_checkpoints": true,
0: "axolotl_config_path": "/lustre/fswork/projects/rech/dgo/udv55np/train/tmp/1763939290349239182.yaml",
0: "base_model": "/lustre/fswork/projects/rech/qwv/udv55np/Gemma/base/gemma-3-12b",
0: "base_model_config": "/lustre/fswork/projects/rech/qwv/udv55np/Gemma/base/gemma-3-12b",
0: "batch_size": 16,
0: "bf16": true,
0: "capabilities": {
0: "bf16": true,
0: "compute_capability": "sm_90",
0: "fp8": false,
0: "n_gpu": 16,
0: "n_node": 1
0: },
0: "chat_template": "gemma3",
0: "context_parallel_size": 1,
0: "dataloader_num_workers": 16,
0: "dataloader_pin_memory": true,
0: "dataloader_prefetch_factor": 256,
0: "dataset_prepared_path": "/lustre/fswork/projects/rech/dgo/udv55np/dataset_gemma/Nemotron-Super-49B-v1_5/split_0",
0: "dataset_processes": 192,
0: "datasets": [
0: {
0: "chat_template": "tokenizer_default",
0: "data_files": [
0: "/lustre/fswork/projects/rech/qwv/udv55np/dataset/ift/Nemotron-Super-49B-v1_5/no_thinking/0007.jsonl",
0: "/lustre/fswork/projects/rech/qwv/udv55np/dataset/ift/Nemotron-Super-49B-v1_5/no_thinking/0009.jsonl",
0: "/lustre/fswork/projects/rech/qwv/udv55np/dataset/ift/Nemotron-Super-49B-v1_5/no_thinking/0005.jsonl",
0: "/lustre/fswork/projects/rech/qwv/udv55np/dataset/ift/Nemotron-Super-49B-v1_5/no_thinking/0006.jsonl",
0: "/lustre/fswork/projects/rech/qwv/udv55np/dataset/ift/Nemotron-Super-49B-v1_5/no_thinking/0014.jsonl",
0: "/lustre/fswork/projects/rech/qwv/udv55np/dataset/ift/Nemotron-Super-49B-v1_5/no_thinking/0010.jsonl",
0: "/lustre/fswork/projects/rech/qwv/udv55np/dataset/ift/Nemotron-Super-49B-v1_5/no_thinking/0012.jsonl",
0: "/lustre/fswork/projects/rech/qwv/udv55np/dataset/ift/Nemotron-Super-49B-v1_5/no_thinking/0008.jsonl",
0: "/lustre/fswork/projects/rech/qwv/udv55np/dataset/ift/Nemotron-Super-49B-v1_5/no_thinking/0001.jsonl",
0: "/lustre/fswork/projects/rech/qwv/udv55np/dataset/ift/Nemotron-Super-49B-v1_5/no_thinking/0002.jsonl",
0: "/lustre/fswork/projects/rech/qwv/udv55np/dataset/ift/Nemotron-Super-49B-v1_5/no_thinking/0013.jsonl",
0: "/lustre/fswork/projects/rech/qwv/udv55np/dataset/ift/Nemotron-Super-49B-v1_5/no_thinking/0015.jsonl",
0: "/lustre/fswork/projects/rech/qwv/udv55np/dataset/ift/Nemotron-Super-49B-v1_5/no_thinking/0004.jsonl",
0: "/lustre/fswork/projects/rech/qwv/udv55np/dataset/ift/Nemotron-Super-49B-v1_5/no_thinking/0011.jsonl",
0: "/lustre/fswork/projects/rech/qwv/udv55np/dataset/ift/Nemotron-Super-49B-v1_5/no_thinking/0000.jsonl",
0: "/lustre/fswork/projects/rech/qwv/udv55np/dataset/ift/Nemotron-Super-49B-v1_5/no_thinking/0003.jsonl"
0: ],
0: "ds_type": "json",
0: "field_messages": "conversations",
0: "message_property_mappings": {
0: "content": "content",
0: "role": "role"
0: },
0: "path": "/lustre/fswork/projects/rech/qwv/udv55np/dataset/ift/Nemotron-Super-49B-v1_5/no_thinking",
0: "trust_remote_code": false,
0: "type": "chat_template"
0: }
0: ],
0: "ddp": true,
0: "deepspeed": {
0: "bf16": {
0: "enabled": true
0: },
0: "gradient_accumulation_steps": "auto",
0: "gradient_clipping": "auto",
0: "train_batch_size": "auto",
0: "train_micro_batch_size_per_gpu": "auto",
0: "wall_clock_breakdown": false,
0: "zero_optimization": {
0: "contiguous_gradients": true,
0: "overlap_comm": true,
0: "reduce_bucket_size": "auto",
0: "stage": 3,
0: "stage3_gather_16bit_weights_on_model_save": true,
0: "stage3_param_persistence_threshold": "auto",
0: "stage3_prefetch_bucket_size": "auto",
0: "sub_group_size": 0
0: }
0: },
0: "device": "cuda:0",
0: "device_map": {
0: "": 0
0: },
0: "dion_rank_fraction": 1.0,
0: "dion_rank_multiple_of": 1,
0: "env_capabilities": {
0: "torch_version": "2.6.0"
0: },
0: "eot_tokens": [
0: "<end_of_turn>"
0: ],
0: "eval_batch_size": 1,
0: "eval_causal_lm_metrics": [
0: "sacrebleu",
0: "comet",
0: "ter",
0: "chrf"
0: ],
0: "eval_max_new_tokens": 128,
0: "eval_sample_packing": true,
0: "eval_table_size": 0,
0: "evals_per_epoch": 0,
0: "flash_attention": true,
0: "fp16": false,
0: "gradient_accumulation_steps": 1,
0: "gradient_checkpointing": true,
0: "gradient_checkpointing_kwargs": {
0: "use_reentrant": true
0: },
0: "is_multimodal": true,
0: "learning_rate": 2e-06,
0: "lisa_layers_attribute": "model.layers",
0: "load_best_model_at_end": false,
0: "load_in_4bit": false,
0: "load_in_8bit": false,
0: "local_rank": 0,
0: "logging_steps": 10,
0: "lora_dropout": 0.0,
0: "loraplus_lr_embedding": 1e-06,
0: "lr_scheduler": "warmup_stable_decay",
0: "lr_scheduler_kwargs": {
0: "min_lr_ratio": 0.1,
0: "num_decay_steps": 200
0: },
0: "max_prompt_len": 512,
0: "mean_resizing_embeddings": false,
0: "micro_batch_size": 1,
0: "model_config_type": "gemma3",
0: "num_epochs": 0.6,
0: "optimizer": "adamw_torch_fused",
0: "output_dir": "/lustre/fswork/projects/rech/dgo/udv55np/ift/Nemotron-Super-49B-v1_5/gemma-3-12b/0",
0: "pad_to_sequence_len": true,
0: "pretrain_multipack_attn": true,
0: "pretrain_multipack_buffer_size": 10000,
0: "processor_config": "/lustre/fswork/projects/rech/qwv/udv55np/Gemma/base/gemma-3-12b",
0: "profiler_steps_start": 0,
0: "qlora_sharded_model_loading": false,
0: "ray_num_workers": 1,
0: "resources_per_worker": {
0: "GPU": 1
0: },
0: "sample_packing": true,
0: "sample_packing_bin_size": 200,
0: "sample_packing_group_size": 100000,
0: "save_only_model": true,
0: "save_safetensors": true,
0: "save_total_limit": 20,
0: "saves_per_epoch": 1,
0: "sequence_len": 16384,
0: "shuffle_before_merging_datasets": false,
0: "shuffle_merged_datasets": true,
0: "skip_prepare_dataset": false,
0: "strict": false,
0: "tensor_parallel_size": 1,
0: "tf32": false,
0: "tiled_mlp_use_original_mlp": true,
0: "tokenizer_config": "/lustre/fswork/projects/rech/qwv/udv55np/Gemma/base/gemma-3-27b",
0: "torch_dtype": "torch.bfloat16",
0: "train_on_inputs": false,
0: "trl": {
0: "log_completions": false,
0: "mask_truncated_completions": false,
0: "ref_model_mixup_alpha": 0.9,
0: "ref_model_sync_steps": 64,
0: "scale_rewards": true,
0: "sync_ref_model": false,
0: "use_vllm": false,
0: "vllm_server_host": "0.0.0.0",
0: "vllm_server_port": 8000
0: },
0: "use_ray": false,
0: "use_tensorboard": true,
0: "val_set_size": 0.0,
0: "vllm": {
0: "device": "auto",
0: "dtype": "auto",
0: "gpu_memory_utilization": 0.9,
0: "host": "0.0.0.0",
0: "port": 8000
0: },
0: "warmup_steps": 100,
0: "weight_decay": 0.0,
0: "world_size": 16
0: }[39m
0: [2025-11-24 00:08:40,026] [INFO] [axolotl.cli.checks.check_user_token:35] [PID:3081979] [RANK:0] Skipping HuggingFace token verification because HF_HUB_OFFLINE is set to True. Only local files will be used.[39m
0: [2025-11-24 00:08:41,217] [INFO] [axolotl.utils.data.shared.load_preprocessed_dataset:472] [PID:3081979] [RANK:0] Loading prepared dataset from disk at /lustre/fswork/projects/rech/dgo/udv55np/dataset_gemma/Nemotron-Super-49B-v1_5/split_0/06698e902d3dba325ca34849b1dea5ea...[39m
0: [2025-11-24 00:09:14,927] [INFO] [axolotl.utils.samplers.multipack.calc_min_len:436] [PID:3081979] [RANK:0] gather_len_batches: [18976, 18976, 18976, 18975, 18977, 18976, 18975, 18976, 18976, 18975, 18976, 18976, 18976, 18976, 18976, 18976][39m
0: [2025-11-24 00:09:14,950] [INFO] [axolotl.utils.trainer.calc_sample_packing_eff_est:495] [PID:3081979] [RANK:0] sample_packing_eff_est across ranks: [0.9989354014396667, 0.9988301396369934, 0.9989880323410034, 0.9988827705383301, 0.9988827705383301, 0.9988827705383301, 0.9989354014396667, 0.9989354014396667, 0.9989354014396667, 0.9988827705383301, 0.9989354014396667, 0.9988827705383301, 0.9988827705383301, 0.9988827705383301, 0.9988827705383301, 0.9989354014396667][39m
0: [2025-11-24 00:09:14,959] [INFO] [axolotl.utils.data.sft._prepare_standard_dataset:127] [PID:3081979] [RANK:0] Maximum number of steps set at 711[39m
3: Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.52, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
1: Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.52, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
3: Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.52, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
1: Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.52, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
2: Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.52, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
2: Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.52, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
2: Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.52, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
2: Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.52, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
1: Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.52, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
1: Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.52, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
0: Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.52, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
3: Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.52, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
3: Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.52, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
0: Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.52, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
0: Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.52, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
0: Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.52, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
0: [2025-11-24 00:09:22,718] [INFO] [axolotl.monkeypatch.transformers.trainer_loss_calc.patch_evaluation_loop:110] [PID:3081979] [RANK:0] Patched Trainer.evaluation_loop with nanmean loss calculation[39m
0: [2025-11-24 00:09:22,719] [INFO] [axolotl.monkeypatch.transformers.trainer_loss_calc.patch_maybe_log_save_evaluate:164] [PID:3081979] [RANK:0] Patched Trainer._maybe_log_save_evaluate with nanmean loss calculation[39m
3:
Loading checkpoint shards: 0%| | 0/5 [00:00<?, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00<?, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00<?, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00<?, ?it/s]
Loading checkpoint shards: 20%|ββ | 1/5 [00:11<00:47, 11.79s/it]
Loading checkpoint shards: 20%|ββ | 1/5 [00:11<00:47, 11.79s/it]
Loading checkpoint shards: 20%|ββ | 1/5 [00:11<00:47, 11.79s/it]
Loading checkpoint shards: 20%|ββ | 1/5 [00:11<00:47, 11.79s/it]
Loading checkpoint shards: 40%|ββββ | 2/5 [00:22<00:32, 10.98s/it]
Loading checkpoint shards: 40%|ββββ | 2/5 [00:22<00:32, 10.97s/it]
Loading checkpoint shards: 40%|ββββ | 2/5 [00:22<00:32, 10.98s/it]
Loading checkpoint shards: 40%|ββββ | 2/5 [00:22<00:32, 10.98s/it]
Loading checkpoint shards: 60%|ββββββ | 3/5 [00:31<00:20, 10.27s/it]
Loading checkpoint shards: 60%|ββββοΏ½
1:
Loading checkpoint shards: 0%| | 0/5 [00:00<?, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00<?, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00<?, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00<?, ?it/s]
Loading checkpoint shards: 20%|ββ | 1/5 [00:11<00:47, 11.79s/it]
Loading checkpoint shards: 20%|ββ | 1/5 [00:11<00:47, 11.79s/it]
Loading checkpoint shards: 20%|ββ | 1/5 [00:11<00:47, 11.79s/it]
Loading checkpoint shards: 20%|ββ | 1/5 [00:11<00:47, 11.79s/it]
Loading checkpoint shards: 40%|ββββ | 2/5 [00:22<00:32, 10.98s/it]
Loading checkpoint shards: 40%|ββββ | 2/5 [00:22<00:32, 10.98s/it]
Loading checkpoint shards: 40%|ββββ | 2/5 [00:22<00:32, 10.97s/it]
Loading checkpoint shards: 40%|ββββ | 2/5 [00:22<00:32, 10.98s/it]
Loading checkpoint shards: 60%|ββββββ | 3/5 [00:31<00:20, 10.27s/it]
Loading checkpoint shards: 60%|ββββοΏ½
2:
Loading checkpoint shards: 0%| | 0/5 [00:00<?, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00<?, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00<?, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00<?, ?it/s]
Loading checkpoint shards: 20%|ββ | 1/5 [00:11<00:47, 11.79s/it]
Loading checkpoint shards: 20%|ββ | 1/5 [00:11<00:47, 11.79s/it]
Loading checkpoint shards: 20%|ββ | 1/5 [00:11<00:47, 11.79s/it]
Loading checkpoint shards: 20%|ββ | 1/5 [00:11<00:47, 11.79s/it]
Loading checkpoint shards: 40%|ββββ | 2/5 [00:22<00:32, 10.98s/it]
Loading checkpoint shards: 40%|ββββ | 2/5 [00:22<00:32, 10.98s/it]
Loading checkpoint shards: 40%|ββββ | 2/5 [00:22<00:32, 10.98s/it]
Loading checkpoint shards: 40%|ββββ | 2/5 [00:22<00:32, 10.98s/it]
Loading checkpoint shards: 60%|ββββββ | 3/5 [00:31<00:20, 10.27s/it]
Loading checkpoint shards: 60%|ββββοΏ½
0:
Loading checkpoint shards: 0%| | 0/5 [00:00<?, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00<?, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00<?, ?it/s]
Loading checkpoint shards: 0%| | 0/5 [00:00<?, ?it/s]
Loading checkpoint shards: 20%|ββ | 1/5 [00:11<00:47, 11.79s/it]
Loading checkpoint shards: 20%|ββ | 1/5 [00:11<00:47, 11.79s/it]
Loading checkpoint shards: 20%|ββ | 1/5 [00:11<00:47, 11.79s/it]
Loading checkpoint shards: 20%|ββ | 1/5 [00:15<01:00, 15.22s/it]
Loading checkpoint shards: 40%|ββββ | 2/5 [00:22<00:32, 10.98s/it]
Loading checkpoint shards: 40%|ββββ | 2/5 [00:22<00:32, 10.98s/it]
Loading checkpoint shards: 40%|ββββ | 2/5 [00:22<00:32, 10.97s/it]
Loading checkpoint shards: 40%|ββββ | 2/5 [00:25<00:36, 12.21s/it]
Loading checkpoint shards: 60%|ββββββ | 3/5 [00:31<00:20, 10.27s/it]
Loading checkpoint shards: 60%|ββββοΏ½
0: οΏ½β | 3/5 [00:31<00:20, 10.27s/it]
Loading checkpoint shards: 60%|ββββββ | 3/5 [00:31<00:20, 10.27s/it]
Loading checkpoint shards: 60%|ββββββ | 3/5 [00:35<00:22, 11.47s/it]
Loading checkpoint shards: 80%|ββββββββ | 4/5 [00:41<00:10, 10.19s/it]
Loading checkpoint shards: 80%|ββββββββ | 4/5 [00:41<00:10, 10.19s/it]
Loading checkpoint shards: 80%|ββββββββ | 4/5 [00:41<00:10, 10.19s/it]
Loading checkpoint shards: 80%|ββββββββ | 4/5 [00:45<00:10, 10.54s/it]
Loading checkpoint shards: 100%|ββββββββββ| 5/5 [00:51<00:00, 9.95s/it]
Loading checkpoint shards: 100%|ββββββββββ| 5/5 [00:51<00:00, 10.25s/it]
3: οΏ½β | 3/5 [00:31<00:20, 10.27s/it]
Loading checkpoint shards: 60%|ββββββ | 3/5 [00:31<00:20, 10.27s/it]
Loading checkpoint shards: 60%|ββββββ | 3/5 [00:31<00:20, 10.27s/it]
Loading checkpoint shards: 80%|ββββββββ | 4/5 [00:41<00:10, 10.19s/it]
Loading checkpoint shards: 80%|ββββββββ | 4/5 [00:41<00:10, 10.19s/it]
Loading checkpoint shards: 80%|ββββββββ | 4/5 [00:41<00:10, 10.19s/it]
Loading checkpoint shards: 80%|ββββββββ | 4/5 [00:41<00:10, 10.19s/it]
Loading checkpoint shards: 100%|ββββββββββ| 5/5 [00:51<00:00, 9.95s/it]
Loading checkpoint shards: 100%|ββββββββββ| 5/5 [00:51<00:00, 9.95s/it]
Loading checkpoint shards: 100%|ββββββββββ| 5/5 [00:51<00:00, 9.95s/it]
Loading checkpoint shards: 100%|ββββββββββ| 5/5 [00:51<00:00, 10.25s/it]
1: οΏ½β | 3/5 [00:31<00:20, 10.27s/it]
Loading checkpoint shards: 60%|ββββββ | 3/5 [00:31<00:20, 10.27s/it]
Loading checkpoint shards: 60%|ββββββ | 3/5 [00:31<00:20, 10.27s/it]
Loading checkpoint shards: 80%|ββββββββ | 4/5 [00:41<00:10, 10.19s/it]
Loading checkpoint shards: 80%|ββββββββ | 4/5 [00:41<00:10, 10.19s/it]
Loading checkpoint shards: 80%|ββββββββ | 4/5 [00:41<00:10, 10.19s/it]
Loading checkpoint shards: 80%|ββββββββ | 4/5 [00:41<00:10, 10.19s/it]
Loading checkpoint shards: 100%|ββββββββββ| 5/5 [00:51<00:00, 9.95s/it]
Loading checkpoint shards: 100%|ββββββββββ| 5/5 [00:51<00:00, 9.95s/it]
Loading checkpoint shards: 100%|ββββββββββ| 5/5 [00:51<00:00, 9.95s/it]
Loading checkpoint shards: 100%|ββββββββββ| 5/5 [00:51<00:00, 10.25s/it]
Loading checkpoint shards: 100%|ββββββββββ| 5/5 [00:51<00:00, 10.25
1: s/it]
1:
3:
Loading checkpoint shards: 100%|ββββββββββ| 5/5 [00:51<00:00, 10.25s/it]
Loading checkpoint shards: 100%|ββββββββββ| 5/5 [00:51<00:00, 10.25s/it]
0:
Loading checkpoint shards: 100%|ββββββββββ| 5/5 [00:51<00:00, 9.95s/it]
Loading checkpoint shards: 100%|ββββββββββ| 5/5 [00:51<00:00, 9.95s/it]
Loading checkpoint shards: 100%|ββββββββββ| 5/5 [00:51<00:00, 10.25s/it]
1:
Loading checkpoint shards: 100%|ββββββββββ| 5/5 [00:51<00:00, 10.25s/it]
3:
0:
Loading checkpoint shards: 100%|ββββββββββ| 5/5 [00:51<00:00, 10.25s/it]
2: οΏ½β | 3/5 [00:31<00:20, 10.27s/it]
Loading checkpoint shards: 60%|ββββββ | 3/5 [00:31<00:20, 10.27s/it]
Loading checkpoint shards: 60%|ββββββ | 3/5 [00:31<00:20, 10.27s/it]
Loading checkpoint shards: 80%|ββββββββ | 4/5 [00:41<00:10, 10.19s/it]
Loading checkpoint shards: 80%|ββββββββ | 4/5 [00:41<00:10, 10.19s/it]
Loading checkpoint shards: 80%|ββββββββ | 4/5 [00:41<00:10, 10.19s/it]
Loading checkpoint shards: 80%|ββββββββ | 4/5 [00:41<00:10, 10.19s/it]
Loading checkpoint shards: 100%|ββββββββββ| 5/5 [00:51<00:00, 9.95s/it]
Loading checkpoint shards: 100%|ββββββββββ| 5/5 [00:51<00:00, 9.95s/it]
Loading checkpoint shards: 100%|ββββββββββ| 5/5 [00:51<00:00, 9.95s/it]
Loading checkpoint shards: 100%|ββββββββββ| 5/5 [00:51<00:00, 10.25s/it]
3:
Loading checkpoint shards: 100%|ββββββββββ| 5/5 [00:51<00:00, 9.95s/it]
Loading checkpoint shards: 100%|ββββββββββ| 5/5 [00:51<00:00, 10.25s/it]
2:
Loading checkpoint shards: 100%|ββββββββββ| 5/5 [00:51<00:00, 10.25s/it]
2:
Loading checkpoint shards: 100%|ββββββββββ| 5/5 [00:51<00:00, 10.25s/it]
2:
Loading checkpoint shards: 100%|ββββββββββ| 5/5 [00:51<00:00, 9.95s/it]
Loading checkpoint shards: 100%|ββββββββββ| 5/5 [00:51<00:00, 10.25s/it]
1:
Loading checkpoint shards: 100%|ββββββββββ| 5/5 [00:51<00:00, 9.95s/it]
Loading checkpoint shards: 100%|ββββββββββ| 5/5 [00:51<00:00, 10.25s/it]
0:
Loading checkpoint shards: 100%|ββββββββββ| 5/5 [00:54<00:00, 10.29s/it]
Loading checkpoint shards: 100%|ββββββββββ| 5/5 [00:54<00:00, 10.97s/it]
0: [2025-11-24 00:10:19,017] [INFO] [axolotl.loaders.model._configure_embedding_dtypes:345] [PID:3081979] [RANK:0] Converting modules to torch.bfloat16[39m
0: [2025-11-24 00:10:22,748] [INFO] [axolotl.train.save_initial_configs:416] [PID:3081979] [RANK:0] Pre-saving tokenizer to /lustre/fswork/projects/rech/dgo/udv55np/ift/Nemotron-Super-49B-v1_5/gemma-3-12b/0...[39m
0: [2025-11-24 00:10:23,317] [INFO] [axolotl.train.save_initial_configs:419] [PID:3081979] [RANK:0] Pre-saving model config to /lustre/fswork/projects/rech/dgo/udv55np/ift/Nemotron-Super-49B-v1_5/gemma-3-12b/0...[39m
0: [2025-11-24 00:10:23,327] [INFO] [axolotl.train.save_initial_configs:423] [PID:3081979] [RANK:0] Pre-saving processor to /lustre/fswork/projects/rech/dgo/udv55np/ift/Nemotron-Super-49B-v1_5/gemma-3-12b/0...[39m
0: [2025-11-24 00:10:26,392] [INFO] [axolotl.train.execute_training:203] [PID:3081979] [RANK:0] Starting trainer...[39m
0: [2025-11-24 00:11:58,358] [INFO] [axolotl.utils.samplers.multipack.calc_min_len:436] [PID:3081979] [RANK:0] gather_len_batches: [18976, 18976, 18976, 18976, 18976, 18976, 18976, 18976, 18976, 18976, 18976, 18976, 18976, 18976, 18976, 18976][39m
0: Parameter Offload - Persistent parameters statistics: param_count = 563, numel = 1166448
0: {'loss': 0.6182, 'grad_norm': 2.8189747023390073, 'learning_rate': 3.62e-07, 'memory/max_mem_active(gib)': 67.99, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.01}
0:
0%| | 0/711 [00:00<?, ?it/s]
0%| | 1/711 [03:14<38:20:16, 194.39s/it]
0%| | 2/711 [03:19<16:22:13, 83.12s/it]
0%| | 3/711 [03:24<9:20:24, 47.49s/it]
1%| | 4/711 [03:29<6:02:21, 30.75s/it]
1%| | 5/711 [03:35<4:14:24, 21.62s/it]
1%| | 6/711 [03:40<3:09:35, 16.14s/it]
1%| | 7/711 [03:45<2:27:08, 12.54s/it]
1%| | 8/711 [03:50<1:59:06, 10.17s/it]
1%|β | 9/711 [03:56<1:40:22, 8.58s/it]
1%|β | 10/711 [04:01<1:27:41, 7.51s/it]
1%|β | 10/711 [04:01<1:27:41, 7.51s/it]
2%|β | 11/711 [04:06<1:18:52, 6.76s/it]
2%|β | 12/711 [04:11<1:12:59, 6.27s/it]
2%|β | 13/711 [04:16<1:08:45, 5.91s/it]
2%|β | 14/711 [04:21<1:06:01, 5.68s/it]
2%|β | 15/711 [04:26<1:03:51, 5.51s/it]
2%|β | 16/711 [04:31<1:02:15, 5.38s/it]
2%|β | 17/711 [04:37<1:01:45, 5.34s/i
0: {'loss': 0.5822, 'grad_norm': 1.7276350224873818, 'learning_rate': 5.420000000000001e-07, 'memory/max_mem_active(gib)': 67.99, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.02}
0: {'loss': 0.5571, 'grad_norm': 2.161001413543057, 'learning_rate': 7.219999999999999e-07, 'memory/max_mem_active(gib)': 67.99, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.03}
0: t]
3%|β | 18/711 [04:42<1:01:12, 5.30s/it]
3%|β | 19/711 [04:47<1:00:37, 5.26s/it]
3%|β | 20/711 [04:52<1:00:10, 5.23s/it]
3%|β | 20/711 [04:52<1:00:10, 5.23s/it]
3%|β | 21/711 [04:57<59:44, 5.19s/it]
3%|β | 22/711 [05:02<59:22, 5.17s/it]
3%|β | 23/711 [05:07<59:00, 5.15s/it]
3%|β | 24/711 [05:13<58:57, 5.15s/it]
4%|β | 25/711 [05:18<59:09, 5.17s/it]
4%|β | 26/711 [05:23<58:51, 5.16s/it]
4%|β | 27/711 [05:28<58:27, 5.13s/it]
4%|β | 28/711 [05:33<58:17, 5.12s/it]
4%|β | 29/711 [05:38<58:07, 5.11s/it]
4%|β | 30/711 [05:44<59:10, 5.21s/it]
4%|β | 30/711 [05:44<59:10, 5.21s/it]
4%|β | 31/711 [05:49<58:50, 5.19s/it]
5%|β | 32/711 [05:54<58:36, 5.18s/it]
5%|β | 33/711 [05:59<59:31, 5
0: {'loss': 0.5218, 'grad_norm': 1.0906530849609661, 'learning_rate': 9.020000000000001e-07, 'memory/max_mem_active(gib)': 67.99, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.03}
0: .27s/it]
5%|β | 34/711 [06:04<58:50, 5.22s/it]
5%|β | 35/711 [06:10<58:21, 5.18s/it]
5%|β | 36/711 [06:15<57:59, 5.16s/it]
5%|β | 37/711 [06:20<57:35, 5.13s/it]
5%|β | 38/711 [06:25<57:22, 5.12s/it]
5%|β | 39/711 [06:30<57:16, 5.11s/it]
6%|β | 40/711 [06:35<57:20, 5.13s/it]
6%|β | 40/711 [06:35<57:20, 5.13s/it]
6%|β | 41/711 [06:40<57:23, 5.14s/it]
6%|β | 42/711 [06:45<57:09, 5.13s/it]
6%|β | 43/711 [06:51<57:31, 5.17s/it]
6%|β | 44/711 [06:56<57:25, 5.17s/it]
6%|β | 45/711 [07:01<57:08, 5.15s/it]
6%|β | 46/711 [07:06<57:01, 5.15s/it]
7%|β | 47/711 [07:11<56:53, 5.14s/it]
7%|β | 48/711 [07:16<57:06, 5.17s/it]
7%|β | 49/711 [07:22<57:03, 5.17s/it]
7%|β | 50/711 [07:27<57:26, 5.21s/it]
0: {'loss': 0.4959, 'grad_norm': 0.8804401875885586, 'learning_rate': 1.082e-06, 'memory/max_mem_active(gib)': 67.99, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.04}
0: {'loss': 0.4729, 'grad_norm': 1.7572079203155466, 'learning_rate': 1.262e-06, 'memory/max_mem_active(gib)': 67.99, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.05}
0:
7%|β | 50/711 [07:27<57:26, 5.21s/it]
7%|β | 51/711 [07:32<57:06, 5.19s/it]
7%|β | 52/711 [07:37<57:02, 5.19s/it]
7%|β | 53/711 [07:43<57:29, 5.24s/it]
8%|β | 54/711 [07:48<58:04, 5.30s/it]
8%|β | 55/711 [07:53<57:20, 5.25s/it]
8%|β | 56/711 [07:59<57:54, 5.30s/it]
8%|β | 57/711 [08:04<57:10, 5.25s/it]
8%|β | 58/711 [08:09<57:55, 5.32s/it]
8%|β | 59/711 [08:14<57:11, 5.26s/it]
8%|β | 60/711 [08:19<56:30, 5.21s/it]
8%|β | 60/711 [08:19<56:30, 5.21s/it]
9%|β | 61/711 [08:25<56:35, 5.22s/it]
9%|β | 62/711 [08:30<56:18, 5.21s/it]
9%|β | 63/711 [08:35<57:08, 5.29s/it]
9%|β | 64/711 [08:41<56:59, 5.28s/it]
9%|β | 65/711 [08:46<56:22, 5.24s/it]
9%|β | 66/711 [08:51<56:36, 5.27s/it]
9%|β | 67/711 [08:56<56:06, 5.23s/it]
1
0: {'loss': 0.4737, 'grad_norm': 1.0832691281380182, 'learning_rate': 1.442e-06, 'memory/max_mem_active(gib)': 67.99, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.06}
0: {'loss': 0.4648, 'grad_norm': 0.9351167776948649, 'learning_rate': 1.622e-06, 'memory/max_mem_active(gib)': 67.99, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.07}
0: 0%|β | 68/711 [09:01<55:32, 5.18s/it]
10%|β | 69/711 [09:06<55:12, 5.16s/it]
10%|β | 70/711 [09:12<55:17, 5.18s/it]
10%|β | 70/711 [09:12<55:17, 5.18s/it]
10%|β | 71/711 [09:17<54:55, 5.15s/it]
10%|β | 72/711 [09:22<54:39, 5.13s/it]
10%|β | 73/711 [09:27<54:25, 5.12s/it]
10%|β | 74/711 [09:32<54:18, 5.12s/it]
11%|β | 75/711 [09:37<54:05, 5.10s/it]
11%|β | 76/711 [09:42<54:01, 5.11s/it]
11%|β | 77/711 [09:47<53:56, 5.11s/it]
11%|β | 78/711 [09:52<54:06, 5.13s/it]
11%|β | 79/711 [09:57<53:56, 5.12s/it]
11%|ββ | 80/711 [10:03<54:04, 5.14s/it]
11%|ββ | 80/711 [10:03<54:04, 5.14s/it]
11%|ββ | 81/711 [10:08<55:07, 5.25s/it]
12%|ββ | 82/711 [10:13<54:50, 5.23s/it]
12%|ββ | 83/711 [10:19<55:29, 5.30s/it
0: {'loss': 0.4437, 'grad_norm': 1.0944333242533355, 'learning_rate': 1.802e-06, 'memory/max_mem_active(gib)': 67.99, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.08}
0: ]
12%|ββ | 84/711 [10:24<54:57, 5.26s/it]
12%|ββ | 85/711 [10:29<54:21, 5.21s/it]
12%|ββ | 86/711 [10:35<55:05, 5.29s/it]
12%|ββ | 87/711 [10:40<54:33, 5.25s/it]
12%|ββ | 88/711 [10:45<54:02, 5.20s/it]
13%|ββ | 89/711 [10:50<53:35, 5.17s/it]
13%|ββ | 90/711 [10:55<53:14, 5.14s/it]
13%|ββ | 90/711 [10:55<53:14, 5.14s/it]
13%|ββ | 91/711 [11:00<52:59, 5.13s/it]
13%|ββ | 92/711 [11:05<53:42, 5.21s/it]
13%|ββ | 93/711 [11:11<54:32, 5.30s/it]
13%|ββ | 94/711 [11:16<54:50, 5.33s/it]
13%|ββ | 95/711 [11:22<55:36, 5.42s/it]
14%|ββ | 96/711 [11:27<55:11, 5.38s/it]
14%|ββ | 97/711 [11:32<54:13, 5.30s/it]
14%|ββ | 98/711 [11:38<54:39, 5.35s/it]
14%|ββ | 99/711 [11:43<53:58, 5.29s/it]
14%|ββ | 100/711 [11:48<53:15, 5.23s/it]
0: {'loss': 0.4312, 'grad_norm': 0.821415164120209, 'learning_rate': 1.982e-06, 'memory/max_mem_active(gib)': 67.99, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.08}
0: {'loss': 0.4519, 'grad_norm': 1.098049116364939, 'learning_rate': 2e-06, 'memory/max_mem_active(gib)': 67.99, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.09}
0:
14%|ββ | 100/711 [11:48<53:15, 5.23s/it]
14%|ββ | 101/711 [11:53<52:46, 5.19s/it]
14%|ββ | 102/711 [11:58<52:21, 5.16s/it]
14%|ββ | 103/711 [12:03<52:00, 5.13s/it]
15%|ββ | 104/711 [12:08<51:44, 5.11s/it]
15%|ββ | 105/711 [12:14<51:39, 5.11s/it]
15%|ββ | 106/711 [12:19<51:43, 5.13s/it]
15%|ββ | 107/711 [12:24<51:34, 5.12s/it]
15%|ββ | 108/711 [12:29<51:22, 5.11s/it]
15%|ββ | 109/711 [12:34<51:11, 5.10s/it]
15%|ββ | 110/711 [12:39<51:14, 5.12s/it]
15%|ββ | 110/711 [12:39<51:14, 5.12s/it]
16%|ββ | 111/711 [12:44<51:43, 5.17s/it]
16%|ββ | 112/711 [12:50<51:33, 5.16s/it]
16%|ββ | 113/711 [12:55<52:08, 5.23s/it]
16%|ββ | 114/711 [13:00<51:48, 5.21s/it]
16%|ββ | 115/711 [13:05<51:23, 5.17s/it]
16%|ββ |
0: {'loss': 0.4418, 'grad_norm': 0.8654847799165983, 'learning_rate': 2e-06, 'memory/max_mem_active(gib)': 67.99, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.1}
0: {'loss': 0.4272, 'grad_norm': 0.8743836149172823, 'learning_rate': 2e-06, 'memory/max_mem_active(gib)': 67.99, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.11}
0: 116/711 [13:10<51:17, 5.17s/it]
16%|ββ | 117/711 [13:16<51:03, 5.16s/it]
17%|ββ | 118/711 [13:21<50:59, 5.16s/it]
17%|ββ | 119/711 [13:26<51:20, 5.20s/it]
17%|ββ | 120/711 [13:31<50:54, 5.17s/it]
17%|ββ | 120/711 [13:31<50:54, 5.17s/it]
17%|ββ | 121/711 [13:36<50:42, 5.16s/it]
17%|ββ | 122/711 [13:41<50:37, 5.16s/it]
17%|ββ | 123/711 [13:47<50:33, 5.16s/it]
17%|ββ | 124/711 [13:52<50:44, 5.19s/it]
18%|ββ | 125/711 [13:57<51:31, 5.28s/it]
18%|ββ | 126/711 [14:03<52:11, 5.35s/it]
18%|ββ | 127/711 [14:08<52:12, 5.36s/it]
18%|ββ | 128/711 [14:14<52:10, 5.37s/it]
18%|ββ | 129/711 [14:19<51:21, 5.29s/it]
18%|ββ | 130/711 [14:24<50:50, 5.25s/it]
18%|ββ | 130/711 [14:24<50:50, 5.25s/it]
18%|ββ | 131/
0: {'loss': 0.4317, 'grad_norm': 0.886837889977122, 'learning_rate': 2e-06, 'memory/max_mem_active(gib)': 67.99, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.12}
0: 711 [14:29<50:24, 5.22s/it]
19%|ββ | 132/711 [14:34<50:04, 5.19s/it]
19%|ββ | 133/711 [14:39<50:21, 5.23s/it]
19%|ββ | 134/711 [14:45<49:58, 5.20s/it]
19%|ββ | 135/711 [14:50<49:37, 5.17s/it]
19%|ββ | 136/711 [14:55<49:54, 5.21s/it]
19%|ββ | 137/711 [15:00<49:29, 5.17s/it]
19%|ββ | 138/711 [15:05<49:14, 5.16s/it]
20%|ββ | 139/711 [15:10<49:05, 5.15s/it]
20%|ββ | 140/711 [15:16<49:19, 5.18s/it]
20%|ββ | 140/711 [15:16<49:19, 5.18s/it]
20%|ββ | 141/711 [15:21<49:04, 5.17s/it]
20%|ββ | 142/711 [15:26<48:43, 5.14s/it]
20%|ββ | 143/711 [15:31<48:31, 5.13s/it]
20%|ββ | 144/711 [15:36<48:59, 5.19s/it]
20%|ββ | 145/711 [15:41<48:54, 5.19s/it]
21%|ββ | 146/711 [15:46<48:39, 5.17s/it]
21%|ββ | 147/711 [15:52<48:22, 5.15s/it]
21%|ββ | 148/7
0: {'loss': 0.4309, 'grad_norm': 1.0717708423744885, 'learning_rate': 2e-06, 'memory/max_mem_active(gib)': 67.99, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.13}
0: {'loss': 0.4316, 'grad_norm': 0.8573484702226136, 'learning_rate': 2e-06, 'memory/max_mem_active(gib)': 67.99, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.13}
0: 11 [15:57<48:11, 5.14s/it]
21%|ββ | 149/711 [16:02<48:06, 5.14s/it]
21%|ββ | 150/711 [16:07<48:06, 5.14s/it]
21%|ββ | 150/711 [16:07<48:06, 5.14s/it]
21%|ββ | 151/711 [16:12<48:00, 5.14s/it]
21%|βββ | 152/711 [16:17<48:35, 5.22s/it]
22%|βββ | 153/711 [16:23<48:21, 5.20s/it]
22%|βββ | 154/711 [16:28<48:00, 5.17s/it]
22%|βββ | 155/711 [16:33<47:54, 5.17s/it]
22%|βββ | 156/711 [16:38<47:42, 5.16s/it]
22%|βββ | 157/711 [16:43<47:36, 5.16s/it]
22%|βββ | 158/711 [16:48<47:27, 5.15s/it]
22%|βββ | 159/711 [16:54<48:09, 5.23s/it]
23%|βββ | 160/711 [16:59<47:40, 5.19s/it]
23%|βββ | 160/711 [16:59<47:40, 5.19s/it]
23%|βββ | 161/711 [17:04<47:17, 5.16s/it]
23%|βββ | 162/711 [17:09<47:17, 5.17s/it]
23%|οΏ½
0: {'loss': 0.4239, 'grad_norm': 0.8728825320101697, 'learning_rate': 2e-06, 'memory/max_mem_active(gib)': 67.99, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.14}
0: οΏ½οΏ½ββ | 163/711 [17:14<46:56, 5.14s/it]
23%|βββ | 164/711 [17:20<47:49, 5.25s/it]
23%|βββ | 165/711 [17:25<47:18, 5.20s/it]
23%|βββ | 166/711 [17:30<47:54, 5.27s/it]
23%|βββ | 167/711 [17:35<47:21, 5.22s/it]
24%|βββ | 168/711 [17:41<47:10, 5.21s/it]
24%|βββ | 169/711 [17:46<46:57, 5.20s/it]
24%|βββ | 170/711 [17:51<46:38, 5.17s/it]
24%|βββ | 170/711 [17:51<46:38, 5.17s/it]
24%|βββ | 171/711 [17:56<46:21, 5.15s/it]
24%|βββ | 172/711 [18:01<46:17, 5.15s/it]
24%|βββ | 173/711 [18:06<46:18, 5.16s/it]
24%|βββ | 174/711 [18:11<46:01, 5.14s/it]
25%|βββ | 175/711 [18:16<45:50, 5.13s/it]
25%|βββ | 176/711 [18:22<45:49, 5.14s/it]
25%|βββ | 177/711 [18:27<45:49, 5.15s/it]
25%|βββ | 178/711 [18:32<46:45, 5.26s/it]
25%|βββ | 179/
0: {'loss': 0.4173, 'grad_norm': 2.470513995230686, 'learning_rate': 2e-06, 'memory/max_mem_active(gib)': 67.99, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.15}
0: {'loss': 0.4151, 'grad_norm': 0.9038938137872402, 'learning_rate': 2e-06, 'memory/max_mem_active(gib)': 67.99, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.16}
0: 711 [18:37<46:12, 5.21s/it]
25%|βββ | 180/711 [18:43<45:49, 5.18s/it]
25%|βββ | 180/711 [18:43<45:49, 5.18s/it]
25%|βββ | 181/711 [18:48<45:33, 5.16s/it]
26%|βββ | 182/711 [18:53<45:22, 5.15s/it]
26%|βββ | 183/711 [18:58<45:10, 5.13s/it]
26%|βββ | 184/711 [19:03<45:33, 5.19s/it]
26%|βββ | 185/711 [19:08<45:10, 5.15s/it]
26%|βββ | 186/711 [19:13<44:56, 5.14s/it]
26%|βββ | 187/711 [19:18<44:44, 5.12s/it]
26%|βββ | 188/711 [19:24<45:35, 5.23s/it]
27%|βββ | 189/711 [19:29<45:10, 5.19s/it]
27%|βββ | 190/711 [19:34<44:59, 5.18s/it]
27%|βββ | 190/711 [19:34<44:59, 5.18s/it]
27%|βββ | 191/711 [19:39<44:41, 5.16s/it]
27%|βββ | 192/711 [19:44<44:29, 5.14s/it]
27%|βββ | 193/711 [19:50<44:25, 5.15s/i
0: {'loss': 0.4194, 'grad_norm': 2.3527260378633015, 'learning_rate': 2e-06, 'memory/max_mem_active(gib)': 67.99, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.17}
0: t]
27%|βββ | 194/711 [19:55<44:10, 5.13s/it]
27%|βββ | 195/711 [20:00<44:25, 5.17s/it]
28%|βββ | 196/711 [20:05<44:10, 5.15s/it]
28%|βββ | 197/711 [20:10<44:27, 5.19s/it]
28%|βββ | 198/711 [20:16<45:08, 5.28s/it]
28%|βββ | 199/711 [20:21<44:34, 5.22s/it]
28%|βββ | 200/711 [20:26<44:17, 5.20s/it]
28%|βββ | 200/711 [20:26<44:17, 5.20s/it]
28%|βββ | 201/711 [20:31<43:55, 5.17s/it]
28%|βββ | 202/711 [20:36<43:35, 5.14s/it]
29%|βββ | 203/711 [20:41<43:37, 5.15s/it]
29%|βββ | 204/711 [20:47<44:14, 5.24s/it]
29%|βββ | 205/711 [20:52<44:01, 5.22s/it]
29%|βββ | 206/711 [20:57<43:43, 5.20s/it]
29%|βββ | 207/711 [21:02<43:30, 5.18s/it]
29%|βββ | 208/711 [21:07<43:14, 5.16s/it]
29%|βββ | 209/711 [21:12<43:02, 5.15s/it]
30%|βββ
0: {'loss': 0.413, 'grad_norm': 0.893185793908122, 'learning_rate': 2e-06, 'memory/max_mem_active(gib)': 67.99, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.18}
0: {'loss': 0.4217, 'grad_norm': 1.160958862723743, 'learning_rate': 2e-06, 'memory/max_mem_active(gib)': 67.99, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.19}
0: | 210/711 [21:18<42:50, 5.13s/it]
30%|βββ | 210/711 [21:18<42:50, 5.13s/it]
30%|βββ | 211/711 [21:23<42:40, 5.12s/it]
30%|βββ | 212/711 [21:28<42:38, 5.13s/it]
30%|βββ | 213/711 [21:33<42:38, 5.14s/it]
30%|βββ | 214/711 [21:38<42:36, 5.14s/it]
30%|βββ | 215/711 [21:43<42:24, 5.13s/it]
30%|βββ | 216/711 [21:48<42:15, 5.12s/it]
31%|βββ | 217/711 [21:53<42:11, 5.12s/it]
31%|βββ | 218/711 [21:59<42:01, 5.12s/it]
31%|βββ | 219/711 [22:04<42:01, 5.12s/it]
31%|βββ | 220/711 [22:09<41:50, 5.11s/it]
31%|βββ | 220/711 [22:09<41:50, 5.11s/it]
31%|βββ | 221/711 [22:14<42:03, 5.15s/it]
31%|βββ | 222/711 [22:19<42:36, 5.23s/it]
31%|ββββ | 223/711 [22:25<42:39, 5.25s/it]
32%|ββββ | 224/711 [22:30<42
0: {'loss': 0.4102, 'grad_norm': 0.8461972280700218, 'learning_rate': 2e-06, 'memory/max_mem_active(gib)': 67.99, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.19}
0: :22, 5.22s/it]
32%|ββββ | 225/711 [22:35<42:13, 5.21s/it]
32%|ββββ | 226/711 [22:40<42:40, 5.28s/it]
32%|ββββ | 227/711 [22:46<42:11, 5.23s/it]
32%|ββββ | 228/711 [22:51<41:45, 5.19s/it]
32%|ββββ | 229/711 [22:56<41:33, 5.17s/it]
32%|ββββ | 230/711 [23:01<41:16, 5.15s/it]
32%|ββββ | 230/711 [23:01<41:16, 5.15s/it]
32%|ββββ | 231/711 [23:06<41:02, 5.13s/it]
33%|ββββ | 232/711 [23:11<40:52, 5.12s/it]
33%|ββββ | 233/711 [23:16<40:57, 5.14s/it]
33%|ββββ | 234/711 [23:21<40:58, 5.15s/it]
33%|ββββ | 235/711 [23:27<40:52, 5.15s/it]
33%|ββββ | 236/711 [23:32<40:41, 5.14s/it]
33%|ββββ | 237/711 [23:37<40:32, 5.13s/it]
33%|ββββ | 238/711 [23:42<40:21, 5.12s/it]
34%|ββββ | 239/711 [23:47<40:22, 5.13s/it]
34%|ββββ | 240/
0: {'loss': 0.4155, 'grad_norm': 0.8314605620161184, 'learning_rate': 2e-06, 'memory/max_mem_active(gib)': 67.99, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.2}
0: {'loss': 0.4045, 'grad_norm': 0.8328744939735258, 'learning_rate': 2e-06, 'memory/max_mem_active(gib)': 69.44, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.21}
0: 711 [23:52<40:14, 5.13s/it]
34%|ββββ | 240/711 [23:52<40:14, 5.13s/it]
34%|ββββ | 241/711 [23:57<40:04, 5.12s/it]
34%|ββββ | 242/711 [24:03<40:30, 5.18s/it]
34%|ββββ | 243/711 [24:08<40:55, 5.25s/it]
34%|ββββ | 244/711 [24:13<40:38, 5.22s/it]
34%|ββββ | 245/711 [24:18<40:16, 5.18s/it]
35%|ββββ | 246/711 [24:23<40:06, 5.18s/it]
35%|ββββ | 247/711 [24:29<40:20, 5.22s/it]
35%|ββββ | 248/711 [24:34<39:58, 5.18s/it]
35%|ββββ | 249/711 [24:39<39:40, 5.15s/it]
35%|ββββ | 250/711 [24:44<39:34, 5.15s/it]
35%|ββββ | 250/711 [24:44<39:34, 5.15s/it]
35%|ββββ | 251/711 [24:49<39:23, 5.14s/it]
35%|ββββ | 252/711 [24:54<39:08, 5.12s/it]
36%|ββββ | 253/711 [24:59<39:13, 5.14s/it]
36%|ββββ
0: {'loss': 0.4005, 'grad_norm': 0.8810433727017853, 'learning_rate': 2e-06, 'memory/max_mem_active(gib)': 69.44, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.22}
0: | 254/711 [25:05<39:10, 5.14s/it]
36%|ββββ | 255/711 [25:10<39:07, 5.15s/it]
36%|ββββ | 256/711 [25:15<39:17, 5.18s/it]
36%|ββββ | 257/711 [25:20<38:57, 5.15s/it]
36%|ββββ | 258/711 [25:26<39:48, 5.27s/it]
36%|ββββ | 259/711 [25:31<39:17, 5.22s/it]
37%|ββββ | 260/711 [25:36<38:58, 5.19s/it]
37%|ββββ | 260/711 [25:36<38:58, 5.19s/it]
37%|ββββ | 261/711 [25:41<38:40, 5.16s/it]
37%|ββββ | 262/711 [25:46<38:26, 5.14s/it]
37%|ββββ | 263/711 [25:51<38:26, 5.15s/it]
37%|ββββ | 264/711 [25:56<38:28, 5.16s/it]
37%|ββββ | 265/711 [26:02<38:16, 5.15s/it]
37%|ββββ | 266/711 [26:07<38:12, 5.15s/it]
38%|ββββ | 267/711 [26:12<38:50, 5.25s/it]
38%|ββββ | 268/711 [26:18<39:17, 5.32s/it]
38%|ββββ | 269/711 [26:23<38:44, 5.26s/it]
38%|βοΏ½
0: {'loss': 0.4021, 'grad_norm': 1.0060252029086465, 'learning_rate': 2e-06, 'memory/max_mem_active(gib)': 69.44, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.23}
0: [2025-11-24 00:38:52,072] [WARNING] [stage3.py:2150:step] 2 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
0: {'loss': 0.4124, 'grad_norm': 0.9014415482740915, 'learning_rate': 2e-06, 'memory/max_mem_active(gib)': 69.44, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.24}
0: οΏ½ββ | 270/711 [26:28<38:17, 5.21s/it]
38%|ββββ | 270/711 [26:28<38:17, 5.21s/it]
38%|ββββ | 271/711 [26:33<37:58, 5.18s/it]
38%|ββββ | 272/711 [26:38<37:42, 5.15s/it]
38%|ββββ | 273/711 [26:43<37:32, 5.14s/it]
39%|ββββ | 274/711 [26:49<39:58, 5.49s/it]
39%|ββββ | 275/711 [26:55<39:08, 5.39s/it]
39%|ββββ | 276/711 [27:00<38:28, 5.31s/it]
39%|ββββ | 277/711 [27:05<38:44, 5.36s/it]
39%|ββββ | 278/711 [27:10<38:16, 5.30s/it]
39%|ββββ | 279/711 [27:16<37:45, 5.24s/it]
39%|ββββ | 280/711 [27:21<37:26, 5.21s/it]
39%|ββββ | 280/711 [27:21<37:26, 5.21s/it]
40%|ββββ | 281/711 [27:26<38:16, 5.34s/it]
40%|ββββ | 282/711 [27:31<37:40, 5.27s/it]
40%|ββββ | 283/711 [27:37<37:37, 5.28s/it]
40%
0: {'loss': 0.3928, 'grad_norm': 1.1303634088009527, 'learning_rate': 2e-06, 'memory/max_mem_active(gib)': 69.44, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.24}
0: |ββββ | 284/711 [27:42<37:57, 5.33s/it]
40%|ββββ | 285/711 [27:47<37:34, 5.29s/it]
40%|ββββ | 286/711 [27:53<37:14, 5.26s/it]
40%|ββββ | 287/711 [27:58<37:31, 5.31s/it]
41%|ββββ | 288/711 [28:03<37:04, 5.26s/it]
41%|ββββ | 289/711 [28:08<36:40, 5.21s/it]
41%|ββββ | 290/711 [28:13<36:19, 5.18s/it]
41%|ββββ | 290/711 [28:13<36:19, 5.18s/it]
41%|ββββ | 291/711 [28:19<36:32, 5.22s/it]
41%|ββββ | 292/711 [28:24<36:57, 5.29s/it]
41%|ββββ | 293/711 [28:29<36:57, 5.31s/it]
41%|βββββ | 294/711 [28:35<36:36, 5.27s/it]
41%|βββββ | 295/711 [28:40<36:18, 5.24s/it]
42%|βββββ | 296/711 [28:45<35:59, 5.20s/it]
42%|βββββ | 297/711 [28:50<36:22, 5.27s/it]
42%|βββββ | 298/711 [28:55<36:02, 5.24s/it]
42%|βββββ | 299/711 [29:
0: {'loss': 0.4025, 'grad_norm': 0.8789278025527175, 'learning_rate': 2e-06, 'memory/max_mem_active(gib)': 69.44, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.25}
0: {'loss': 0.4015, 'grad_norm': 0.7615557087401322, 'learning_rate': 2e-06, 'memory/max_mem_active(gib)': 69.44, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.26}
0: 01<35:58, 5.24s/it]
42%|βββββ | 300/711 [29:06<36:01, 5.26s/it]
42%|βββββ | 300/711 [29:06<36:01, 5.26s/it]
42%|βββββ | 301/711 [29:11<35:42, 5.23s/it]
42%|βββββ | 302/711 [29:16<35:28, 5.20s/it]
43%|βββββ | 303/711 [29:21<35:11, 5.17s/it]
43%|βββββ | 304/711 [29:27<35:03, 5.17s/it]
43%|βββββ | 305/711 [29:32<35:16, 5.21s/it]
43%|βββββ | 306/711 [29:37<34:57, 5.18s/it]
43%|βββββ | 307/711 [29:42<34:42, 5.15s/it]
43%|βββββ | 308/711 [29:47<34:33, 5.15s/it]
43%|βββββ | 309/711 [29:53<35:23, 5.28s/it]
44%|βββββ | 310/711 [29:59<36:23, 5.45s/it]
44%|βββββ | 310/711 [29:59<36:23, 5.45s/it]
44%|βββββ | 311/711 [30:04<35:40, 5.35s/it]
44%|βββββ | 312/711 [30:09<35:47, 5.38s/it]
0: {'loss': 0.4047, 'grad_norm': 1.0096950251075136, 'learning_rate': 2e-06, 'memory/max_mem_active(gib)': 69.44, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.27}
0: 44%|βββββ | 313/711 [30:14<35:07, 5.30s/it]
44%|βββββ | 314/711 [30:20<35:18, 5.34s/it]
44%|βββββ | 315/711 [30:25<35:09, 5.33s/it]
44%|βββββ | 316/711 [30:30<34:42, 5.27s/it]
45%|βββββ | 317/711 [30:35<34:17, 5.22s/it]
45%|βββββ | 318/711 [30:40<34:02, 5.20s/it]
45%|βββββ | 319/711 [30:46<33:48, 5.18s/it]
45%|βββββ | 320/711 [30:51<33:36, 5.16s/it]
45%|βββββ | 320/711 [30:51<33:36, 5.16s/it]
45%|βββββ | 321/711 [30:56<33:30, 5.16s/it]
45%|βββββ | 322/711 [31:01<33:19, 5.14s/it]
45%|βββββ | 323/711 [31:06<33:37, 5.20s/it]
46%|βββββ | 324/711 [31:11<33:25, 5.18s/it]
46%|βββββ | 325/711 [31:17<33:17, 5.17s/it]
46%|βββββ | 326/711 [31:22<33:09, 5.17s/it]
46%|βββββ | 327/711 [31:27<33:08, 5.18s/it]
46%|βββ
0: {'loss': 0.4025, 'grad_norm': 0.9227721040091849, 'learning_rate': 2e-06, 'memory/max_mem_active(gib)': 69.44, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.28}
0: {'loss': 0.3987, 'grad_norm': 1.8038936518267323, 'learning_rate': 2e-06, 'memory/max_mem_active(gib)': 69.44, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.29}
0: ββ | 328/711 [31:32<32:55, 5.16s/it]
46%|βββββ | 329/711 [31:37<32:44, 5.14s/it]
46%|βββββ | 330/711 [31:42<32:58, 5.19s/it]
46%|βββββ | 330/711 [31:42<32:58, 5.19s/it]
47%|βββββ | 331/711 [31:48<32:46, 5.18s/it]
47%|βββββ | 332/711 [31:53<32:35, 5.16s/it]
47%|βββββ | 333/711 [31:58<33:05, 5.25s/it]
47%|βββββ | 334/711 [32:03<32:47, 5.22s/it]
47%|βββββ | 335/711 [32:09<33:10, 5.29s/it]
47%|βββββ | 336/711 [32:14<32:41, 5.23s/it]
47%|βββββ | 337/711 [32:19<32:21, 5.19s/it]
48%|βββββ | 338/711 [32:24<32:19, 5.20s/it]
48%|βββββ | 339/711 [32:29<32:05, 5.18s/it]
48%|βββββ | 340/711 [32:34<31:51, 5.15s/it]
48%|βββββ | 340/711 [32:34<31:51, 5.15s/it]
48%|βββββ | 341/711 [
0: {'loss': 0.4004, 'grad_norm': 0.8530478906547682, 'learning_rate': 2e-06, 'memory/max_mem_active(gib)': 69.44, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.3}
0: 32:40<31:54, 5.17s/it]
48%|βββββ | 342/711 [32:45<31:45, 5.16s/it]
48%|βββββ | 343/711 [32:50<31:37, 5.16s/it]
48%|βββββ | 344/711 [32:55<31:44, 5.19s/it]
49%|βββββ | 345/711 [33:00<31:29, 5.16s/it]
49%|βββββ | 346/711 [33:05<31:18, 5.15s/it]
49%|βββββ | 347/711 [33:10<31:07, 5.13s/it]
49%|βββββ | 348/711 [33:16<30:59, 5.12s/it]
49%|βββββ | 349/711 [33:21<30:57, 5.13s/it]
49%|βββββ | 350/711 [33:26<30:52, 5.13s/it]
49%|βββββ | 350/711 [33:26<30:52, 5.13s/it]
49%|βββββ | 351/711 [33:31<30:45, 5.13s/it]
50%|βββββ | 352/711 [33:36<30:36, 5.12s/it]
50%|βββββ | 353/711 [33:41<30:32, 5.12s/it]
50%|βββββ | 354/711 [33:46<30:26, 5.12s/it]
50%|βββββ | 355/711 [33:51<30:20, 5.11s/it]
50%|βββββ | 356/711 [33:57<30:13,
0: {'loss': 0.4055, 'grad_norm': 0.8072887895552343, 'learning_rate': 2e-06, 'memory/max_mem_active(gib)': 69.44, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.3}
0: 5.11s/it]
50%|βββββ | 357/711 [34:02<30:10, 5.11s/it]
50%|βββββ | 358/711 [34:07<30:07, 5.12s/it]
50%|βββββ | 359/711 [34:12<30:03, 5.12s/it]
51%|βββββ | 360/711 [34:17<29:57, 5.12s/it]
51%|βββββ | 360/711 [34:17<29:57, 5.12s/it]
51%|βββββ | 361/711 [34:22<29:53, 5.12s/it]
51%|βββββ | 362/711 [34:27<29:46, 5.12s/it]
51%|βββββ | 363/711 [34:32<29:41, 5.12s/it]
51%|βββββ | 364/711 [34:38<29:39, 5.13s/it]
51%|ββββββ | 365/711 [34:43<29:59, 5.20s/it]
51%|ββββββ | 366/711 [34:48<29:44, 5.17s/it]
52%|ββββββ | 367/711 [34:53<29:30, 5.15s/it]
52%|ββββββ | 368/711 [34:58<29:27, 5.15s/it]
52%|ββββββ | 369/711 [35:03<29:14, 5.13s/it]
52%|ββββββ | 370/711 [35:09<29:11, 5.14s/it]
0: {'loss': 0.4024, 'grad_norm': 0.8486839849343547, 'learning_rate': 2e-06, 'memory/max_mem_active(gib)': 69.44, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.31}
0: {'loss': 0.4021, 'grad_norm': 0.8529581759108179, 'learning_rate': 2e-06, 'memory/max_mem_active(gib)': 69.44, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.32}
0:
52%|ββββββ | 370/711 [35:09<29:11, 5.14s/it]
52%|ββββββ | 371/711 [35:14<29:01, 5.12s/it]
52%|ββββββ | 372/711 [35:19<28:54, 5.12s/it]
52%|ββββββ | 373/711 [35:24<29:01, 5.15s/it]
53%|ββββββ | 374/711 [35:29<28:53, 5.14s/it]
53%|ββββββ | 375/711 [35:34<28:43, 5.13s/it]
53%|ββββββ | 376/711 [35:39<28:33, 5.11s/it]
53%|ββββββ | 377/711 [35:44<28:25, 5.11s/it]
53%|ββββββ | 378/711 [35:49<28:21, 5.11s/it]
53%|ββββββ | 379/711 [35:55<28:52, 5.22s/it]
53%|ββββββ | 380/711 [36:00<28:33, 5.18s/it]
53%|ββββββ | 380/711 [36:00<28:33, 5.18s/it]
54%|ββββββ | 381/711 [36:05<28:53, 5.25s/it]
54%|ββββββ | 382/711 [36:11<28:32, 5.21s/it]
54%|ββββββ | 383/711 [36:16<28:38, 5.24s/it]
54%|ββββββ | 384/711 [36:2
0: {'loss': 0.3972, 'grad_norm': 0.8357610935717936, 'learning_rate': 2e-06, 'memory/max_mem_active(gib)': 69.44, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.33}
0: 1<28:17, 5.19s/it]
54%|ββββββ | 385/711 [36:26<28:02, 5.16s/it]
54%|ββββββ | 386/711 [36:31<27:52, 5.15s/it]
54%|ββββββ | 387/711 [36:36<27:46, 5.14s/it]
55%|ββββββ | 388/711 [36:41<27:35, 5.12s/it]
55%|ββββββ | 389/711 [36:47<27:35, 5.14s/it]
55%|ββββββ | 390/711 [36:52<27:38, 5.17s/it]
55%|ββββββ | 390/711 [36:52<27:38, 5.17s/it]
55%|ββββββ | 391/711 [36:57<27:26, 5.14s/it]
55%|ββββββ | 392/711 [37:02<27:35, 5.19s/it]
55%|ββββββ | 393/711 [37:07<27:27, 5.18s/it]
55%|ββββββ | 394/711 [37:12<27:12, 5.15s/it]
56%|ββββββ | 395/711 [37:18<27:39, 5.25s/it]
56%|ββββββ | 396/711 [37:23<27:19, 5.20s/it]
56%|ββββββ | 397/711 [37:28<27:03, 5.17s/it]
56%|ββββββ | 398/711 [37:33<26:52, 5.15s/it]
56%|ββββββ
0: {'loss': 0.3859, 'grad_norm': 0.8058568338786659, 'learning_rate': 2e-06, 'memory/max_mem_active(gib)': 69.44, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.34}
0: {'loss': 0.3898, 'grad_norm': 0.7954384150397931, 'learning_rate': 2e-06, 'memory/max_mem_active(gib)': 69.44, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.35}
0: | 399/711 [37:38<26:46, 5.15s/it]
56%|ββββββ | 400/711 [37:43<26:35, 5.13s/it]
56%|ββββββ | 400/711 [37:43<26:35, 5.13s/it]
56%|ββββββ | 401/711 [37:48<26:27, 5.12s/it]
57%|ββββββ | 402/711 [37:54<26:18, 5.11s/it]
57%|ββββββ | 403/711 [37:59<26:11, 5.10s/it]
57%|ββββββ | 404/711 [38:04<26:10, 5.11s/it]
57%|ββββββ | 405/711 [38:09<26:34, 5.21s/it]
57%|ββββββ | 406/711 [38:14<26:25, 5.20s/it]
57%|ββββββ | 407/711 [38:19<26:11, 5.17s/it]
57%|ββββββ | 408/711 [38:25<26:03, 5.16s/it]
58%|ββββββ | 409/711 [38:30<26:30, 5.27s/it]
58%|ββββββ | 410/711 [38:35<26:14, 5.23s/it]
58%|ββββββ | 410/711 [38:35<26:14, 5.23s/it]
58%|ββββββ | 411/711 [38:41<26:30, 5.30s/it]
58%|βββοΏ½
0: {'loss': 0.3925, 'grad_norm': 0.8145567494437453, 'learning_rate': 2e-06, 'memory/max_mem_active(gib)': 69.44, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.35}
0: οΏ½οΏ½ββ | 412/711 [38:46<26:10, 5.25s/it]
58%|ββββββ | 413/711 [38:51<25:55, 5.22s/it]
58%|ββββββ | 414/711 [38:56<25:40, 5.19s/it]
58%|ββββββ | 415/711 [39:01<25:28, 5.16s/it]
59%|ββββββ | 416/711 [39:07<25:49, 5.25s/it]
59%|ββββββ | 417/711 [39:12<25:31, 5.21s/it]
59%|ββββββ | 418/711 [39:17<25:17, 5.18s/it]
59%|ββββββ | 419/711 [39:22<25:06, 5.16s/it]
59%|ββββββ | 420/711 [39:27<24:59, 5.15s/it]
59%|ββββββ | 420/711 [39:27<24:59, 5.15s/it]
59%|ββββββ | 421/711 [39:32<24:49, 5.14s/it]
59%|ββββββ | 422/711 [39:37<24:44, 5.14s/it]
59%|ββββββ | 423/711 [39:43<24:35, 5.12s/it]
60%|ββββββ | 424/711 [39:48<24:42, 5.17s/it]
60%|ββββββ | 425/711 [39:53<24:34, 5.16s/it]
60%|ββββββ | 426/711 [39:58<24:30, 5.16s/
0: {'loss': 0.3927, 'grad_norm': 0.8237856091804933, 'learning_rate': 2e-06, 'memory/max_mem_active(gib)': 69.44, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.36}
0: it]
60%|ββββββ | 427/711 [40:03<24:40, 5.21s/it]
60%|ββββββ | 428/711 [40:09<24:55, 5.28s/it]
60%|ββββββ | 429/711 [40:14<24:33, 5.23s/it]
60%|ββββββ | 430/711 [40:19<24:23, 5.21s/it]
60%|ββββββ | 430/711 [40:19<24:23, 5.21s/it]
61%|ββββββ | 431/711 [40:24<24:10, 5.18s/it]
61%|ββββββ | 432/711 [40:29<23:56, 5.15s/it]
61%|ββββββ | 433/711 [40:34<23:50, 5.14s/it]
61%|ββββββ | 434/711 [40:40<23:39, 5.12s/it]
61%|ββββββ | 435/711 [40:45<23:32, 5.12s/it]
61%|βββββββ | 436/711 [40:50<24:14, 5.29s/it]
61%|βββββββ | 437/711 [40:56<24:11, 5.30s/it]
62%|βββββββ | 438/711 [41:01<23:49, 5.24s/it]
62%|βββββββ | 439/711 [41:06<23:33, 5.20s/it]
62%|βββββββ | 440/711 [41:11<23:37, 5.23s/it]
0: {'loss': 0.3937, 'grad_norm': 0.8553439901672909, 'learning_rate': 2e-06, 'memory/max_mem_active(gib)': 69.44, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.37}
0: {'loss': 0.3873, 'grad_norm': 0.8286249080798415, 'learning_rate': 2e-06, 'memory/max_mem_active(gib)': 69.44, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.38}
0:
62%|βββββββ | 440/711 [41:11<23:37, 5.23s/it]
62%|βββββββ | 441/711 [41:16<23:23, 5.20s/it]
62%|βββββββ | 442/711 [41:21<23:13, 5.18s/it]
62%|βββββββ | 443/711 [41:27<23:01, 5.16s/it]
62%|βββββββ | 444/711 [41:32<22:57, 5.16s/it]
63%|βββββββ | 445/711 [41:37<23:14, 5.24s/it]
63%|βββββββ | 446/711 [41:42<22:58, 5.20s/it]
63%|βββββββ | 447/711 [41:47<22:45, 5.17s/it]
63%|βββββββ | 448/711 [41:52<22:34, 5.15s/it]
63%|βββββββ | 449/711 [41:58<22:43, 5.20s/it]
63%|βββββββ | 450/711 [42:03<22:32, 5.18s/it]
63%|βββββββ | 450/711 [42:03<22:32, 5.18s/it]
63%|βββββββ | 451/711 [42:08<22:20, 5.16s/it]
64%|βββββββ | 452/711 [42:13<22:14, 5.15s/it]
64%|βββββββ | 453/711 [42:18<22:09, 5
0: {'loss': 0.384, 'grad_norm': 0.8623716385758442, 'learning_rate': 2e-06, 'memory/max_mem_active(gib)': 69.44, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.39}
0: .15s/it]
64%|βββββββ | 454/711 [42:23<22:03, 5.15s/it]
64%|βββββββ | 455/711 [42:29<21:56, 5.14s/it]
64%|βββββββ | 456/711 [42:34<21:51, 5.14s/it]
64%|βββββββ | 457/711 [42:39<21:44, 5.14s/it]
64%|βββββββ | 458/711 [42:44<21:40, 5.14s/it]
65%|βββββββ | 459/711 [42:49<21:39, 5.16s/it]
65%|βββββββ | 460/711 [42:54<21:46, 5.21s/it]
65%|βββββββ | 460/711 [42:54<21:46, 5.21s/it]
65%|βββββββ | 461/711 [43:00<21:38, 5.19s/it]
65%|βββββββ | 462/711 [43:05<21:30, 5.18s/it]
65%|βββββββ | 463/711 [43:10<21:25, 5.18s/it]
65%|βββββββ | 464/711 [43:15<21:17, 5.17s/it]
65%|βββββββ | 465/711 [43:20<21:05, 5.15s/it]
66%|βββββββ | 466/711 [43:25<20:58, 5.14s/it]
66%|βββββββ | 467/711 [43:30<20:53, 5.14s/it]
66%
0: {'loss': 0.3893, 'grad_norm': 0.7980262942281969, 'learning_rate': 2e-06, 'memory/max_mem_active(gib)': 69.44, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.4}
0: {'loss': 0.3928, 'grad_norm': 0.9024656134697462, 'learning_rate': 2e-06, 'memory/max_mem_active(gib)': 69.44, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.4}
0: |βββββββ | 468/711 [43:36<20:50, 5.14s/it]
66%|βββββββ | 469/711 [43:41<21:10, 5.25s/it]
66%|βββββββ | 470/711 [43:46<20:53, 5.20s/it]
66%|βββββββ | 470/711 [43:46<20:53, 5.20s/it]
66%|βββββββ | 471/711 [43:51<20:45, 5.19s/it]
66%|βββββββ | 472/711 [43:57<20:40, 5.19s/it]
67%|βββββββ | 473/711 [44:02<20:28, 5.16s/it]
67%|βββββββ | 474/711 [44:07<20:23, 5.16s/it]
67%|βββββββ | 475/711 [44:12<20:12, 5.14s/it]
67%|βββββββ | 476/711 [44:18<20:43, 5.29s/it]
67%|βββββββ | 477/711 [44:23<20:23, 5.23s/it]
67%|βββββββ | 478/711 [44:28<20:24, 5.26s/it]
67%|βββββββ | 479/711 [44:33<20:10, 5.22s/it]
68%|βββββββ | 480/711 [44:38<19:59, 5.19s/it]
68%|βββββββ |
0: {'loss': 0.3747, 'grad_norm': 1.4532167164219425, 'learning_rate': 2e-06, 'memory/max_mem_active(gib)': 69.44, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.41}
0: 480/711 [44:38<19:59, 5.19s/it]
68%|βββββββ | 481/711 [44:44<20:13, 5.28s/it]
68%|βββββββ | 482/711 [44:49<20:00, 5.24s/it]
68%|βββββββ | 483/711 [44:54<19:48, 5.21s/it]
68%|βββββββ | 484/711 [44:59<19:39, 5.20s/it]
68%|βββββββ | 485/711 [45:04<19:33, 5.19s/it]
68%|βββββββ | 486/711 [45:10<19:26, 5.18s/it]
68%|βββββββ | 487/711 [45:15<19:19, 5.18s/it]
69%|βββββββ | 488/711 [45:20<19:09, 5.15s/it]
69%|βββββββ | 489/711 [45:25<19:24, 5.25s/it]
69%|βββββββ | 490/711 [45:30<19:09, 5.20s/it]
69%|βββββββ | 490/711 [45:30<19:09, 5.20s/it]
69%|βββββββ | 491/711 [45:36<19:16, 5.26s/it]
69%|βββββββ | 492/711 [45:41<19:00, 5.21s/it]
69%|βββββββ | 493/711 [45:46<18:47, 5.17s/it]
69%|βββββββ | 494/711 [45:
0: {'loss': 0.3797, 'grad_norm': 0.8355553409451639, 'learning_rate': 2e-06, 'memory/max_mem_active(gib)': 69.44, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.42}
0: 51<19:02, 5.27s/it]
70%|βββββββ | 495/711 [45:56<18:45, 5.21s/it]
70%|βββββββ | 496/711 [46:02<18:34, 5.19s/it]
70%|βββββββ | 497/711 [46:07<18:38, 5.22s/it]
70%|βββββββ | 498/711 [46:12<18:25, 5.19s/it]
70%|βββββββ | 499/711 [46:18<18:55, 5.35s/it]
70%|βββββββ | 500/711 [46:23<18:34, 5.28s/it]
70%|βββββββ | 500/711 [46:23<18:34, 5.28s/it]
70%|βββββββ | 501/711 [46:28<18:22, 5.25s/it]
71%|βββββββ | 502/711 [46:33<18:12, 5.23s/it]
71%|βββββββ | 503/711 [46:38<18:04, 5.21s/it]
71%|βββββββ | 504/711 [46:44<17:53, 5.19s/it]
71%|βββββββ | 505/711 [46:49<17:43, 5.16s/it]
71%|βββββββ | 506/711 [46:54<17:36, 5.16s/it]
71%|ββββββββ | 507/711 [46:59<17:29, 5.14s/it]
71%|ββββββββ | 508/711 [47:04<17:21,
0: {'loss': 0.3917, 'grad_norm': 0.8425621928447311, 'learning_rate': 2e-06, 'memory/max_mem_active(gib)': 69.44, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.43}
0: {'loss': 0.3825, 'grad_norm': 0.7816311224212293, 'learning_rate': 1.9929032311830302e-06, 'memory/max_mem_active(gib)': 69.44, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.44}
0: 5.13s/it]
72%|ββββββββ | 509/711 [47:09<17:16, 5.13s/it]
72%|ββββββββ | 510/711 [47:14<17:09, 5.12s/it]
72%|ββββββββ | 510/711 [47:14<17:09, 5.12s/it]
72%|ββββββββ | 511/711 [47:20<17:21, 5.21s/it]
72%|ββββββββ | 512/711 [47:25<17:12, 5.19s/it]
72%|ββββββββ | 513/711 [47:30<17:00, 5.16s/it]
72%|ββββββββ | 514/711 [47:35<16:51, 5.14s/it]
72%|ββββββββ | 515/711 [47:40<16:45, 5.13s/it]
73%|ββββββββ | 516/711 [47:45<16:40, 5.13s/it]
73%|ββββββββ | 517/711 [47:50<16:32, 5.12s/it]
73%|ββββββββ | 518/711 [47:55<16:30, 5.13s/it]
73%|ββββββββ | 519/711 [48:01<16:25, 5.13s/it]
73%|ββββββββ | 520/711 [48:06<16:42, 5.25s/it]
73%|ββββββββ | 520/711 [48:06<16:4
0: {'loss': 0.3819, 'grad_norm': 0.8516269037345293, 'learning_rate': 1.9642643171092486e-06, 'memory/max_mem_active(gib)': 69.44, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.45}
0: 2, 5.25s/it]
73%|ββββββββ | 521/711 [48:11<16:30, 5.21s/it]
73%|ββββββββ | 522/711 [48:16<16:18, 5.18s/it]
74%|ββββββββ | 523/711 [48:22<16:20, 5.22s/it]
74%|ββββββββ | 524/711 [48:27<16:36, 5.33s/it]
74%|ββββββββ | 525/711 [48:32<16:20, 5.27s/it]
74%|ββββββββ | 526/711 [48:37<16:07, 5.23s/it]
74%|ββββββββ | 527/711 [48:43<15:53, 5.18s/it]
74%|ββββββββ | 528/711 [48:48<15:54, 5.22s/it]
74%|ββββββββ | 529/711 [48:53<15:42, 5.18s/it]
75%|ββββββββ | 530/711 [48:58<15:38, 5.18s/it]
75%|ββββββββ | 530/711 [48:58<15:38, 5.18s/it]
75%|ββββββββ | 531/711 [49:03<15:27, 5.15s/it]
75%|ββββββββ | 532/711 [49:08<15:19, 5.14s/it]
75%|ββββββββ | 533/711 [49:13<15:11, 5.12s/it]
75%|ββββββββ | 53
0: {'loss': 0.3918, 'grad_norm': 0.9451621145813273, 'learning_rate': 1.9143443472194176e-06, 'memory/max_mem_active(gib)': 69.44, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.46}
0: 4/711 [49:18<15:05, 5.12s/it]
75%|ββββββββ | 535/711 [49:24<14:58, 5.11s/it]
75%|ββββββββ | 536/711 [49:29<15:04, 5.17s/it]
76%|ββββββββ | 537/711 [49:34<14:59, 5.17s/it]
76%|ββββββββ | 538/711 [49:39<14:48, 5.14s/it]
76%|ββββββββ | 539/711 [49:44<14:46, 5.16s/it]
76%|ββββββββ | 540/711 [49:49<14:41, 5.15s/it]
76%|ββββββββ | 540/711 [49:49<14:41, 5.15s/it]
76%|ββββββββ | 541/711 [49:55<14:33, 5.14s/it]
76%|ββββββββ | 542/711 [50:00<14:26, 5.13s/it]
76%|ββββββββ | 543/711 [50:05<14:23, 5.14s/it]
77%|ββββββββ | 544/711 [50:10<14:17, 5.13s/it]
77%|ββββββββ | 545/711 [50:15<14:10, 5.12s/it]
77%|ββββββββ | 546/711 [50:20<14:04, 5.12s/it]
77%|ββββββββ | 547/711 [50:25<13:59, 5.12s/it]
77%|ββββοΏ½
0: {'loss': 0.3907, 'grad_norm': 0.8481507125427856, 'learning_rate': 1.8443725168471053e-06, 'memory/max_mem_active(gib)': 69.44, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.46}
0: {'loss': 0.3803, 'grad_norm': 0.8683953024369212, 'learning_rate': 1.7560717646792703e-06, 'memory/max_mem_active(gib)': 69.44, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.47}
0: οΏ½οΏ½βββ | 548/711 [50:30<13:52, 5.11s/it]
77%|ββββββββ | 549/711 [50:35<13:47, 5.11s/it]
77%|ββββββββ | 550/711 [50:41<13:42, 5.11s/it]
77%|ββββββββ | 550/711 [50:41<13:42, 5.11s/it]
77%|ββββββββ | 551/711 [50:46<13:40, 5.13s/it]
78%|ββββββββ | 552/711 [50:51<13:36, 5.13s/it]
78%|ββββββββ | 553/711 [50:56<13:29, 5.12s/it]
78%|ββββββββ | 554/711 [51:01<13:24, 5.12s/it]
78%|ββββββββ | 555/711 [51:06<13:21, 5.14s/it]
78%|ββββββββ | 556/711 [51:11<13:14, 5.12s/it]
78%|ββββββββ | 557/711 [51:17<13:25, 5.23s/it]
78%|ββββββββ | 558/711 [51:22<13:32, 5.31s/it]
79%|ββββββββ | 559/711 [51:27<13:18, 5.25s/it]
79%|ββββββββ | 560/711 [51:33<13:06, 5.21s/it]
79%|βββοΏ½
0: {'loss': 0.3904, 'grad_norm': 0.8636181194234771, 'learning_rate': 1.6516163482876789e-06, 'memory/max_mem_active(gib)': 69.44, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.48}
0: οΏ½ββββ | 560/711 [51:33<13:06, 5.21s/it]
79%|ββββββββ | 561/711 [51:38<12:58, 5.19s/it]
79%|ββββββββ | 562/711 [51:43<13:13, 5.33s/it]
79%|ββββββββ | 563/711 [51:49<13:11, 5.35s/it]
79%|ββββββββ | 564/711 [51:54<12:58, 5.29s/it]
79%|ββββββββ | 565/711 [51:59<12:47, 5.26s/it]
80%|ββββββββ | 566/711 [52:04<12:34, 5.21s/it]
80%|ββββββββ | 567/711 [52:10<12:40, 5.28s/it]
80%|ββββββββ | 568/711 [52:15<12:28, 5.23s/it]
80%|ββββββββ | 569/711 [52:20<12:27, 5.26s/it]
80%|ββββββββ | 570/711 [52:25<12:14, 5.21s/it]
80%|ββββββββ | 570/711 [52:25<12:14, 5.21s/it]
80%|ββββββββ | 571/711 [52:31<12:14, 5.24s/it]
80%|ββββββββ | 572/711 [52:36<12:04, 5.21s/it]
81%|ββββββββ | 573/711 [52:41<12:02, 5.24s/it]
0: {'loss': 0.3828, 'grad_norm': 0.8879170447340103, 'learning_rate': 1.5335783066915436e-06, 'memory/max_mem_active(gib)': 69.44, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 75.77, 'epoch': 0.49}
0:
81%|ββββββββ | 574/711 [52:46<11:53, 5.21s/it]
81%|ββββββββ | 575/711 [52:51<11:44, 5.18s/it]
81%|ββββββββ | 576/711 [52:56<11:38, 5.17s/it]
81%|ββββββββ | 577/711 [53:02<11:46, 5.27s/it]
81%|βββββββββ | 578/711 [53:07<11:49, 5.33s/it]
81%|βββββββββ | 579/711 [53:12<11:34, 5.26s/it]
82%|βββββββββ | 580/711 [53:18<11:25, 5.23s/it]
82%|βββββββββ | 580/711 [53:18<11:25, 5.23s/it]
82%|βββββββββ | 581/711 [53:23<11:15, 5.19s/it]
82%|βββββββββ | 582/711 [53:28<11:06, 5.16s/it]
82%|βββββββββ | 583/711 [53:33<10:59, 5.15s/it]
82%|βββββββββ | 584/711 [53:38<10:52, 5.14s/it]
82%|βββββββββ | 585/711 [53:43<10:46, 5.13s/it]
82%|βββββββββ | 586/711 [53:48<10:42, 5.14s/it]
83%|βββββββοΏ½
0: {'loss': 0.3763, 'grad_norm': 0.829865464468096, 'learning_rate': 1.4048641282207622e-06, 'memory/max_mem_active(gib)': 69.44, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 76.53, 'epoch': 0.5}
0: οΏ½β | 587/711 [53:54<11:03, 5.35s/it]
83%|βββββββββ | 588/711 [53:59<10:55, 5.33s/it]
83%|βββββββββ | 589/711 [54:05<10:40, 5.25s/it]
83%|βββββββββ | 590/711 [54:10<10:43, 5.32s/it]
83%|βββββββββ | 590/711 [54:10<10:43, 5.32s/it]
83%|βββββββββ | 591/711 [54:15<10:32, 5.27s/it]
83%|βββββββββ | 592/711 [54:20<10:23, 5.24s/it]
83%|βββββββββ | 593/711 [54:25<10:14, 5.21s/it]
84%|βββββββββ | 594/711 [54:31<10:07, 5.19s/it]
84%|βββββββββ | 595/711 [54:36<09:59, 5.17s/it]
84%|βββββββββ | 596/711 [54:41<09:51, 5.14s/it]
84%|βββββββββ | 597/711 [54:46<09:53, 5.21s/it]
84%|βββββββββ | 598/711 [54:51<09:45, 5.18s/it]
84%|βββββββββ | 599/711 [54:57<10:07, 5.42s/it]
84%|βββββββββ | 600/711 [55:02
0: {'loss': 0.3895, 'grad_norm': 1.0461353857982227, 'learning_rate': 1.2686431831271522e-06, 'memory/max_mem_active(gib)': 69.44, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 76.53, 'epoch': 0.51}
0: {'loss': 0.3726, 'grad_norm': 0.8291006806562558, 'learning_rate': 1.1282696831703153e-06, 'memory/max_mem_active(gib)': 69.44, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 76.53, 'epoch': 0.51}
0: <09:53, 5.35s/it]
84%|βββββββββ | 600/711 [55:02<09:53, 5.35s/it]
85%|βββββββββ | 601/711 [55:08<09:48, 5.35s/it]
85%|βββββββββ | 602/711 [55:13<09:35, 5.28s/it]
85%|βββββββββ | 603/711 [55:18<09:24, 5.23s/it]
85%|βββββββββ | 604/711 [55:23<09:22, 5.26s/it]
85%|βββββββββ | 605/711 [55:28<09:12, 5.22s/it]
85%|βββββββββ | 606/711 [55:34<09:27, 5.41s/it]
85%|βββββββββ | 607/711 [55:40<09:29, 5.47s/it]
86%|βββββββββ | 608/711 [55:45<09:17, 5.41s/it]
86%|βββββββββ | 609/711 [55:50<09:03, 5.32s/it]
86%|βββββββββ | 610/711 [55:56<08:56, 5.31s/it]
86%|βββββββββ | 610/711 [55:56<08:56, 5.31s/it]
86%|βββββββββ | 611/711 [56:01<08:45, 5.25s/it]
86%|ββββοΏ½
0: {'loss': 0.3749, 'grad_norm': 0.8273940149239204, 'learning_rate': 9.87200089792126e-07, 'memory/max_mem_active(gib)': 69.44, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 76.53, 'epoch': 0.52}
0: οΏ½ββββ | 612/711 [56:06<08:36, 5.22s/it]
86%|βββββββββ | 613/711 [56:11<08:34, 5.24s/it]
86%|βββββββββ | 614/711 [56:16<08:25, 5.22s/it]
86%|βββββββββ | 615/711 [56:21<08:17, 5.19s/it]
87%|βββββββββ | 616/711 [56:28<08:41, 5.48s/it]
87%|βββββββββ | 617/711 [56:33<08:24, 5.37s/it]
87%|βββββββββ | 618/711 [56:38<08:23, 5.41s/it]
87%|βββββββββ | 619/711 [56:43<08:09, 5.33s/it]
87%|βββββββββ | 620/711 [56:49<07:59, 5.27s/it]
87%|βββββββββ | 620/711 [56:49<07:59, 5.27s/it]
87%|βββββββββ | 621/711 [56:54<07:51, 5.24s/it]
87%|βββββββββ | 622/711 [56:59<07:43, 5.21s/it]
88%|βββββββββ | 623/711 [57:04<07:44, 5.28s/it]
88%|βββββββββ | 624/711 [57:09<07:35, 5.23s/it]
88%|βββββββββ | 625/7
0: {'loss': 0.3717, 'grad_norm': 0.7609373973543032, 'learning_rate': 8.489080045646937e-07, 'memory/max_mem_active(gib)': 69.44, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 76.53, 'epoch': 0.53}
0: 11 [57:14<07:26, 5.19s/it]
88%|βββββββββ | 626/711 [57:20<07:19, 5.17s/it]
88%|βββββββββ | 627/711 [57:25<07:12, 5.14s/it]
88%|βββββββββ | 628/711 [57:30<07:07, 5.15s/it]
88%|βββββββββ | 629/711 [57:35<07:03, 5.16s/it]
89%|βββββββββ | 630/711 [57:41<07:25, 5.49s/it]
89%|βββββββββ | 630/711 [57:41<07:25, 5.49s/it]
89%|βββββββββ | 631/711 [57:47<07:13, 5.42s/it]
89%|βββββββββ | 632/711 [57:52<07:01, 5.33s/it]
89%|βββββββββ | 633/711 [57:57<06:51, 5.28s/it]
89%|βββββββββ | 634/711 [58:02<06:42, 5.23s/it]
89%|βββββββββ | 635/711 [58:07<06:35, 5.21s/it]
89%|βββββββββ | 636/711 [58:13<06:36, 5.28s/it]
90%|βββββββββ | 637/711 [58:18<06:26, 5.23s/it]
90%|βββββββββ | 638/711 [58:23<06:19, 5.2
0: {'loss': 0.3746, 'grad_norm': 0.8664669621801867, 'learning_rate': 7.167986375914345e-07, 'memory/max_mem_active(gib)': 69.44, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 76.53, 'epoch': 0.54}
0: {'loss': 0.3774, 'grad_norm': 0.7890688699500655, 'learning_rate': 5.941249599330827e-07, 'memory/max_mem_active(gib)': 69.44, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 76.53, 'epoch': 0.55}
0: 0s/it]
90%|βββββββββ | 639/711 [58:28<06:19, 5.28s/it]
90%|βββββββββ | 640/711 [58:33<06:11, 5.24s/it]
90%|βββββββββ | 640/711 [58:33<06:11, 5.24s/it]
90%|βββββββββ | 641/711 [58:39<06:10, 5.30s/it]
90%|βββββββββ | 642/711 [58:44<06:02, 5.25s/it]
90%|βββββββββ | 643/711 [58:49<05:53, 5.20s/it]
91%|βββββββββ | 644/711 [58:54<05:46, 5.17s/it]
91%|βββββββββ | 645/711 [59:00<05:46, 5.26s/it]
91%|βββββββββ | 646/711 [59:05<05:38, 5.21s/it]
91%|βββββββββ | 647/711 [59:10<05:31, 5.18s/it]
91%|βββββββββ | 648/711 [59:15<05:25, 5.17s/it]
91%|ββββββββββ| 649/711 [59:20<05:18, 5.14s/it]
91%|ββββββββββ| 650/711 [59:25<05:18, 5.23s/it]
91%|βββββββοΏ½
0: {'loss': 0.3821, 'grad_norm': 0.8161369753902079, 'learning_rate': 4.839076046641801e-07, 'memory/max_mem_active(gib)': 69.44, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 76.53, 'epoch': 0.56}
0: οΏ½οΏ½ββ| 650/711 [59:25<05:18, 5.23s/it]
92%|ββββββββββ| 651/711 [59:31<05:11, 5.20s/it]
92%|ββββββββββ| 652/711 [59:36<05:04, 5.16s/it]
92%|ββββββββββ| 653/711 [59:41<05:07, 5.31s/it]
92%|ββββββββββ| 654/711 [59:46<04:58, 5.24s/it]
92%|ββββββββββ| 655/711 [59:52<04:52, 5.22s/it]
92%|ββββββββββ| 656/711 [59:57<04:51, 5.30s/it]
92%|ββββββββββ| 657/711 [1:00:02<04:43, 5.26s/it]
93%|ββββββββββ| 658/711 [1:00:07<04:36, 5.22s/it]
93%|ββββββββββ| 659/711 [1:00:13<04:32, 5.23s/it]
93%|ββββββββββ| 660/711 [1:00:18<04:24, 5.19s/it]
93%|ββββββββββ| 660/711 [1:00:18<04:24, 5.19s/it]
93%|ββββββββββ| 661/711 [1:00:23<04:23, 5.28s/it]
93%|ββββββββββ| 662/711 [1:00:28<04:16, 5.23s/it]
93%
0: {'loss': 0.3655, 'grad_norm': 0.8247018856496126, 'learning_rate': 3.888604888618786e-07, 'memory/max_mem_active(gib)': 69.44, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 76.53, 'epoch': 0.56}
0: |ββββββββββ| 663/711 [1:00:33<04:09, 5.20s/it]
93%|ββββββββββ| 664/711 [1:00:39<04:02, 5.17s/it]
94%|ββββββββββ| 665/711 [1:00:44<03:57, 5.16s/it]
94%|ββββββββββ| 666/711 [1:00:49<03:54, 5.21s/it]
94%|ββββββββββ| 667/711 [1:00:54<03:48, 5.19s/it]
94%|ββββββββββ| 668/711 [1:00:59<03:41, 5.16s/it]
94%|ββββββββββ| 669/711 [1:01:04<03:35, 5.14s/it]
94%|ββββββββββ| 670/711 [1:01:10<03:33, 5.22s/it]
94%|ββββββββββ| 670/711 [1:01:10<03:33, 5.22s/it]
94%|ββββββββββ| 671/711 [1:01:15<03:27, 5.18s/it]
95%|ββββββββββ| 672/711 [1:01:20<03:23, 5.22s/it]
95%|ββββββββββ| 673/711 [1:01:25<03:17, 5.20s/it]
95%|ββββββββββ| 674/711 [1:01:30<03:10, 5.16s/it]
95%|ββββββββββ| 67
0: {'loss': 0.3832, 'grad_norm': 0.7788264476641573, 'learning_rate': 3.1132398796052294e-07, 'memory/max_mem_active(gib)': 69.55, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 76.53, 'epoch': 0.57}
0: 5/711 [1:01:36<03:06, 5.19s/it]
95%|ββββββββββ| 676/711 [1:01:42<03:13, 5.53s/it]
95%|ββββββββββ| 677/711 [1:01:48<03:11, 5.63s/it]
95%|ββββββββββ| 678/711 [1:01:53<03:02, 5.52s/it]
95%|ββββββββββ| 679/711 [1:01:58<02:52, 5.38s/it]
96%|ββββββββββ| 680/711 [1:02:03<02:44, 5.29s/it]
96%|ββββββββββ| 680/711 [1:02:03<02:44, 5.29s/it]
96%|ββββββββββ| 681/711 [1:02:08<02:37, 5.25s/it]
96%|ββββββββββ| 682/711 [1:02:14<02:33, 5.31s/it]
96%|ββββββββββ| 683/711 [1:02:19<02:27, 5.25s/it]
96%|ββββββββββ| 684/711 [1:02:24<02:20, 5.21s/it]
96%|ββββββββββ| 685/711 [1:02:29<02:14, 5.18s/it]
96%|ββββββββββ| 686/711 [1:02:34<02:09, 5.17s/it]
97%|ββββββββββ| 687/711 [1:02:39<02:03, 5.17s/it]
9
0: {'loss': 0.3818, 'grad_norm': 0.7875994058840892, 'learning_rate': 2.532073079411971e-07, 'memory/max_mem_active(gib)': 69.55, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 76.53, 'epoch': 0.58}
0: 7%|ββββββββββ| 688/711 [1:02:45<01:58, 5.15s/it]
97%|ββββββββββ| 689/711 [1:02:50<01:53, 5.15s/it]
97%|ββββββββββ| 690/711 [1:02:55<01:47, 5.14s/it]
97%|ββββββββββ| 690/711 [1:02:55<01:47, 5.14s/it]
97%|ββββββββββ| 691/711 [1:03:00<01:43, 5.19s/it]
97%|ββββββββββ| 692/711 [1:03:05<01:37, 5.16s/it]
97%|ββββββββββ| 693/711 [1:03:10<01:32, 5.14s/it]
98%|ββββββββββ| 694/711 [1:03:15<01:27, 5.13s/it]
98%|ββββββββββ| 695/711 [1:03:21<01:22, 5.13s/it]
98%|ββββββββββ| 696/711 [1:03:26<01:17, 5.14s/it]
98%|ββββββββββ| 697/711 [1:03:31<01:11, 5.14s/it]
98%|ββββββββββ| 698/711 [1:03:36<01:06, 5.14s/it]
98%|ββββββββββ| 699/711 [1:03:41<01:02, 5.17s/it]
98%|ββββββββββ|
0: {'loss': 0.3763, 'grad_norm': 0.7322258611860605, 'learning_rate': 2.1594147434418026e-07, 'memory/max_mem_active(gib)': 69.55, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 76.53, 'epoch': 0.59}
0: {'loss': 0.3734, 'grad_norm': 0.7653492019720352, 'learning_rate': 2.0044409567084156e-07, 'memory/max_mem_active(gib)': 69.55, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 76.53, 'epoch': 0.6}
0: 700/711 [1:03:47<00:57, 5.24s/it]
98%|ββββββββββ| 700/711 [1:03:47<00:57, 5.24s/it]
99%|ββββββββββ| 701/711 [1:03:52<00:52, 5.26s/it]
99%|ββββββββββ| 702/711 [1:03:57<00:47, 5.23s/it]
99%|ββββββββββ| 703/711 [1:04:02<00:41, 5.20s/it]
99%|ββββββββββ| 704/711 [1:04:07<00:36, 5.20s/it]
99%|ββββββββββ| 705/711 [1:04:13<00:31, 5.30s/it]
99%|ββββββββββ| 706/711 [1:04:18<00:26, 5.24s/it]
99%|ββββββββββ| 707/711 [1:04:23<00:21, 5.27s/it]
100%|ββββββββββ| 708/711 [1:04:28<00:15, 5.21s/it]
100%|ββββββββββ| 709/711 [1:04:34<00:10, 5.19s/it]
100%|ββββββββββ| 710/711 [1:04:39<00:05, 5.28s/it]
100%|ββββββββββ| 710/711 [1:04:39<00:05, 5.28s/it]
100%|ββββοΏ½
0: [2025-11-24 01:16:53,191] [INFO] [axolotl.core.trainers.base._save:613] [PID:3081979] [RANK:0] Saving model checkpoint to /lustre/fswork/projects/rech/dgo/udv55np/ift/Nemotron-Super-49B-v1_5/gemma-3-12b/0/checkpoint-711[39m
0: [2025-11-24 01:17:11,725] [INFO] [axolotl.core.trainers.base._save:662] [PID:3081979] [RANK:0] Saving Trainer.data_collator.tokenizer by default as Trainer.processing_class is `None`[39m
0: {'train_runtime': 3910.4069, 'train_samples_per_second': 2.909, 'train_steps_per_second': 0.182, 'train_loss': 0.4125736778295493, 'memory/max_mem_active(gib)': 69.55, 'memory/max_mem_allocated(gib)': 67.66, 'memory/device_mem_reserved(gib)': 76.53, 'epoch': 0.6}
0: οΏ½βββββ| 711/711 [1:04:44<00:00, 5.22s/it]
100%|ββββββββββ| 711/711 [1:05:10<00:00, 5.22s/it]
100%|ββββββββββ| 711/711 [1:05:10<00:00, 5.50s/it]
0: [2025-11-24 01:17:21,056] [INFO] [axolotl.train.save_trained_model:228] [PID:3081979] [RANK:0] Training completed! Saving trained model to /lustre/fswork/projects/rech/dgo/udv55np/ift/Nemotron-Super-49B-v1_5/gemma-3-12b/0.[39m
0: [2025-11-24 01:17:26,694] [INFO] [axolotl.core.trainers.base._save:613] [PID:3081979] [RANK:0] Saving model checkpoint to /lustre/fswork/projects/rech/dgo/udv55np/ift/Nemotron-Super-49B-v1_5/gemma-3-12b/0[39m
0: [2025-11-24 01:17:44,493] [INFO] [axolotl.core.trainers.base._save:662] [PID:3081979] [RANK:0] Saving Trainer.data_collator.tokenizer by default as Trainer.processing_class is `None`[39m
0: [2025-11-24 01:17:44,817] [INFO] [axolotl.train.save_trained_model:350] [PID:3081979] [RANK:0] Model successfully saved to /lustre/fswork/projects/rech/dgo/udv55np/ift/Nemotron-Super-49B-v1_5/gemma-3-12b/0[39m
|