Download checkpoint-21/trainer_state.json from leducanh1203/BioMistral7B_AutoTrain: direct link, hf CLI and curl.
- Browser
- Download file 3.71 kB
-
https://huggingface.co/leducanh1203/BioMistral7B_AutoTrain/resolve/main/checkpoint-21/trainer_state.json
- Command line
-
hf download hf://leducanh1203/BioMistral7B_AutoTrain/checkpoint-21/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/leducanh1203/BioMistral7B_AutoTrain/resolve/main/checkpoint-21/trainer_state.json
3.71 kB
| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 21, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 2.9258434772491455, | |
| "learning_rate": 9.999999999999999e-06, | |
| "loss": 2.1748, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 2.7063839435577393, | |
| "learning_rate": 1.9999999999999998e-05, | |
| "loss": 1.9763, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 2.6058349609375, | |
| "learning_rate": 3e-05, | |
| "loss": 2.0765, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": 2.4401776790618896, | |
| "learning_rate": 2.8333333333333332e-05, | |
| "loss": 1.8445, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 2.4424264430999756, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 1.8471, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 2.358938217163086, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.738, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 3.549773931503296, | |
| "learning_rate": 2.3333333333333336e-05, | |
| "loss": 1.5309, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "grad_norm": 2.1476035118103027, | |
| "learning_rate": 2.1666666666666667e-05, | |
| "loss": 1.7547, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "grad_norm": 2.203382968902588, | |
| "learning_rate": 1.9999999999999998e-05, | |
| "loss": 1.5624, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "grad_norm": 2.297717332839966, | |
| "learning_rate": 1.8333333333333336e-05, | |
| "loss": 1.4664, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "grad_norm": 2.1212267875671387, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 1.303, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "grad_norm": 2.2762389183044434, | |
| "learning_rate": 1.5e-05, | |
| "loss": 1.592, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "grad_norm": 2.2024176120758057, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 1.4487, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 2.8860790729522705, | |
| "learning_rate": 1.1666666666666668e-05, | |
| "loss": 1.4676, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "grad_norm": 2.149879217147827, | |
| "learning_rate": 9.999999999999999e-06, | |
| "loss": 1.254, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "grad_norm": 2.1534736156463623, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 1.1987, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "grad_norm": 2.24772572517395, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 1.3075, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "grad_norm": 2.0693881511688232, | |
| "learning_rate": 4.9999999999999996e-06, | |
| "loss": 1.1817, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "grad_norm": 2.126629114151001, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 1.3248, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "grad_norm": 2.1558408737182617, | |
| "learning_rate": 1.6666666666666667e-06, | |
| "loss": 1.4871, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 2.790468454360962, | |
| "learning_rate": 0.0, | |
| "loss": 1.4053, | |
| "step": 21 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 21, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 1713878153035776.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |