Download checkpoint-2205/trainer_state.json from visolex/bartpho-hsd-span: direct link, hf CLI and curl.
- Browser
- Download file 4.79 kB
-
https://huggingface.co/visolex/bartpho-hsd-span/resolve/main/checkpoint-2205/trainer_state.json
- Command line
-
hf download hf://visolex/bartpho-hsd-span/checkpoint-2205/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/visolex/bartpho-hsd-span/resolve/main/checkpoint-2205/trainer_state.json
4.79 kB
| { | |
| "best_global_step": 2205, | |
| "best_metric": 0.8215573432280139, | |
| "best_model_checkpoint": "outputs/runs/bartpho/checkpoint-2205", | |
| "epoch": 7.0, | |
| "eval_steps": 500, | |
| "global_step": 2205, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.9968253968253968, | |
| "grad_norm": 3.099806785583496, | |
| "learning_rate": 4.999432333543028e-06, | |
| "loss": 0.5217, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5575607044846632, | |
| "eval_f1": 0.5515728094561057, | |
| "eval_loss": 1.320883870124817, | |
| "eval_precision": 0.6356662607616385, | |
| "eval_recall": 0.613408724428726, | |
| "eval_runtime": 5.7255, | |
| "eval_samples_per_second": 227.228, | |
| "eval_steps_per_second": 7.161, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 1.9936507936507937, | |
| "grad_norm": 1.9128671884536743, | |
| "learning_rate": 4.996525669931999e-06, | |
| "loss": 0.3798, | |
| "step": 628 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7966790565185674, | |
| "eval_f1": 0.7727173370771165, | |
| "eval_loss": 0.47158923745155334, | |
| "eval_precision": 0.8049817216732861, | |
| "eval_recall": 0.7621576186595547, | |
| "eval_runtime": 5.7417, | |
| "eval_samples_per_second": 226.586, | |
| "eval_steps_per_second": 7.141, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 2.9904761904761905, | |
| "grad_norm": 2.9943490028381348, | |
| "learning_rate": 4.991155236893945e-06, | |
| "loss": 0.3319, | |
| "step": 942 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.821516656824261, | |
| "eval_f1": 0.8026111791478101, | |
| "eval_loss": 0.4115768074989319, | |
| "eval_precision": 0.8293916217775468, | |
| "eval_recall": 0.7918328303886295, | |
| "eval_runtime": 5.7518, | |
| "eval_samples_per_second": 226.191, | |
| "eval_steps_per_second": 7.128, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 3.9873015873015873, | |
| "grad_norm": 3.69238543510437, | |
| "learning_rate": 4.983326334397891e-06, | |
| "loss": 0.3164, | |
| "step": 1256 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8272310417896968, | |
| "eval_f1": 0.8089149421105615, | |
| "eval_loss": 0.39312005043029785, | |
| "eval_precision": 0.8362205682758683, | |
| "eval_recall": 0.7978148005325525, | |
| "eval_runtime": 5.7808, | |
| "eval_samples_per_second": 225.054, | |
| "eval_steps_per_second": 7.092, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 4.984126984126984, | |
| "grad_norm": 20.970905303955078, | |
| "learning_rate": 4.97304668862541e-06, | |
| "loss": 1.1543, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.6326814186959392, | |
| "eval_f1": 0.43821110851496803, | |
| "eval_loss": 0.6246408224105835, | |
| "eval_precision": 0.8027087477481067, | |
| "eval_recall": 0.5281280484111368, | |
| "eval_runtime": 5.7608, | |
| "eval_samples_per_second": 225.837, | |
| "eval_steps_per_second": 7.117, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 5.980952380952381, | |
| "grad_norm": 7.541131019592285, | |
| "learning_rate": 4.9603264443458e-06, | |
| "loss": 0.7372, | |
| "step": 1884 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.8111994997742036, | |
| "eval_f1": 0.7970220873127174, | |
| "eval_loss": 0.38770145177841187, | |
| "eval_precision": 0.8059464877876692, | |
| "eval_recall": 0.7915295487509866, | |
| "eval_runtime": 5.7788, | |
| "eval_samples_per_second": 225.131, | |
| "eval_steps_per_second": 7.095, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 6.977777777777778, | |
| "grad_norm": 3.5747125148773193, | |
| "learning_rate": 4.945178154904432e-06, | |
| "loss": 0.3252, | |
| "step": 2198 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.8378782089137458, | |
| "eval_f1": 0.8215573432280139, | |
| "eval_loss": 0.3621535897254944, | |
| "eval_precision": 0.846152402138612, | |
| "eval_recall": 0.8106876687211231, | |
| "eval_runtime": 5.775, | |
| "eval_samples_per_second": 225.28, | |
| "eval_steps_per_second": 7.1, | |
| "step": 2205 | |
| } | |
| ], | |
| "logging_steps": 314, | |
| "max_steps": 31500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 100, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |