Download checkpoint-1608/trainer_state.json from computerboy410/Roberta_constraint_2021: direct link, hf CLI and curl.
- Browser
- Download file 4.97 kB
-
https://huggingface.co/computerboy410/Roberta_constraint_2021/resolve/main/checkpoint-1608/trainer_state.json
- Command line
-
hf download hf://computerboy410/Roberta_constraint_2021/checkpoint-1608/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/computerboy410/Roberta_constraint_2021/resolve/main/checkpoint-1608/trainer_state.json
4.97 kB
| { | |
| "best_global_step": 1608, | |
| "best_metric": 0.9739053516143299, | |
| "best_model_checkpoint": "/content/drive/MyDrive/adv_gen/02_Models/Surrogates/RoBERTa_Constraint2021/checkpoint-1608", | |
| "epoch": 4.0, | |
| "eval_steps": 500, | |
| "global_step": 1608, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.24875621890547264, | |
| "grad_norm": 12.755484580993652, | |
| "learning_rate": 1.485e-05, | |
| "loss": 0.5675763320922852, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.4975124378109453, | |
| "grad_norm": 20.837379455566406, | |
| "learning_rate": 2.985e-05, | |
| "loss": 0.28434215545654296, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.746268656716418, | |
| "grad_norm": 2.7691614627838135, | |
| "learning_rate": 2.7890625000000002e-05, | |
| "loss": 0.16768863677978516, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.9950248756218906, | |
| "grad_norm": 19.097896575927734, | |
| "learning_rate": 2.575994318181818e-05, | |
| "loss": 0.19632043838500976, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9485981308411215, | |
| "eval_f1": 0.9526678141135972, | |
| "eval_loss": 0.23201586306095123, | |
| "eval_runtime": 14.1506, | |
| "eval_samples_per_second": 151.23, | |
| "eval_steps_per_second": 9.47, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 1.243781094527363, | |
| "grad_norm": 41.2952880859375, | |
| "learning_rate": 2.3629261363636365e-05, | |
| "loss": 0.11888823509216309, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.4925373134328357, | |
| "grad_norm": 6.743992328643799, | |
| "learning_rate": 2.1498579545454548e-05, | |
| "loss": 0.10398503303527833, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.7412935323383083, | |
| "grad_norm": 0.04455677047371864, | |
| "learning_rate": 1.9367897727272727e-05, | |
| "loss": 0.13183796882629395, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.9900497512437811, | |
| "grad_norm": 25.297327041625977, | |
| "learning_rate": 1.723721590909091e-05, | |
| "loss": 0.09564775466918946, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9682242990654205, | |
| "eval_f1": 0.9697508896797153, | |
| "eval_loss": 0.14717483520507812, | |
| "eval_runtime": 14.1045, | |
| "eval_samples_per_second": 151.725, | |
| "eval_steps_per_second": 9.501, | |
| "step": 804 | |
| }, | |
| { | |
| "epoch": 2.2388059701492535, | |
| "grad_norm": 0.056198760867118835, | |
| "learning_rate": 1.5106534090909092e-05, | |
| "loss": 0.07061147212982177, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.487562189054726, | |
| "grad_norm": 0.029216887429356575, | |
| "learning_rate": 1.2975852272727275e-05, | |
| "loss": 0.051020784378051756, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.7363184079601988, | |
| "grad_norm": 0.06548340618610382, | |
| "learning_rate": 1.0845170454545454e-05, | |
| "loss": 0.041219482421875, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.9850746268656714, | |
| "grad_norm": 0.07763787358999252, | |
| "learning_rate": 8.714488636363636e-06, | |
| "loss": 0.023678507804870606, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9649532710280374, | |
| "eval_f1": 0.9673771204871683, | |
| "eval_loss": 0.20711995661258698, | |
| "eval_runtime": 14.1306, | |
| "eval_samples_per_second": 151.445, | |
| "eval_steps_per_second": 9.483, | |
| "step": 1206 | |
| }, | |
| { | |
| "epoch": 3.2338308457711444, | |
| "grad_norm": 0.006905850488692522, | |
| "learning_rate": 6.5838068181818185e-06, | |
| "loss": 0.006628125905990601, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 3.482587064676617, | |
| "grad_norm": 0.0073797982186079025, | |
| "learning_rate": 4.453125e-06, | |
| "loss": 0.022305617332458495, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 3.7313432835820897, | |
| "grad_norm": 0.2881132960319519, | |
| "learning_rate": 2.3224431818181816e-06, | |
| "loss": 0.020951387882232667, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.9800995024875623, | |
| "grad_norm": 0.00679817283526063, | |
| "learning_rate": 1.9176136363636366e-07, | |
| "loss": 0.01815043807029724, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9724299065420561, | |
| "eval_f1": 0.9739053516143299, | |
| "eval_loss": 0.1720760464668274, | |
| "eval_runtime": 14.1271, | |
| "eval_samples_per_second": 151.482, | |
| "eval_steps_per_second": 9.485, | |
| "step": 1608 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 1608, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "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": 1689172975411200.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |