| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00019502586530538614, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.9502586530538612e-05, | |
| "grad_norm": 35.17543029785156, | |
| "learning_rate": 2e-05, | |
| "loss": 16.2937, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.9502586530538612e-05, | |
| "eval_loss": 3.3730227947235107, | |
| "eval_runtime": 694.1993, | |
| "eval_samples_per_second": 31.101, | |
| "eval_steps_per_second": 15.55, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.9005173061077225e-05, | |
| "grad_norm": 20.761104583740234, | |
| "learning_rate": 4e-05, | |
| "loss": 15.3756, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 5.850775959161584e-05, | |
| "grad_norm": 26.16556739807129, | |
| "learning_rate": 6e-05, | |
| "loss": 15.1367, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 5.850775959161584e-05, | |
| "eval_loss": 3.341076612472534, | |
| "eval_runtime": 693.8398, | |
| "eval_samples_per_second": 31.117, | |
| "eval_steps_per_second": 15.558, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 7.801034612215445e-05, | |
| "grad_norm": 21.161108016967773, | |
| "learning_rate": 8e-05, | |
| "loss": 12.9586, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 9.751293265269307e-05, | |
| "grad_norm": 21.10256576538086, | |
| "learning_rate": 0.0001, | |
| "loss": 13.3408, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00011701551918323167, | |
| "grad_norm": 24.035612106323242, | |
| "learning_rate": 0.00012, | |
| "loss": 12.6553, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00011701551918323167, | |
| "eval_loss": 2.9650354385375977, | |
| "eval_runtime": 694.0893, | |
| "eval_samples_per_second": 31.106, | |
| "eval_steps_per_second": 15.553, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00013651810571377028, | |
| "grad_norm": 27.31441307067871, | |
| "learning_rate": 0.00014, | |
| "loss": 10.5551, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0001560206922443089, | |
| "grad_norm": 22.054399490356445, | |
| "learning_rate": 0.00016, | |
| "loss": 12.2846, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00017552327877484752, | |
| "grad_norm": 20.389366149902344, | |
| "learning_rate": 0.00018, | |
| "loss": 9.8355, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00017552327877484752, | |
| "eval_loss": 2.403569221496582, | |
| "eval_runtime": 694.0715, | |
| "eval_samples_per_second": 31.106, | |
| "eval_steps_per_second": 15.553, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00019502586530538614, | |
| "grad_norm": 24.45635223388672, | |
| "learning_rate": 0.0002, | |
| "loss": 8.9958, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1752669785948160.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |