| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.001486491508417258, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00029729830168345164, | |
| "grad_norm": 1347.6732177734375, | |
| "learning_rate": 1e-05, | |
| "loss": 73.4618, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00029729830168345164, | |
| "eval_loss": 4.563383102416992, | |
| "eval_runtime": 595.1383, | |
| "eval_samples_per_second": 9.519, | |
| "eval_steps_per_second": 4.76, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005945966033669033, | |
| "grad_norm": 1357.683349609375, | |
| "learning_rate": 2e-05, | |
| "loss": 72.9058, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0005945966033669033, | |
| "eval_loss": 3.701875925064087, | |
| "eval_runtime": 504.5896, | |
| "eval_samples_per_second": 11.227, | |
| "eval_steps_per_second": 5.614, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008918949050503549, | |
| "grad_norm": 701.1543579101562, | |
| "learning_rate": 3e-05, | |
| "loss": 59.3373, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0011891932067338066, | |
| "grad_norm": 541.2560424804688, | |
| "learning_rate": 4e-05, | |
| "loss": 48.324, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0011891932067338066, | |
| "eval_loss": 2.6410446166992188, | |
| "eval_runtime": 506.1165, | |
| "eval_samples_per_second": 11.193, | |
| "eval_steps_per_second": 5.598, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001486491508417258, | |
| "grad_norm": 199.951904296875, | |
| "learning_rate": 5e-05, | |
| "loss": 42.5019, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3505343598428160.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |