| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.006052935673801794, | |
| "eval_steps": 14, | |
| "global_step": 55, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00011005337588730534, | |
| "eval_loss": 10.822315216064453, | |
| "eval_runtime": 5.8304, | |
| "eval_samples_per_second": 328.106, | |
| "eval_steps_per_second": 164.139, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011005337588730535, | |
| "grad_norm": 0.6667066216468811, | |
| "learning_rate": 0.0002, | |
| "loss": 10.806, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0015407472624222747, | |
| "eval_loss": 10.737513542175293, | |
| "eval_runtime": 4.7361, | |
| "eval_samples_per_second": 403.918, | |
| "eval_steps_per_second": 202.065, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.002201067517746107, | |
| "grad_norm": 0.5717674493789673, | |
| "learning_rate": 0.0002, | |
| "loss": 10.7408, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0030814945248445495, | |
| "eval_loss": 10.655326843261719, | |
| "eval_runtime": 4.8315, | |
| "eval_samples_per_second": 395.944, | |
| "eval_steps_per_second": 198.076, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0033016012766191602, | |
| "grad_norm": 0.41113874316215515, | |
| "learning_rate": 0.0002, | |
| "loss": 10.6651, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004402135035492214, | |
| "grad_norm": 0.4073917269706726, | |
| "learning_rate": 0.0002, | |
| "loss": 10.6402, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.004622241787266825, | |
| "eval_loss": 10.625805854797363, | |
| "eval_runtime": 4.8039, | |
| "eval_samples_per_second": 398.221, | |
| "eval_steps_per_second": 199.214, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.005502668794365267, | |
| "grad_norm": 0.4459260106086731, | |
| "learning_rate": 0.0002, | |
| "loss": 10.6161, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 55, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 14, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2462328029184.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |