| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.008592910848549946, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008592910848549946, | |
| "grad_norm": 0.6928669214248657, | |
| "learning_rate": 2e-05, | |
| "loss": 1.8317, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008592910848549946, | |
| "eval_loss": 1.6235483884811401, | |
| "eval_runtime": 29.7442, | |
| "eval_samples_per_second": 16.474, | |
| "eval_steps_per_second": 8.237, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0017185821697099893, | |
| "grad_norm": 0.5741440653800964, | |
| "learning_rate": 4e-05, | |
| "loss": 1.6288, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0025778732545649837, | |
| "grad_norm": 0.6028909683227539, | |
| "learning_rate": 6e-05, | |
| "loss": 1.646, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0025778732545649837, | |
| "eval_loss": 1.6179994344711304, | |
| "eval_runtime": 29.1266, | |
| "eval_samples_per_second": 16.823, | |
| "eval_steps_per_second": 8.412, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0034371643394199786, | |
| "grad_norm": 0.538411021232605, | |
| "learning_rate": 8e-05, | |
| "loss": 1.5162, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004296455424274973, | |
| "grad_norm": 0.6801743507385254, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5369, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0051557465091299675, | |
| "grad_norm": 0.6478915214538574, | |
| "learning_rate": 0.00012, | |
| "loss": 1.5441, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0051557465091299675, | |
| "eval_loss": 1.5266551971435547, | |
| "eval_runtime": 29.2097, | |
| "eval_samples_per_second": 16.775, | |
| "eval_steps_per_second": 8.388, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006015037593984963, | |
| "grad_norm": 0.7042550444602966, | |
| "learning_rate": 0.00014, | |
| "loss": 1.4077, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006874328678839957, | |
| "grad_norm": 0.6722047924995422, | |
| "learning_rate": 0.00016, | |
| "loss": 1.4403, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.007733619763694952, | |
| "grad_norm": 0.8278146386146545, | |
| "learning_rate": 0.00018, | |
| "loss": 1.3842, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007733619763694952, | |
| "eval_loss": 1.4125406742095947, | |
| "eval_runtime": 29.2312, | |
| "eval_samples_per_second": 16.763, | |
| "eval_steps_per_second": 8.381, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.008592910848549946, | |
| "grad_norm": 0.9954283833503723, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4096, | |
| "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": 3606650283884544.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |