| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9142857142857143, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.018285714285714287, | |
| "eval_loss": 1.6030340194702148, | |
| "eval_runtime": 22.4221, | |
| "eval_samples_per_second": 16.457, | |
| "eval_steps_per_second": 2.096, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.18285714285714286, | |
| "grad_norm": 0.11251654475927353, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.5836, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.18285714285714286, | |
| "eval_loss": 1.5457781553268433, | |
| "eval_runtime": 22.3246, | |
| "eval_samples_per_second": 16.529, | |
| "eval_steps_per_second": 2.105, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3657142857142857, | |
| "grad_norm": 0.08535242080688477, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.5303, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3657142857142857, | |
| "eval_loss": 1.5059994459152222, | |
| "eval_runtime": 22.2678, | |
| "eval_samples_per_second": 16.571, | |
| "eval_steps_per_second": 2.111, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5485714285714286, | |
| "grad_norm": 0.07273497432470322, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.5166, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5485714285714286, | |
| "eval_loss": 1.4853366613388062, | |
| "eval_runtime": 22.3264, | |
| "eval_samples_per_second": 16.527, | |
| "eval_steps_per_second": 2.105, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.7314285714285714, | |
| "grad_norm": 0.07180826365947723, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.501, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.7314285714285714, | |
| "eval_loss": 1.4780809879302979, | |
| "eval_runtime": 22.2666, | |
| "eval_samples_per_second": 16.572, | |
| "eval_steps_per_second": 2.111, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.9142857142857143, | |
| "grad_norm": 0.08199798315763474, | |
| "learning_rate": 0.0, | |
| "loss": 1.4879, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.9142857142857143, | |
| "eval_loss": 1.4767606258392334, | |
| "eval_runtime": 22.3248, | |
| "eval_samples_per_second": 16.529, | |
| "eval_steps_per_second": 2.105, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.31207786397696e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |