| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.05052631578947368, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0016842105263157896, | |
| "eval_loss": 4.296731948852539, | |
| "eval_runtime": 33.4934, | |
| "eval_samples_per_second": 7.464, | |
| "eval_steps_per_second": 3.732, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0050526315789473685, | |
| "grad_norm": 1.9722530841827393, | |
| "learning_rate": 6e-05, | |
| "loss": 3.827, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010105263157894737, | |
| "grad_norm": 2.1846985816955566, | |
| "learning_rate": 0.00012, | |
| "loss": 3.6769, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.013473684210526317, | |
| "eval_loss": 3.1496376991271973, | |
| "eval_runtime": 33.4282, | |
| "eval_samples_per_second": 7.479, | |
| "eval_steps_per_second": 3.739, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.015157894736842105, | |
| "grad_norm": 1.7809538841247559, | |
| "learning_rate": 0.00018, | |
| "loss": 3.2467, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.020210526315789474, | |
| "grad_norm": 2.0705854892730713, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 2.5268, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.02526315789473684, | |
| "grad_norm": 2.0589914321899414, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.9183, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.026947368421052633, | |
| "eval_loss": 1.4310015439987183, | |
| "eval_runtime": 33.4479, | |
| "eval_samples_per_second": 7.474, | |
| "eval_steps_per_second": 3.737, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.03031578947368421, | |
| "grad_norm": 1.4359524250030518, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.2323, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03536842105263158, | |
| "grad_norm": 2.9023444652557373, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 0.9628, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.04042105263157895, | |
| "grad_norm": 2.346060276031494, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 0.9069, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.04042105263157895, | |
| "eval_loss": 0.9707378149032593, | |
| "eval_runtime": 33.5386, | |
| "eval_samples_per_second": 7.454, | |
| "eval_steps_per_second": 3.727, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.04547368421052632, | |
| "grad_norm": 2.3689370155334473, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 0.8106, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.05052631578947368, | |
| "grad_norm": 2.2287442684173584, | |
| "learning_rate": 0.0, | |
| "loss": 0.8476, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.90433766408192e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |