| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.005803830528148578, | |
| "eval_steps": 14, | |
| "global_step": 55, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00010552419142088324, | |
| "eval_loss": 0.668049156665802, | |
| "eval_runtime": 179.5573, | |
| "eval_samples_per_second": 22.221, | |
| "eval_steps_per_second": 5.558, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010552419142088323, | |
| "grad_norm": 0.5289081931114197, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2967, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0014773386798923654, | |
| "eval_loss": 0.5321353673934937, | |
| "eval_runtime": 179.6624, | |
| "eval_samples_per_second": 22.208, | |
| "eval_steps_per_second": 5.555, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0021104838284176646, | |
| "grad_norm": 0.49633944034576416, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1033, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002954677359784731, | |
| "eval_loss": 0.5081874132156372, | |
| "eval_runtime": 179.6733, | |
| "eval_samples_per_second": 22.207, | |
| "eval_steps_per_second": 5.555, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.003165725742626497, | |
| "grad_norm": 0.41564086079597473, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0025, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004220967656835329, | |
| "grad_norm": 0.4520661234855652, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0454, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.004432016039677096, | |
| "eval_loss": 0.4983692467212677, | |
| "eval_runtime": 179.6429, | |
| "eval_samples_per_second": 22.211, | |
| "eval_steps_per_second": 5.555, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.005276209571044162, | |
| "grad_norm": 0.44811803102493286, | |
| "learning_rate": 0.0002, | |
| "loss": 1.021, | |
| "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": 1.6763560755462144e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |