| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.008573388203017833, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00017146776406035664, | |
| "eval_loss": 4.108325481414795, | |
| "eval_runtime": 43.954, | |
| "eval_samples_per_second": 55.877, | |
| "eval_steps_per_second": 27.938, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008573388203017832, | |
| "grad_norm": 42.89037322998047, | |
| "learning_rate": 5e-05, | |
| "loss": 16.2439, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0017146776406035665, | |
| "grad_norm": 46.44820785522461, | |
| "learning_rate": 0.0001, | |
| "loss": 17.8283, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0017146776406035665, | |
| "eval_loss": 4.063690662384033, | |
| "eval_runtime": 43.7981, | |
| "eval_samples_per_second": 56.075, | |
| "eval_steps_per_second": 28.038, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00257201646090535, | |
| "grad_norm": 66.98910522460938, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 16.1692, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.003429355281207133, | |
| "grad_norm": 61.29043960571289, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 16.7979, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003429355281207133, | |
| "eval_loss": 3.880103826522827, | |
| "eval_runtime": 43.5548, | |
| "eval_samples_per_second": 56.389, | |
| "eval_steps_per_second": 28.194, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0042866941015089165, | |
| "grad_norm": 63.954524993896484, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 14.603, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0051440329218107, | |
| "grad_norm": 75.8990478515625, | |
| "learning_rate": 5e-05, | |
| "loss": 14.0956, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0051440329218107, | |
| "eval_loss": 3.7265784740448, | |
| "eval_runtime": 43.433, | |
| "eval_samples_per_second": 56.547, | |
| "eval_steps_per_second": 28.273, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.006001371742112483, | |
| "grad_norm": 66.21800994873047, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 15.0597, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.006858710562414266, | |
| "grad_norm": 76.97616577148438, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 15.509, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.006858710562414266, | |
| "eval_loss": 3.654423236846924, | |
| "eval_runtime": 43.4661, | |
| "eval_samples_per_second": 56.504, | |
| "eval_steps_per_second": 28.252, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.007716049382716049, | |
| "grad_norm": 61.45713806152344, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 15.0919, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.008573388203017833, | |
| "grad_norm": 93.86244201660156, | |
| "learning_rate": 0.0, | |
| "loss": 15.2501, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.008573388203017833, | |
| "eval_loss": 3.6407275199890137, | |
| "eval_runtime": 43.3062, | |
| "eval_samples_per_second": 56.712, | |
| "eval_steps_per_second": 28.356, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "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": 438642828902400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |