| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02599090318388564, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008663634394628547, | |
| "eval_loss": 5.744724750518799, | |
| "eval_runtime": 68.7269, | |
| "eval_samples_per_second": 7.071, | |
| "eval_steps_per_second": 3.536, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002599090318388564, | |
| "grad_norm": 11.913251876831055, | |
| "learning_rate": 6e-05, | |
| "loss": 21.606, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005198180636777128, | |
| "grad_norm": 22.947242736816406, | |
| "learning_rate": 0.00012, | |
| "loss": 22.887, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006930907515702837, | |
| "eval_loss": 4.1123223304748535, | |
| "eval_runtime": 69.7097, | |
| "eval_samples_per_second": 6.972, | |
| "eval_steps_per_second": 3.486, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.007797270955165692, | |
| "grad_norm": 14.847284317016602, | |
| "learning_rate": 0.00018, | |
| "loss": 18.0358, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.010396361273554255, | |
| "grad_norm": 16.89690589904785, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 9.8642, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01299545159194282, | |
| "grad_norm": 16.955928802490234, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 5.2605, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.013861815031405674, | |
| "eval_loss": 0.9268673062324524, | |
| "eval_runtime": 69.7811, | |
| "eval_samples_per_second": 6.965, | |
| "eval_steps_per_second": 3.482, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.015594541910331383, | |
| "grad_norm": 24.856760025024414, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 3.7021, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.018193632228719947, | |
| "grad_norm": 9.974533081054688, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 3.6239, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02079272254710851, | |
| "grad_norm": 51.8785514831543, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 3.442, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02079272254710851, | |
| "eval_loss": 0.7813513278961182, | |
| "eval_runtime": 69.8015, | |
| "eval_samples_per_second": 6.963, | |
| "eval_steps_per_second": 3.481, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.023391812865497075, | |
| "grad_norm": 20.639318466186523, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 3.7789, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.02599090318388564, | |
| "grad_norm": 27.967222213745117, | |
| "learning_rate": 0.0, | |
| "loss": 3.0044, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 70, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9772495452241920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |