| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.029354207436399216, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009784735812133072, | |
| "eval_loss": 4.510274410247803, | |
| "eval_runtime": 40.6217, | |
| "eval_samples_per_second": 10.61, | |
| "eval_steps_per_second": 5.317, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0029354207436399216, | |
| "grad_norm": 8.555731773376465, | |
| "learning_rate": 6e-05, | |
| "loss": 4.4104, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005870841487279843, | |
| "grad_norm": 3.8659377098083496, | |
| "learning_rate": 0.00012, | |
| "loss": 3.6807, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.007827788649706457, | |
| "eval_loss": 3.0672507286071777, | |
| "eval_runtime": 40.6608, | |
| "eval_samples_per_second": 10.6, | |
| "eval_steps_per_second": 5.312, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.008806262230919765, | |
| "grad_norm": 3.3067519664764404, | |
| "learning_rate": 0.00018, | |
| "loss": 3.1889, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.011741682974559686, | |
| "grad_norm": 3.9382309913635254, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 2.7903, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.014677103718199608, | |
| "grad_norm": 2.91917085647583, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 2.9457, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.015655577299412915, | |
| "eval_loss": 2.708803176879883, | |
| "eval_runtime": 40.6668, | |
| "eval_samples_per_second": 10.598, | |
| "eval_steps_per_second": 5.311, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01761252446183953, | |
| "grad_norm": 2.821608543395996, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.8381, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02054794520547945, | |
| "grad_norm": 2.1717240810394287, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 2.6047, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.023483365949119372, | |
| "grad_norm": 2.577503204345703, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 2.5007, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.023483365949119372, | |
| "eval_loss": 2.635806083679199, | |
| "eval_runtime": 40.6436, | |
| "eval_samples_per_second": 10.604, | |
| "eval_steps_per_second": 5.314, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.026418786692759294, | |
| "grad_norm": 2.677030563354492, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 2.6274, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.029354207436399216, | |
| "grad_norm": 2.461724042892456, | |
| "learning_rate": 0.0, | |
| "loss": 2.5629, | |
| "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": 1.235418813038592e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |