| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.002458462231873963, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.194874106246543e-05, | |
| "eval_loss": 11.113264083862305, | |
| "eval_runtime": 19.5618, | |
| "eval_samples_per_second": 262.655, | |
| "eval_steps_per_second": 131.328, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002458462231873963, | |
| "grad_norm": 1.3417675495147705, | |
| "learning_rate": 6e-05, | |
| "loss": 44.4185, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0004916924463747926, | |
| "grad_norm": 1.1938875913619995, | |
| "learning_rate": 0.00012, | |
| "loss": 44.4719, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0006555899284997234, | |
| "eval_loss": 11.108757019042969, | |
| "eval_runtime": 18.8941, | |
| "eval_samples_per_second": 271.937, | |
| "eval_steps_per_second": 135.968, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0007375386695621888, | |
| "grad_norm": 1.3854049444198608, | |
| "learning_rate": 0.00018, | |
| "loss": 44.4537, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.000983384892749585, | |
| "grad_norm": 1.2061694860458374, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 44.3909, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0012292311159369815, | |
| "grad_norm": 1.3102339506149292, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 44.3994, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0013111798569994469, | |
| "eval_loss": 11.093602180480957, | |
| "eval_runtime": 19.1706, | |
| "eval_samples_per_second": 268.015, | |
| "eval_steps_per_second": 134.008, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0014750773391243777, | |
| "grad_norm": 1.3662303686141968, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 44.3601, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.001720923562311774, | |
| "grad_norm": 1.3945192098617554, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 44.3528, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.00196676978549917, | |
| "grad_norm": 1.4578007459640503, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 44.3023, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00196676978549917, | |
| "eval_loss": 11.081588745117188, | |
| "eval_runtime": 19.807, | |
| "eval_samples_per_second": 259.404, | |
| "eval_steps_per_second": 129.702, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0022126160086865664, | |
| "grad_norm": 1.4502112865447998, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 44.3151, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.002458462231873963, | |
| "grad_norm": 1.383909821510315, | |
| "learning_rate": 0.0, | |
| "loss": 44.314, | |
| "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": 623986606080.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |