| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.002201067517746107, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00022010675177461069, | |
| "grad_norm": 2.269176483154297, | |
| "learning_rate": 2e-05, | |
| "loss": 0.9409, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00022010675177461069, | |
| "eval_loss": 1.067487120628357, | |
| "eval_runtime": 60.6103, | |
| "eval_samples_per_second": 31.562, | |
| "eval_steps_per_second": 15.789, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00044021350354922137, | |
| "grad_norm": 1.5156553983688354, | |
| "learning_rate": 4e-05, | |
| "loss": 0.8715, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0006603202553238321, | |
| "grad_norm": 1.7720623016357422, | |
| "learning_rate": 6e-05, | |
| "loss": 1.0462, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006603202553238321, | |
| "eval_loss": 1.0491960048675537, | |
| "eval_runtime": 59.4137, | |
| "eval_samples_per_second": 32.198, | |
| "eval_steps_per_second": 16.107, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0008804270070984427, | |
| "grad_norm": 3.3025259971618652, | |
| "learning_rate": 8e-05, | |
| "loss": 1.0566, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0011005337588730535, | |
| "grad_norm": 1.7581592798233032, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8201, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0013206405106476642, | |
| "grad_norm": 2.876772403717041, | |
| "learning_rate": 0.00012, | |
| "loss": 0.833, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0013206405106476642, | |
| "eval_loss": 0.6473151445388794, | |
| "eval_runtime": 59.4551, | |
| "eval_samples_per_second": 32.176, | |
| "eval_steps_per_second": 16.096, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0015407472624222747, | |
| "grad_norm": 1.5483531951904297, | |
| "learning_rate": 0.00014, | |
| "loss": 0.552, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0017608540141968855, | |
| "grad_norm": 1.6075634956359863, | |
| "learning_rate": 0.00016, | |
| "loss": 0.4392, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0019809607659714962, | |
| "grad_norm": 1.6612417697906494, | |
| "learning_rate": 0.00018, | |
| "loss": 0.4921, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0019809607659714962, | |
| "eval_loss": 0.451882004737854, | |
| "eval_runtime": 59.5127, | |
| "eval_samples_per_second": 32.144, | |
| "eval_steps_per_second": 16.081, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.002201067517746107, | |
| "grad_norm": 1.6807315349578857, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4406, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1849564248145920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |