| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004081632653061225, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00040816326530612246, | |
| "grad_norm": 1.3468044996261597, | |
| "learning_rate": 2e-05, | |
| "loss": 3.5911, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00040816326530612246, | |
| "eval_loss": 1.0385665893554688, | |
| "eval_runtime": 42.8641, | |
| "eval_samples_per_second": 24.076, | |
| "eval_steps_per_second": 12.038, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008163265306122449, | |
| "grad_norm": 1.3812683820724487, | |
| "learning_rate": 4e-05, | |
| "loss": 3.761, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0012244897959183673, | |
| "grad_norm": 1.443541407585144, | |
| "learning_rate": 6e-05, | |
| "loss": 3.6089, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0012244897959183673, | |
| "eval_loss": 1.0353370904922485, | |
| "eval_runtime": 41.6313, | |
| "eval_samples_per_second": 24.789, | |
| "eval_steps_per_second": 12.395, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0016326530612244899, | |
| "grad_norm": 1.603192687034607, | |
| "learning_rate": 8e-05, | |
| "loss": 4.332, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0020408163265306124, | |
| "grad_norm": 1.6041061878204346, | |
| "learning_rate": 0.0001, | |
| "loss": 4.71, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0024489795918367346, | |
| "grad_norm": 1.2621709108352661, | |
| "learning_rate": 0.00012, | |
| "loss": 3.5178, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0024489795918367346, | |
| "eval_loss": 1.0071607828140259, | |
| "eval_runtime": 41.6643, | |
| "eval_samples_per_second": 24.769, | |
| "eval_steps_per_second": 12.385, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002857142857142857, | |
| "grad_norm": 1.2419335842132568, | |
| "learning_rate": 0.00014, | |
| "loss": 3.5009, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0032653061224489797, | |
| "grad_norm": 2.04611873626709, | |
| "learning_rate": 0.00016, | |
| "loss": 4.0489, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.003673469387755102, | |
| "grad_norm": 1.4641406536102295, | |
| "learning_rate": 0.00018, | |
| "loss": 3.5892, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.003673469387755102, | |
| "eval_loss": 0.9222005009651184, | |
| "eval_runtime": 41.699, | |
| "eval_samples_per_second": 24.749, | |
| "eval_steps_per_second": 12.374, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004081632653061225, | |
| "grad_norm": 1.3472435474395752, | |
| "learning_rate": 0.0002, | |
| "loss": 3.1156, | |
| "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": 3566006697984000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |