| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0002789166875854182, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.7891668758541825e-05, | |
| "grad_norm": 1.1238105297088623, | |
| "learning_rate": 2e-05, | |
| "loss": 4.4271, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.7891668758541825e-05, | |
| "eval_loss": 1.2013081312179565, | |
| "eval_runtime": 958.8034, | |
| "eval_samples_per_second": 15.746, | |
| "eval_steps_per_second": 7.873, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 5.578333751708365e-05, | |
| "grad_norm": 1.0879790782928467, | |
| "learning_rate": 4e-05, | |
| "loss": 4.9715, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 8.367500627562547e-05, | |
| "grad_norm": 1.2436240911483765, | |
| "learning_rate": 6e-05, | |
| "loss": 5.1566, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 8.367500627562547e-05, | |
| "eval_loss": 1.1994664669036865, | |
| "eval_runtime": 939.3782, | |
| "eval_samples_per_second": 16.071, | |
| "eval_steps_per_second": 8.036, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0001115666750341673, | |
| "grad_norm": 1.4930706024169922, | |
| "learning_rate": 8e-05, | |
| "loss": 5.1594, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0001394583437927091, | |
| "grad_norm": 1.4167124032974243, | |
| "learning_rate": 0.0001, | |
| "loss": 5.0046, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00016735001255125095, | |
| "grad_norm": 1.6389849185943604, | |
| "learning_rate": 0.00012, | |
| "loss": 5.5468, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00016735001255125095, | |
| "eval_loss": 1.1673195362091064, | |
| "eval_runtime": 952.3353, | |
| "eval_samples_per_second": 15.853, | |
| "eval_steps_per_second": 7.927, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00019524168130979276, | |
| "grad_norm": 2.352006435394287, | |
| "learning_rate": 0.00014, | |
| "loss": 4.2881, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0002231333500683346, | |
| "grad_norm": 1.347408652305603, | |
| "learning_rate": 0.00016, | |
| "loss": 4.6446, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0002510250188268764, | |
| "grad_norm": 2.6351053714752197, | |
| "learning_rate": 0.00018, | |
| "loss": 4.6772, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0002510250188268764, | |
| "eval_loss": 1.0517847537994385, | |
| "eval_runtime": 882.2945, | |
| "eval_samples_per_second": 17.111, | |
| "eval_steps_per_second": 8.556, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0002789166875854182, | |
| "grad_norm": 1.5746909379959106, | |
| "learning_rate": 0.0002, | |
| "loss": 4.2952, | |
| "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": 3053904828825600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |