| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.006946373992775771, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001389274798555154, | |
| "eval_loss": 1.242689609527588, | |
| "eval_runtime": 245.9055, | |
| "eval_samples_per_second": 12.326, | |
| "eval_steps_per_second": 6.165, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006946373992775772, | |
| "grad_norm": 2.261873722076416, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1573, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0013892747985551543, | |
| "grad_norm": 2.256624221801758, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2028, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0013892747985551543, | |
| "eval_loss": 1.2393931150436401, | |
| "eval_runtime": 245.6576, | |
| "eval_samples_per_second": 12.338, | |
| "eval_steps_per_second": 6.171, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0020839121978327314, | |
| "grad_norm": 2.7475228309631348, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.0912, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0027785495971103086, | |
| "grad_norm": 2.3452649116516113, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.0641, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0027785495971103086, | |
| "eval_loss": 1.2139338254928589, | |
| "eval_runtime": 246.0087, | |
| "eval_samples_per_second": 12.321, | |
| "eval_steps_per_second": 6.162, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0034731869963878855, | |
| "grad_norm": 4.441437721252441, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.278, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004167824395665463, | |
| "grad_norm": 3.263500690460205, | |
| "learning_rate": 5e-05, | |
| "loss": 1.2457, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004167824395665463, | |
| "eval_loss": 1.187597632408142, | |
| "eval_runtime": 246.9745, | |
| "eval_samples_per_second": 12.273, | |
| "eval_steps_per_second": 6.138, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0048624617949430396, | |
| "grad_norm": 2.6320784091949463, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.117, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.005557099194220617, | |
| "grad_norm": 3.183335304260254, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.1804, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.005557099194220617, | |
| "eval_loss": 1.1752910614013672, | |
| "eval_runtime": 246.4683, | |
| "eval_samples_per_second": 12.298, | |
| "eval_steps_per_second": 6.151, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.006251736593498194, | |
| "grad_norm": 2.3987159729003906, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.1308, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.006946373992775771, | |
| "grad_norm": 2.901054620742798, | |
| "learning_rate": 0.0, | |
| "loss": 1.1039, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.006946373992775771, | |
| "eval_loss": 1.1731762886047363, | |
| "eval_runtime": 246.5185, | |
| "eval_samples_per_second": 12.295, | |
| "eval_steps_per_second": 6.15, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6211308512870400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |