| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03386960203217612, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003386960203217612, | |
| "grad_norm": 0.44434577226638794, | |
| "learning_rate": 2e-05, | |
| "loss": 6.0938, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003386960203217612, | |
| "eval_loss": 1.5689184665679932, | |
| "eval_runtime": 8.655, | |
| "eval_samples_per_second": 14.443, | |
| "eval_steps_per_second": 7.279, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006773920406435224, | |
| "grad_norm": 0.46434304118156433, | |
| "learning_rate": 4e-05, | |
| "loss": 6.1191, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.010160880609652836, | |
| "grad_norm": 0.5094742178916931, | |
| "learning_rate": 6e-05, | |
| "loss": 6.3601, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010160880609652836, | |
| "eval_loss": 1.5683244466781616, | |
| "eval_runtime": 8.6667, | |
| "eval_samples_per_second": 14.423, | |
| "eval_steps_per_second": 7.269, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.013547840812870448, | |
| "grad_norm": 0.5346540808677673, | |
| "learning_rate": 8e-05, | |
| "loss": 6.7304, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01693480101608806, | |
| "grad_norm": 0.52632737159729, | |
| "learning_rate": 0.0001, | |
| "loss": 6.4703, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02032176121930567, | |
| "grad_norm": 0.6785563826560974, | |
| "learning_rate": 0.00012, | |
| "loss": 6.197, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02032176121930567, | |
| "eval_loss": 1.5579965114593506, | |
| "eval_runtime": 8.6954, | |
| "eval_samples_per_second": 14.375, | |
| "eval_steps_per_second": 7.245, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.023708721422523286, | |
| "grad_norm": 0.7789506912231445, | |
| "learning_rate": 0.00014, | |
| "loss": 6.6092, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.027095681625740897, | |
| "grad_norm": 0.8114117980003357, | |
| "learning_rate": 0.00016, | |
| "loss": 6.1868, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03048264182895851, | |
| "grad_norm": 1.0380289554595947, | |
| "learning_rate": 0.00018, | |
| "loss": 6.321, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03048264182895851, | |
| "eval_loss": 1.4929735660552979, | |
| "eval_runtime": 8.6742, | |
| "eval_samples_per_second": 14.411, | |
| "eval_steps_per_second": 7.263, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03386960203217612, | |
| "grad_norm": 0.9744961261749268, | |
| "learning_rate": 0.0002, | |
| "loss": 5.8398, | |
| "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": 3257498484080640.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |