| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004090118954292921, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00013633729847643068, | |
| "eval_loss": 2.229485273361206, | |
| "eval_runtime": 156.1586, | |
| "eval_samples_per_second": 19.781, | |
| "eval_steps_per_second": 9.894, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00040901189542929205, | |
| "grad_norm": 1.152373194694519, | |
| "learning_rate": 6e-05, | |
| "loss": 2.0629, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0008180237908585841, | |
| "grad_norm": 1.0188978910446167, | |
| "learning_rate": 0.00012, | |
| "loss": 2.3258, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0010906983878114455, | |
| "eval_loss": 2.1215057373046875, | |
| "eval_runtime": 157.3311, | |
| "eval_samples_per_second": 19.634, | |
| "eval_steps_per_second": 9.82, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0012270356862878762, | |
| "grad_norm": 0.878460705280304, | |
| "learning_rate": 0.00018, | |
| "loss": 2.1532, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0016360475817171682, | |
| "grad_norm": 0.876745343208313, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 2.1755, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0020450594771464605, | |
| "grad_norm": 0.892664909362793, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.9987, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002181396775622891, | |
| "eval_loss": 2.047835111618042, | |
| "eval_runtime": 157.4554, | |
| "eval_samples_per_second": 19.618, | |
| "eval_steps_per_second": 9.812, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0024540713725757523, | |
| "grad_norm": 0.9952620267868042, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.2332, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0028630832680050446, | |
| "grad_norm": 0.9254711270332336, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 2.019, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0032720951634343364, | |
| "grad_norm": 0.8415443897247314, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 2.1299, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0032720951634343364, | |
| "eval_loss": 2.0182554721832275, | |
| "eval_runtime": 157.4278, | |
| "eval_samples_per_second": 19.622, | |
| "eval_steps_per_second": 9.814, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0036811070588636287, | |
| "grad_norm": 0.7659211754798889, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 2.1099, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.004090118954292921, | |
| "grad_norm": 0.586293637752533, | |
| "learning_rate": 0.0, | |
| "loss": 2.1006, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3885912614240256.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |