| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0037460900185431454, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.492180037086291e-05, | |
| "eval_loss": 4.0028395652771, | |
| "eval_runtime": 173.327, | |
| "eval_samples_per_second": 32.424, | |
| "eval_steps_per_second": 16.212, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003746090018543146, | |
| "grad_norm": 25.325063705444336, | |
| "learning_rate": 5e-05, | |
| "loss": 2.8481, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0007492180037086292, | |
| "grad_norm": 16.591045379638672, | |
| "learning_rate": 0.0001, | |
| "loss": 3.235, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0007492180037086292, | |
| "eval_loss": 2.25746488571167, | |
| "eval_runtime": 170.0427, | |
| "eval_samples_per_second": 33.051, | |
| "eval_steps_per_second": 16.525, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0011238270055629438, | |
| "grad_norm": 4.520763874053955, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.9174, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0014984360074172583, | |
| "grad_norm": 4.631959438323975, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.5114, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0014984360074172583, | |
| "eval_loss": 1.635870099067688, | |
| "eval_runtime": 170.8481, | |
| "eval_samples_per_second": 32.895, | |
| "eval_steps_per_second": 16.447, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0018730450092715727, | |
| "grad_norm": 4.3356170654296875, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.4282, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0022476540111258875, | |
| "grad_norm": 3.696913480758667, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4056, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0022476540111258875, | |
| "eval_loss": 1.4081323146820068, | |
| "eval_runtime": 169.9989, | |
| "eval_samples_per_second": 33.059, | |
| "eval_steps_per_second": 16.53, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.002622263012980202, | |
| "grad_norm": 2.769284963607788, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.3726, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0029968720148345167, | |
| "grad_norm": 3.6250598430633545, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.807, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0029968720148345167, | |
| "eval_loss": 1.3421251773834229, | |
| "eval_runtime": 170.1126, | |
| "eval_samples_per_second": 33.037, | |
| "eval_steps_per_second": 16.518, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.003371481016688831, | |
| "grad_norm": 4.033442497253418, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.2707, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0037460900185431454, | |
| "grad_norm": 1.2162737846374512, | |
| "learning_rate": 0.0, | |
| "loss": 1.1374, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0037460900185431454, | |
| "eval_loss": 1.3300808668136597, | |
| "eval_runtime": 169.6943, | |
| "eval_samples_per_second": 33.118, | |
| "eval_steps_per_second": 16.559, | |
| "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": 1291749490163712.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |