| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.007665772326561901, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007665772326561902, | |
| "grad_norm": 2.108569622039795, | |
| "learning_rate": 2e-05, | |
| "loss": 3.9583, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007665772326561902, | |
| "eval_loss": 0.9905641674995422, | |
| "eval_runtime": 16.4632, | |
| "eval_samples_per_second": 33.408, | |
| "eval_steps_per_second": 16.704, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015331544653123803, | |
| "grad_norm": 1.8891140222549438, | |
| "learning_rate": 4e-05, | |
| "loss": 3.9198, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0022997316979685703, | |
| "grad_norm": 1.9558780193328857, | |
| "learning_rate": 6e-05, | |
| "loss": 3.8577, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0022997316979685703, | |
| "eval_loss": 0.986197292804718, | |
| "eval_runtime": 16.3367, | |
| "eval_samples_per_second": 33.667, | |
| "eval_steps_per_second": 16.833, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0030663089306247606, | |
| "grad_norm": 1.9550318717956543, | |
| "learning_rate": 8e-05, | |
| "loss": 3.7145, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0038328861632809506, | |
| "grad_norm": 2.522987127304077, | |
| "learning_rate": 0.0001, | |
| "loss": 4.1681, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0045994633959371405, | |
| "grad_norm": 2.159330129623413, | |
| "learning_rate": 0.00012, | |
| "loss": 3.3765, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0045994633959371405, | |
| "eval_loss": 0.9371883869171143, | |
| "eval_runtime": 16.4944, | |
| "eval_samples_per_second": 33.345, | |
| "eval_steps_per_second": 16.672, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005366040628593331, | |
| "grad_norm": 2.697432518005371, | |
| "learning_rate": 0.00014, | |
| "loss": 4.3155, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006132617861249521, | |
| "grad_norm": 3.4887795448303223, | |
| "learning_rate": 0.00016, | |
| "loss": 3.5013, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.006899195093905711, | |
| "grad_norm": 2.555102586746216, | |
| "learning_rate": 0.00018, | |
| "loss": 3.3774, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006899195093905711, | |
| "eval_loss": 0.7540295124053955, | |
| "eval_runtime": 16.4494, | |
| "eval_samples_per_second": 33.436, | |
| "eval_steps_per_second": 16.718, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007665772326561901, | |
| "grad_norm": 2.223823308944702, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4521, | |
| "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": 917953377730560.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |