| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.2508710801393728, | |
| "eval_steps": 9, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.027874564459930314, | |
| "grad_norm": 1.528730034828186, | |
| "learning_rate": 5e-05, | |
| "loss": 5.1122, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.027874564459930314, | |
| "eval_loss": 4.7186970710754395, | |
| "eval_runtime": 1.266, | |
| "eval_samples_per_second": 191.16, | |
| "eval_steps_per_second": 48.185, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05574912891986063, | |
| "grad_norm": 1.4118348360061646, | |
| "learning_rate": 0.0001, | |
| "loss": 4.8444, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.08362369337979095, | |
| "grad_norm": 1.4177184104919434, | |
| "learning_rate": 9.978670881475172e-05, | |
| "loss": 5.0323, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.11149825783972125, | |
| "grad_norm": 1.3121063709259033, | |
| "learning_rate": 9.91486549841951e-05, | |
| "loss": 4.9379, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.13937282229965156, | |
| "grad_norm": 1.1417440176010132, | |
| "learning_rate": 9.809128215864097e-05, | |
| "loss": 4.9118, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1672473867595819, | |
| "grad_norm": 1.0766890048980713, | |
| "learning_rate": 9.662361147021779e-05, | |
| "loss": 4.8126, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1951219512195122, | |
| "grad_norm": 1.0330865383148193, | |
| "learning_rate": 9.475816456775313e-05, | |
| "loss": 5.0199, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.2229965156794425, | |
| "grad_norm": 0.8478246331214905, | |
| "learning_rate": 9.251085678648072e-05, | |
| "loss": 4.7868, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.2508710801393728, | |
| "grad_norm": 0.7461872100830078, | |
| "learning_rate": 8.9900861364012e-05, | |
| "loss": 4.7503, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.2508710801393728, | |
| "eval_loss": 4.568607330322266, | |
| "eval_runtime": 1.2588, | |
| "eval_samples_per_second": 192.254, | |
| "eval_steps_per_second": 48.461, | |
| "step": 9 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 36, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 9, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1547005696409600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |