| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.041688379364252216, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008337675872850442, | |
| "grad_norm": 1.2135348320007324, | |
| "learning_rate": 1e-05, | |
| "loss": 1.9883, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008337675872850442, | |
| "eval_loss": 1.805505394935608, | |
| "eval_runtime": 48.6533, | |
| "eval_samples_per_second": 4.152, | |
| "eval_steps_per_second": 2.076, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.016675351745700884, | |
| "grad_norm": 1.1472969055175781, | |
| "learning_rate": 2e-05, | |
| "loss": 1.748, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.016675351745700884, | |
| "eval_loss": 1.7929213047027588, | |
| "eval_runtime": 5.1239, | |
| "eval_samples_per_second": 39.423, | |
| "eval_steps_per_second": 19.712, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02501302761855133, | |
| "grad_norm": 0.9575781226158142, | |
| "learning_rate": 3e-05, | |
| "loss": 1.7125, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03335070349140177, | |
| "grad_norm": 0.9966278076171875, | |
| "learning_rate": 4e-05, | |
| "loss": 1.7875, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03335070349140177, | |
| "eval_loss": 1.7802919149398804, | |
| "eval_runtime": 5.1321, | |
| "eval_samples_per_second": 39.36, | |
| "eval_steps_per_second": 19.68, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.041688379364252216, | |
| "grad_norm": 1.0722049474716187, | |
| "learning_rate": 5e-05, | |
| "loss": 1.694, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3822182832537600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |