| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.028665615594094883, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005733123118818977, | |
| "eval_loss": 1.7667937278747559, | |
| "eval_runtime": 129.1672, | |
| "eval_samples_per_second": 5.69, | |
| "eval_steps_per_second": 2.849, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0028665615594094885, | |
| "grad_norm": 1.2960819005966187, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1536, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005733123118818977, | |
| "grad_norm": 3.142393112182617, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1694, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005733123118818977, | |
| "eval_loss": 0.8553229570388794, | |
| "eval_runtime": 136.6121, | |
| "eval_samples_per_second": 5.38, | |
| "eval_steps_per_second": 2.694, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008599684678228465, | |
| "grad_norm": 1.2863491773605347, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.6717, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.011466246237637954, | |
| "grad_norm": 1.5075558423995972, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.4702, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.011466246237637954, | |
| "eval_loss": 0.43800613284111023, | |
| "eval_runtime": 136.7324, | |
| "eval_samples_per_second": 5.375, | |
| "eval_steps_per_second": 2.691, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.014332807797047441, | |
| "grad_norm": 1.00019371509552, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.3006, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01719936935645693, | |
| "grad_norm": 2.1608903408050537, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3844, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01719936935645693, | |
| "eval_loss": 0.27488309144973755, | |
| "eval_runtime": 136.8011, | |
| "eval_samples_per_second": 5.373, | |
| "eval_steps_per_second": 2.69, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.020065930915866417, | |
| "grad_norm": 0.7577710747718811, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.308, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.022932492475275908, | |
| "grad_norm": 0.8970661163330078, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.2806, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.022932492475275908, | |
| "eval_loss": 0.26833829283714294, | |
| "eval_runtime": 136.7125, | |
| "eval_samples_per_second": 5.376, | |
| "eval_steps_per_second": 2.692, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.025799054034685395, | |
| "grad_norm": 0.4498438835144043, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.2123, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.028665615594094883, | |
| "grad_norm": 1.3362246751785278, | |
| "learning_rate": 0.0, | |
| "loss": 0.2544, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.028665615594094883, | |
| "eval_loss": 0.24482083320617676, | |
| "eval_runtime": 136.8236, | |
| "eval_samples_per_second": 5.372, | |
| "eval_steps_per_second": 2.69, | |
| "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": 1.84956424814592e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |