| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00984251968503937, | |
| "eval_steps": 8, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004921259842519685, | |
| "eval_loss": 1.3110560178756714, | |
| "eval_runtime": 12.4816, | |
| "eval_samples_per_second": 68.581, | |
| "eval_steps_per_second": 34.29, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0014763779527559055, | |
| "grad_norm": 0.9920353889465332, | |
| "learning_rate": 6e-05, | |
| "loss": 4.8986, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002952755905511811, | |
| "grad_norm": 1.4685040712356567, | |
| "learning_rate": 0.00012, | |
| "loss": 5.0753, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003937007874015748, | |
| "eval_loss": 1.2657536268234253, | |
| "eval_runtime": 12.5041, | |
| "eval_samples_per_second": 68.458, | |
| "eval_steps_per_second": 34.229, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0044291338582677165, | |
| "grad_norm": 1.1031194925308228, | |
| "learning_rate": 0.00018, | |
| "loss": 4.9321, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005905511811023622, | |
| "grad_norm": 2.2096595764160156, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 5.3159, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0073818897637795275, | |
| "grad_norm": 2.601541519165039, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 5.5939, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007874015748031496, | |
| "eval_loss": 1.2247308492660522, | |
| "eval_runtime": 12.5266, | |
| "eval_samples_per_second": 68.335, | |
| "eval_steps_per_second": 34.167, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.008858267716535433, | |
| "grad_norm": 1.7524709701538086, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 4.542, | |
| "step": 18 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1048101657772032.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |