| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.06317119393556538, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0012634238787113076, | |
| "eval_loss": 0.8878610730171204, | |
| "eval_runtime": 41.0395, | |
| "eval_samples_per_second": 8.139, | |
| "eval_steps_per_second": 4.069, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006317119393556538, | |
| "grad_norm": 0.5309655070304871, | |
| "learning_rate": 5e-05, | |
| "loss": 0.865, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.012634238787113077, | |
| "grad_norm": 0.5345095992088318, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8402, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.012634238787113077, | |
| "eval_loss": 0.7144569754600525, | |
| "eval_runtime": 41.3875, | |
| "eval_samples_per_second": 8.07, | |
| "eval_steps_per_second": 4.035, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.018951358180669616, | |
| "grad_norm": 0.6154476404190063, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.6647, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.025268477574226154, | |
| "grad_norm": 0.5439320802688599, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.6373, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.025268477574226154, | |
| "eval_loss": 0.5970596075057983, | |
| "eval_runtime": 41.5592, | |
| "eval_samples_per_second": 8.037, | |
| "eval_steps_per_second": 4.018, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03158559696778269, | |
| "grad_norm": 0.4888911545276642, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.5915, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03790271636133923, | |
| "grad_norm": 0.5220611691474915, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5889, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03790271636133923, | |
| "eval_loss": 0.5668606162071228, | |
| "eval_runtime": 41.6213, | |
| "eval_samples_per_second": 8.025, | |
| "eval_steps_per_second": 4.012, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04421983575489577, | |
| "grad_norm": 0.4219604730606079, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.569, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.05053695514845231, | |
| "grad_norm": 0.4335253834724426, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.5527, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05053695514845231, | |
| "eval_loss": 0.5540109276771545, | |
| "eval_runtime": 41.8184, | |
| "eval_samples_per_second": 7.987, | |
| "eval_steps_per_second": 3.993, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.056854074542008845, | |
| "grad_norm": 0.48217666149139404, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.5588, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.06317119393556538, | |
| "grad_norm": 0.45759883522987366, | |
| "learning_rate": 0.0, | |
| "loss": 0.5631, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06317119393556538, | |
| "eval_loss": 0.5510811805725098, | |
| "eval_runtime": 41.4399, | |
| "eval_samples_per_second": 8.06, | |
| "eval_steps_per_second": 4.03, | |
| "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": 1.61937503551488e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |