| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.1238390092879257, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002476780185758514, | |
| "eval_loss": 1.6189539432525635, | |
| "eval_runtime": 10.5009, | |
| "eval_samples_per_second": 16.189, | |
| "eval_steps_per_second": 8.095, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01238390092879257, | |
| "grad_norm": 0.3939303457736969, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5211, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02476780185758514, | |
| "grad_norm": 0.39231282472610474, | |
| "learning_rate": 0.0001, | |
| "loss": 1.6835, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02476780185758514, | |
| "eval_loss": 1.5852490663528442, | |
| "eval_runtime": 10.6661, | |
| "eval_samples_per_second": 15.938, | |
| "eval_steps_per_second": 7.969, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03715170278637771, | |
| "grad_norm": 0.5686100721359253, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.5611, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04953560371517028, | |
| "grad_norm": 0.5406749248504639, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.4431, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04953560371517028, | |
| "eval_loss": 1.4391350746154785, | |
| "eval_runtime": 10.6788, | |
| "eval_samples_per_second": 15.919, | |
| "eval_steps_per_second": 7.96, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06191950464396285, | |
| "grad_norm": 0.6904301047325134, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.3865, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07430340557275542, | |
| "grad_norm": 0.7052592635154724, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5696, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07430340557275542, | |
| "eval_loss": 1.3532814979553223, | |
| "eval_runtime": 10.9419, | |
| "eval_samples_per_second": 15.537, | |
| "eval_steps_per_second": 7.768, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08668730650154799, | |
| "grad_norm": 0.6560043096542358, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.4716, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.09907120743034056, | |
| "grad_norm": 0.6745664477348328, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.3079, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09907120743034056, | |
| "eval_loss": 1.3183584213256836, | |
| "eval_runtime": 10.9598, | |
| "eval_samples_per_second": 15.511, | |
| "eval_steps_per_second": 7.756, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11145510835913312, | |
| "grad_norm": 0.6428639888763428, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.3807, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1238390092879257, | |
| "grad_norm": 0.5295817255973816, | |
| "learning_rate": 0.0, | |
| "loss": 1.357, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1238390092879257, | |
| "eval_loss": 1.3137385845184326, | |
| "eval_runtime": 10.7907, | |
| "eval_samples_per_second": 15.754, | |
| "eval_steps_per_second": 7.877, | |
| "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": 9078482348802048.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |