| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.9323671497584543, | |
| "eval_steps": 25, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.24154589371980675, | |
| "grad_norm": 0.3504341244697571, | |
| "learning_rate": 0.000493936638139193, | |
| "loss": 1.2154, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.24154589371980675, | |
| "eval_loss": 1.2845402956008911, | |
| "eval_runtime": 58.0708, | |
| "eval_samples_per_second": 3.565, | |
| "eval_steps_per_second": 0.448, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.4830917874396135, | |
| "grad_norm": 0.11877840012311935, | |
| "learning_rate": 0.000463751348237005, | |
| "loss": 0.7638, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4830917874396135, | |
| "eval_loss": 1.255712628364563, | |
| "eval_runtime": 58.0315, | |
| "eval_samples_per_second": 3.567, | |
| "eval_steps_per_second": 0.448, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7246376811594203, | |
| "grad_norm": 0.09250932186841965, | |
| "learning_rate": 0.000411248712216741, | |
| "loss": 0.7477, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.7246376811594203, | |
| "eval_loss": 1.1869494915008545, | |
| "eval_runtime": 57.9221, | |
| "eval_samples_per_second": 3.574, | |
| "eval_steps_per_second": 0.449, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.966183574879227, | |
| "grad_norm": 0.10278703272342682, | |
| "learning_rate": 0.00034191042415818, | |
| "loss": 0.7249, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.966183574879227, | |
| "eval_loss": 1.317003607749939, | |
| "eval_runtime": 57.9128, | |
| "eval_samples_per_second": 3.574, | |
| "eval_steps_per_second": 0.449, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.2077294685990339, | |
| "grad_norm": 0.09411193430423737, | |
| "learning_rate": 0.00026297595453297494, | |
| "loss": 0.7095, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.2077294685990339, | |
| "eval_loss": 1.3763236999511719, | |
| "eval_runtime": 57.9829, | |
| "eval_samples_per_second": 3.57, | |
| "eval_steps_per_second": 0.448, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.4492753623188406, | |
| "grad_norm": 0.08513357490301132, | |
| "learning_rate": 0.00018268669172909137, | |
| "loss": 0.708, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.4492753623188406, | |
| "eval_loss": 1.2287328243255615, | |
| "eval_runtime": 57.9704, | |
| "eval_samples_per_second": 3.571, | |
| "eval_steps_per_second": 0.449, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.6908212560386473, | |
| "grad_norm": 0.08826680481433868, | |
| "learning_rate": 0.00010942547535123056, | |
| "loss": 0.7055, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.6908212560386473, | |
| "eval_loss": 1.2410857677459717, | |
| "eval_runtime": 58.0223, | |
| "eval_samples_per_second": 3.568, | |
| "eval_steps_per_second": 0.448, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.9323671497584543, | |
| "grad_norm": 0.0850740373134613, | |
| "learning_rate": 5.0841360885691e-05, | |
| "loss": 0.7017, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.9323671497584543, | |
| "eval_loss": 1.2755271196365356, | |
| "eval_runtime": 57.8348, | |
| "eval_samples_per_second": 3.579, | |
| "eval_steps_per_second": 0.45, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 250, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.8667153521278976e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |