| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.2222222222222222, |
| "eval_steps": 50, |
| "global_step": 100, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.022222222222222223, |
| "grad_norm": 0.6193130612373352, |
| "learning_rate": 9.910000000000001e-05, |
| "loss": 1.654, |
| "mean_token_accuracy": 0.6766653224825859, |
| "num_tokens": 23330.0, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.044444444444444446, |
| "grad_norm": 0.5931444764137268, |
| "learning_rate": 9.81e-05, |
| "loss": 1.0695, |
| "mean_token_accuracy": 0.7898772016167641, |
| "num_tokens": 46070.0, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.06666666666666667, |
| "grad_norm": 0.3904027044773102, |
| "learning_rate": 9.71e-05, |
| "loss": 0.7556, |
| "mean_token_accuracy": 0.8578989505767822, |
| "num_tokens": 68719.0, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.08888888888888889, |
| "grad_norm": 0.32560470700263977, |
| "learning_rate": 9.61e-05, |
| "loss": 0.6186, |
| "mean_token_accuracy": 0.8813577085733414, |
| "num_tokens": 92126.0, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.1111111111111111, |
| "grad_norm": 0.30384671688079834, |
| "learning_rate": 9.51e-05, |
| "loss": 0.5761, |
| "mean_token_accuracy": 0.8921546742320061, |
| "num_tokens": 114738.0, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.1111111111111111, |
| "eval_loss": 0.5330827236175537, |
| "eval_mean_token_accuracy": 0.9009262701869011, |
| "eval_num_tokens": 114738.0, |
| "eval_runtime": 40.5094, |
| "eval_samples_per_second": 4.937, |
| "eval_steps_per_second": 4.937, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.13333333333333333, |
| "grad_norm": 0.40981799364089966, |
| "learning_rate": 9.41e-05, |
| "loss": 0.4978, |
| "mean_token_accuracy": 0.9065196111798286, |
| "num_tokens": 136310.0, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.15555555555555556, |
| "grad_norm": 0.5167299509048462, |
| "learning_rate": 9.310000000000001e-05, |
| "loss": 0.4466, |
| "mean_token_accuracy": 0.9203566908836365, |
| "num_tokens": 158193.0, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.17777777777777778, |
| "grad_norm": 0.5062010884284973, |
| "learning_rate": 9.21e-05, |
| "loss": 0.4003, |
| "mean_token_accuracy": 0.9284946233034134, |
| "num_tokens": 180767.0, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 0.38172802329063416, |
| "learning_rate": 9.11e-05, |
| "loss": 0.3457, |
| "mean_token_accuracy": 0.9404646947979927, |
| "num_tokens": 203203.0, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.2222222222222222, |
| "grad_norm": 0.4985530376434326, |
| "learning_rate": 9.010000000000001e-05, |
| "loss": 0.3271, |
| "mean_token_accuracy": 0.9434564337134361, |
| "num_tokens": 226070.0, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.2222222222222222, |
| "eval_loss": 0.3216829001903534, |
| "eval_mean_token_accuracy": 0.9481457704305649, |
| "eval_num_tokens": 226070.0, |
| "eval_runtime": 41.0245, |
| "eval_samples_per_second": 4.875, |
| "eval_steps_per_second": 4.875, |
| "step": 100 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 1000, |
| "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": 1094077520640000.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
