| { | |
| "best_metric": 7.529487609863281, | |
| "best_model_checkpoint": "./results/checkpoint-916", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 916, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.1091703056768559, | |
| "grad_norm": 25.480337142944336, | |
| "learning_rate": 2.959061135371179e-05, | |
| "loss": 56.923, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2183406113537118, | |
| "grad_norm": 39.87223815917969, | |
| "learning_rate": 2.918122270742358e-05, | |
| "loss": 46.6475, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.32751091703056767, | |
| "grad_norm": 48.05048751831055, | |
| "learning_rate": 2.877183406113537e-05, | |
| "loss": 33.6867, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.4366812227074236, | |
| "grad_norm": 31.941883087158203, | |
| "learning_rate": 2.8362445414847164e-05, | |
| "loss": 21.1084, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.5458515283842795, | |
| "grad_norm": 55.025856018066406, | |
| "learning_rate": 2.7953056768558954e-05, | |
| "loss": 12.9495, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.6550218340611353, | |
| "grad_norm": 34.957523345947266, | |
| "learning_rate": 2.7543668122270742e-05, | |
| "loss": 10.0745, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.7641921397379913, | |
| "grad_norm": 24.020906448364258, | |
| "learning_rate": 2.7134279475982533e-05, | |
| "loss": 8.3541, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.8733624454148472, | |
| "grad_norm": 32.709571838378906, | |
| "learning_rate": 2.6724890829694323e-05, | |
| "loss": 7.5128, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.982532751091703, | |
| "grad_norm": 38.94672393798828, | |
| "learning_rate": 2.6315502183406114e-05, | |
| "loss": 7.2241, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_avg_mae": 7.529487609863281, | |
| "eval_loss": 7.529487609863281, | |
| "eval_mae_lex": 6.992014408111572, | |
| "eval_mae_sem": 5.432034492492676, | |
| "eval_mae_syn": 10.164413452148438, | |
| "eval_runtime": 27.1764, | |
| "eval_samples_per_second": 269.609, | |
| "eval_steps_per_second": 8.426, | |
| "step": 916 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 7328, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 8, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1927766233338624.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |