| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.056100981767180924, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0018700327255726976, | |
| "eval_loss": 9.52480411529541, | |
| "eval_runtime": 1.3402, | |
| "eval_samples_per_second": 168.635, | |
| "eval_steps_per_second": 84.318, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005610098176718092, | |
| "grad_norm": 11424.5166015625, | |
| "learning_rate": 6e-05, | |
| "loss": 36.5485, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009350163627863487, | |
| "eval_loss": 9.466535568237305, | |
| "eval_runtime": 1.8078, | |
| "eval_samples_per_second": 125.011, | |
| "eval_steps_per_second": 62.505, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.011220196353436185, | |
| "grad_norm": 19902.013671875, | |
| "learning_rate": 0.00012, | |
| "loss": 38.8329, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.016830294530154277, | |
| "grad_norm": 13192.7705078125, | |
| "learning_rate": 0.00018, | |
| "loss": 37.2331, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.018700327255726974, | |
| "eval_loss": 9.326210975646973, | |
| "eval_runtime": 1.3413, | |
| "eval_samples_per_second": 168.497, | |
| "eval_steps_per_second": 84.249, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02244039270687237, | |
| "grad_norm": 7629.75390625, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 38.3511, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.028050490883590462, | |
| "grad_norm": 6675.2470703125, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 37.0423, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.028050490883590462, | |
| "eval_loss": 9.183147430419922, | |
| "eval_runtime": 1.3759, | |
| "eval_samples_per_second": 164.259, | |
| "eval_steps_per_second": 82.129, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.033660589060308554, | |
| "grad_norm": 12042.025390625, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 35.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03740065451145395, | |
| "eval_loss": 8.979737281799316, | |
| "eval_runtime": 1.3233, | |
| "eval_samples_per_second": 170.783, | |
| "eval_steps_per_second": 85.391, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03927068723702665, | |
| "grad_norm": 13065.3056640625, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 35.4466, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.04488078541374474, | |
| "grad_norm": 5766.87890625, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 34.962, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.04675081813931744, | |
| "eval_loss": 8.88081169128418, | |
| "eval_runtime": 1.388, | |
| "eval_samples_per_second": 162.82, | |
| "eval_steps_per_second": 81.41, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05049088359046283, | |
| "grad_norm": 6992.9677734375, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 35.5057, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.056100981767180924, | |
| "grad_norm": 7209.02197265625, | |
| "learning_rate": 0.0, | |
| "loss": 34.8763, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.056100981767180924, | |
| "eval_loss": 8.885871887207031, | |
| "eval_runtime": 1.8791, | |
| "eval_samples_per_second": 120.271, | |
| "eval_steps_per_second": 60.135, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 11539033620480.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |