| { | |
| "best_metric": 5.248876094818115, | |
| "best_model_checkpoint": "autotrain-htyqd-ivazp/checkpoint-64", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 64, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.046875, | |
| "grad_norm": 14.052762985229492, | |
| "learning_rate": 1.5625e-06, | |
| "loss": 3.6996, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.09375, | |
| "grad_norm": 14.165870666503906, | |
| "learning_rate": 3.90625e-06, | |
| "loss": 3.6546, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.140625, | |
| "grad_norm": 16.012378692626953, | |
| "learning_rate": 6.25e-06, | |
| "loss": 3.4308, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1875, | |
| "grad_norm": 14.69151496887207, | |
| "learning_rate": 8.59375e-06, | |
| "loss": 2.9723, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.234375, | |
| "grad_norm": 14.49859619140625, | |
| "learning_rate": 1.09375e-05, | |
| "loss": 2.55, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.28125, | |
| "grad_norm": 9.837970733642578, | |
| "learning_rate": 1.3281250000000001e-05, | |
| "loss": 2.1128, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.328125, | |
| "grad_norm": 5.071118354797363, | |
| "learning_rate": 1.5625e-05, | |
| "loss": 1.6801, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.375, | |
| "grad_norm": 2.0291266441345215, | |
| "learning_rate": 1.796875e-05, | |
| "loss": 1.6157, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.421875, | |
| "grad_norm": 3.643156051635742, | |
| "learning_rate": 2.0312500000000002e-05, | |
| "loss": 1.4422, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.46875, | |
| "grad_norm": 2.610175609588623, | |
| "learning_rate": 2.2656250000000002e-05, | |
| "loss": 1.5487, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.515625, | |
| "grad_norm": 2.2735087871551514, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.5584, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.5625, | |
| "grad_norm": 3.6203994750976562, | |
| "learning_rate": 2.734375e-05, | |
| "loss": 1.4387, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.609375, | |
| "grad_norm": 1.6243354082107544, | |
| "learning_rate": 2.96875e-05, | |
| "loss": 1.4952, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.65625, | |
| "grad_norm": 1.4888181686401367, | |
| "learning_rate": 3.203125e-05, | |
| "loss": 1.3624, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.703125, | |
| "grad_norm": 2.144364595413208, | |
| "learning_rate": 3.4375e-05, | |
| "loss": 1.5163, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 1.7939876317977905, | |
| "learning_rate": 3.671875e-05, | |
| "loss": 1.2903, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.796875, | |
| "grad_norm": 1.5901564359664917, | |
| "learning_rate": 3.90625e-05, | |
| "loss": 1.2762, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.84375, | |
| "grad_norm": 1.5492233037948608, | |
| "learning_rate": 4.140625e-05, | |
| "loss": 1.3743, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.890625, | |
| "grad_norm": 1.4556649923324585, | |
| "learning_rate": 4.375e-05, | |
| "loss": 1.4039, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.9375, | |
| "grad_norm": 2.0221164226531982, | |
| "learning_rate": 4.609375e-05, | |
| "loss": 1.464, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.984375, | |
| "grad_norm": 1.9775513410568237, | |
| "learning_rate": 4.8437500000000005e-05, | |
| "loss": 1.385, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.0026870229007633587, | |
| "eval_f1": 0.0, | |
| "eval_loss": 5.248876094818115, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_runtime": 0.4245, | |
| "eval_samples_per_second": 327.45, | |
| "eval_steps_per_second": 21.202, | |
| "step": 64 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 640, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 16636128375552.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |