| { | |
| "best_metric": 0.4411565661430359, | |
| "best_model_checkpoint": "autotrain-3c51k-w49bn/checkpoint-69", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 69, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.17391304347826086, | |
| "grad_norm": 3.44027042388916, | |
| "learning_rate": 1.7142857142857142e-05, | |
| "loss": 0.7869, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.34782608695652173, | |
| "grad_norm": 1.9074159860610962, | |
| "learning_rate": 2.9516129032258067e-05, | |
| "loss": 0.7022, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5217391304347826, | |
| "grad_norm": 3.345827579498291, | |
| "learning_rate": 2.758064516129032e-05, | |
| "loss": 0.6482, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.6956521739130435, | |
| "grad_norm": 2.091654062271118, | |
| "learning_rate": 2.5645161290322582e-05, | |
| "loss": 0.5571, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.8695652173913043, | |
| "grad_norm": 1.436171054840088, | |
| "learning_rate": 2.370967741935484e-05, | |
| "loss": 0.5698, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.5249526500701904, | |
| "eval_runtime": 3.0089, | |
| "eval_samples_per_second": 60.487, | |
| "eval_steps_per_second": 3.988, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.0434782608695652, | |
| "grad_norm": 1.838670015335083, | |
| "learning_rate": 2.1774193548387097e-05, | |
| "loss": 0.4771, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.2173913043478262, | |
| "grad_norm": 1.2238214015960693, | |
| "learning_rate": 1.9838709677419355e-05, | |
| "loss": 0.444, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.391304347826087, | |
| "grad_norm": 2.102836847305298, | |
| "learning_rate": 1.7903225806451616e-05, | |
| "loss": 0.6149, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.5652173913043477, | |
| "grad_norm": 1.8485645055770874, | |
| "learning_rate": 1.596774193548387e-05, | |
| "loss": 0.5523, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.7391304347826086, | |
| "grad_norm": 2.7359752655029297, | |
| "learning_rate": 1.403225806451613e-05, | |
| "loss": 0.4806, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.9130434782608696, | |
| "grad_norm": 1.4217264652252197, | |
| "learning_rate": 1.2096774193548387e-05, | |
| "loss": 0.4623, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.46536698937416077, | |
| "eval_runtime": 3.1677, | |
| "eval_samples_per_second": 57.456, | |
| "eval_steps_per_second": 3.788, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.0869565217391304, | |
| "grad_norm": 1.995253562927246, | |
| "learning_rate": 1.0161290322580644e-05, | |
| "loss": 0.4039, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.260869565217391, | |
| "grad_norm": 2.4988834857940674, | |
| "learning_rate": 8.225806451612904e-06, | |
| "loss": 0.47, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.4347826086956523, | |
| "grad_norm": 1.7685775756835938, | |
| "learning_rate": 6.290322580645162e-06, | |
| "loss": 0.3878, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.608695652173913, | |
| "grad_norm": 2.7405200004577637, | |
| "learning_rate": 4.35483870967742e-06, | |
| "loss": 0.5158, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.782608695652174, | |
| "grad_norm": 3.4083738327026367, | |
| "learning_rate": 2.4193548387096776e-06, | |
| "loss": 0.5203, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.9565217391304346, | |
| "grad_norm": 1.6851589679718018, | |
| "learning_rate": 4.838709677419355e-07, | |
| "loss": 0.4446, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.4411565661430359, | |
| "eval_runtime": 1.7496, | |
| "eval_samples_per_second": 104.022, | |
| "eval_steps_per_second": 6.859, | |
| "step": 69 | |
| } | |
| ], | |
| "logging_steps": 4, | |
| "max_steps": 69, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |