| { | |
| "best_metric": 0.29650357365608215, | |
| "best_model_checkpoint": "autotrain-revmo-53leq/checkpoint-66", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 66, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.045454545454545456, | |
| "grad_norm": 28.6497802734375, | |
| "learning_rate": 7.142857142857143e-06, | |
| "loss": 0.4602, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.09090909090909091, | |
| "grad_norm": 12.750972747802734, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 0.4166, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.13636363636363635, | |
| "grad_norm": 16.603534698486328, | |
| "learning_rate": 2.1428571428571428e-05, | |
| "loss": 0.5021, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.18181818181818182, | |
| "grad_norm": 17.277828216552734, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 0.4096, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.22727272727272727, | |
| "grad_norm": 11.877945899963379, | |
| "learning_rate": 3.571428571428572e-05, | |
| "loss": 0.2947, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2727272727272727, | |
| "grad_norm": 11.792537689208984, | |
| "learning_rate": 4.2857142857142856e-05, | |
| "loss": 0.2097, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3181818181818182, | |
| "grad_norm": 46.741493225097656, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1688, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.36363636363636365, | |
| "grad_norm": 18.050052642822266, | |
| "learning_rate": 4.915254237288136e-05, | |
| "loss": 0.2662, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.4090909090909091, | |
| "grad_norm": 44.04240036010742, | |
| "learning_rate": 4.8305084745762714e-05, | |
| "loss": 0.7818, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.45454545454545453, | |
| "grad_norm": 64.99262237548828, | |
| "learning_rate": 4.745762711864407e-05, | |
| "loss": 1.3822, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 15.207534790039062, | |
| "learning_rate": 4.6610169491525425e-05, | |
| "loss": 0.1982, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.5454545454545454, | |
| "grad_norm": 79.90739440917969, | |
| "learning_rate": 4.5762711864406784e-05, | |
| "loss": 0.4197, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5909090909090909, | |
| "grad_norm": 56.48210906982422, | |
| "learning_rate": 4.491525423728814e-05, | |
| "loss": 1.0359, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.6363636363636364, | |
| "grad_norm": 56.141273498535156, | |
| "learning_rate": 4.4067796610169495e-05, | |
| "loss": 0.5439, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.6818181818181818, | |
| "grad_norm": 11.973394393920898, | |
| "learning_rate": 4.3220338983050854e-05, | |
| "loss": 0.1168, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "grad_norm": 42.663795471191406, | |
| "learning_rate": 4.2372881355932206e-05, | |
| "loss": 0.7024, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.7727272727272727, | |
| "grad_norm": 33.43160629272461, | |
| "learning_rate": 4.152542372881356e-05, | |
| "loss": 0.5774, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.8181818181818182, | |
| "grad_norm": 19.131776809692383, | |
| "learning_rate": 4.067796610169492e-05, | |
| "loss": 0.2992, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.8636363636363636, | |
| "grad_norm": 29.990232467651367, | |
| "learning_rate": 3.983050847457627e-05, | |
| "loss": 0.3489, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.9090909090909091, | |
| "grad_norm": 27.957719802856445, | |
| "learning_rate": 3.898305084745763e-05, | |
| "loss": 0.2338, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.9545454545454546, | |
| "grad_norm": 31.963809967041016, | |
| "learning_rate": 3.813559322033898e-05, | |
| "loss": 0.3252, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 38.80619812011719, | |
| "learning_rate": 3.728813559322034e-05, | |
| "loss": 0.2618, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7906976744186046, | |
| "eval_f1_macro": 0.8060606060606061, | |
| "eval_f1_micro": 0.7906976744186046, | |
| "eval_f1_weighted": 0.79903352461492, | |
| "eval_loss": 0.48887890577316284, | |
| "eval_precision_macro": 0.8636363636363636, | |
| "eval_precision_micro": 0.7906976744186046, | |
| "eval_precision_weighted": 0.876321353065539, | |
| "eval_recall_macro": 0.8141025641025642, | |
| "eval_recall_micro": 0.7906976744186046, | |
| "eval_recall_weighted": 0.7906976744186046, | |
| "eval_runtime": 7.9869, | |
| "eval_samples_per_second": 5.384, | |
| "eval_steps_per_second": 0.376, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.0454545454545454, | |
| "grad_norm": 3.3973186016082764, | |
| "learning_rate": 3.644067796610169e-05, | |
| "loss": 0.0647, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.0909090909090908, | |
| "grad_norm": 28.498188018798828, | |
| "learning_rate": 3.559322033898305e-05, | |
| "loss": 0.3141, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.1363636363636362, | |
| "grad_norm": 6.814549922943115, | |
| "learning_rate": 3.474576271186441e-05, | |
| "loss": 0.0961, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.1818181818181819, | |
| "grad_norm": 16.97162437438965, | |
| "learning_rate": 3.389830508474576e-05, | |
| "loss": 0.3739, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.2272727272727273, | |
| "grad_norm": 22.352941513061523, | |
| "learning_rate": 3.305084745762712e-05, | |
| "loss": 0.1515, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.2727272727272727, | |
| "grad_norm": 77.6449966430664, | |
| "learning_rate": 3.2203389830508473e-05, | |
| "loss": 0.2559, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.3181818181818181, | |
| "grad_norm": 5.475510597229004, | |
| "learning_rate": 3.135593220338983e-05, | |
| "loss": 0.0531, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.3636363636363638, | |
| "grad_norm": 44.47045135498047, | |
| "learning_rate": 3.050847457627119e-05, | |
| "loss": 0.2621, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.4090909090909092, | |
| "grad_norm": 44.55425262451172, | |
| "learning_rate": 2.9661016949152544e-05, | |
| "loss": 0.3704, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.4545454545454546, | |
| "grad_norm": 19.289321899414062, | |
| "learning_rate": 2.88135593220339e-05, | |
| "loss": 0.0849, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 41.094688415527344, | |
| "learning_rate": 2.7966101694915255e-05, | |
| "loss": 0.4387, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.5454545454545454, | |
| "grad_norm": 21.01316261291504, | |
| "learning_rate": 2.711864406779661e-05, | |
| "loss": 0.1633, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.5909090909090908, | |
| "grad_norm": 38.75764465332031, | |
| "learning_rate": 2.627118644067797e-05, | |
| "loss": 0.2388, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.6363636363636362, | |
| "grad_norm": 4.39246129989624, | |
| "learning_rate": 2.5423728813559322e-05, | |
| "loss": 0.0239, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.6818181818181817, | |
| "grad_norm": 3.055365562438965, | |
| "learning_rate": 2.457627118644068e-05, | |
| "loss": 0.0268, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.7272727272727273, | |
| "grad_norm": 13.96273422241211, | |
| "learning_rate": 2.3728813559322036e-05, | |
| "loss": 0.0578, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.7727272727272727, | |
| "grad_norm": 2.8645408153533936, | |
| "learning_rate": 2.2881355932203392e-05, | |
| "loss": 0.0209, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.8181818181818183, | |
| "grad_norm": 1.836397647857666, | |
| "learning_rate": 2.2033898305084748e-05, | |
| "loss": 0.0236, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.8636363636363638, | |
| "grad_norm": 0.4018004834651947, | |
| "learning_rate": 2.1186440677966103e-05, | |
| "loss": 0.0107, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.9090909090909092, | |
| "grad_norm": 4.601925373077393, | |
| "learning_rate": 2.033898305084746e-05, | |
| "loss": 0.03, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.9545454545454546, | |
| "grad_norm": 48.49919128417969, | |
| "learning_rate": 1.9491525423728814e-05, | |
| "loss": 1.0566, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.6449614763259888, | |
| "learning_rate": 1.864406779661017e-05, | |
| "loss": 0.0057, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.813953488372093, | |
| "eval_f1_macro": 0.6898809523809524, | |
| "eval_f1_micro": 0.813953488372093, | |
| "eval_f1_weighted": 0.8011212624584718, | |
| "eval_loss": 0.6852538585662842, | |
| "eval_precision_macro": 0.8657513348588863, | |
| "eval_precision_micro": 0.813953488372093, | |
| "eval_precision_weighted": 0.85195040178809, | |
| "eval_recall_macro": 0.6858974358974358, | |
| "eval_recall_micro": 0.813953488372093, | |
| "eval_recall_weighted": 0.813953488372093, | |
| "eval_runtime": 8.2824, | |
| "eval_samples_per_second": 5.192, | |
| "eval_steps_per_second": 0.362, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.0454545454545454, | |
| "grad_norm": 49.31159973144531, | |
| "learning_rate": 1.7796610169491526e-05, | |
| "loss": 0.4487, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.090909090909091, | |
| "grad_norm": 5.494616985321045, | |
| "learning_rate": 1.694915254237288e-05, | |
| "loss": 0.0139, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.1363636363636362, | |
| "grad_norm": 4.503355979919434, | |
| "learning_rate": 1.6101694915254237e-05, | |
| "loss": 0.0236, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.1818181818181817, | |
| "grad_norm": 5.209221363067627, | |
| "learning_rate": 1.5254237288135596e-05, | |
| "loss": 0.0177, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.227272727272727, | |
| "grad_norm": 7.11909818649292, | |
| "learning_rate": 1.440677966101695e-05, | |
| "loss": 0.7101, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.2727272727272725, | |
| "grad_norm": 0.2786655128002167, | |
| "learning_rate": 1.3559322033898305e-05, | |
| "loss": 0.0055, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.3181818181818183, | |
| "grad_norm": 1.114147663116455, | |
| "learning_rate": 1.2711864406779661e-05, | |
| "loss": 0.0099, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 2.3636363636363638, | |
| "grad_norm": 0.2622224688529968, | |
| "learning_rate": 1.1864406779661018e-05, | |
| "loss": 0.0077, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.409090909090909, | |
| "grad_norm": 26.776103973388672, | |
| "learning_rate": 1.1016949152542374e-05, | |
| "loss": 0.0448, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.4545454545454546, | |
| "grad_norm": 0.48683127760887146, | |
| "learning_rate": 1.016949152542373e-05, | |
| "loss": 0.008, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 0.2846999764442444, | |
| "learning_rate": 9.322033898305085e-06, | |
| "loss": 0.0068, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.5454545454545454, | |
| "grad_norm": 9.395466804504395, | |
| "learning_rate": 8.47457627118644e-06, | |
| "loss": 0.0232, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.590909090909091, | |
| "grad_norm": 0.19868876039981842, | |
| "learning_rate": 7.627118644067798e-06, | |
| "loss": 0.0045, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.6363636363636362, | |
| "grad_norm": 0.4353472590446472, | |
| "learning_rate": 6.779661016949153e-06, | |
| "loss": 0.0069, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.6818181818181817, | |
| "grad_norm": 1.6797751188278198, | |
| "learning_rate": 5.932203389830509e-06, | |
| "loss": 0.0121, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.7272727272727275, | |
| "grad_norm": 0.7504879832267761, | |
| "learning_rate": 5.084745762711865e-06, | |
| "loss": 0.0079, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.7727272727272725, | |
| "grad_norm": 0.19052772223949432, | |
| "learning_rate": 4.23728813559322e-06, | |
| "loss": 0.0059, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.8181818181818183, | |
| "grad_norm": 1.1264681816101074, | |
| "learning_rate": 3.3898305084745763e-06, | |
| "loss": 0.0078, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.8636363636363638, | |
| "grad_norm": 0.4816828668117523, | |
| "learning_rate": 2.5423728813559323e-06, | |
| "loss": 0.005, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.909090909090909, | |
| "grad_norm": 0.21697530150413513, | |
| "learning_rate": 1.6949152542372882e-06, | |
| "loss": 0.005, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.9545454545454546, | |
| "grad_norm": 11.91680908203125, | |
| "learning_rate": 8.474576271186441e-07, | |
| "loss": 0.0207, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 5.379342079162598, | |
| "learning_rate": 0.0, | |
| "loss": 0.0206, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9302325581395349, | |
| "eval_f1_macro": 0.9078720022116249, | |
| "eval_f1_micro": 0.9302325581395349, | |
| "eval_f1_weighted": 0.9292296119852065, | |
| "eval_loss": 0.29650357365608215, | |
| "eval_precision_macro": 0.949667616334283, | |
| "eval_precision_micro": 0.9302325581395349, | |
| "eval_precision_weighted": 0.9319552110249785, | |
| "eval_recall_macro": 0.8782051282051282, | |
| "eval_recall_micro": 0.9302325581395349, | |
| "eval_recall_weighted": 0.9302325581395349, | |
| "eval_runtime": 9.0133, | |
| "eval_samples_per_second": 4.771, | |
| "eval_steps_per_second": 0.333, | |
| "step": 66 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 66, | |
| "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": 33349625697024.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |