| { | |
| "best_metric": 0.1553138643503189, | |
| "best_model_checkpoint": "speech-multiclassifier-run-2/checkpoint-6384", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 9576, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.15664160401002505, | |
| "grad_norm": 11.20281982421875, | |
| "learning_rate": 1.8955722639933167e-05, | |
| "loss": 0.1599, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.3132832080200501, | |
| "grad_norm": 16.948055267333984, | |
| "learning_rate": 1.7911445279866332e-05, | |
| "loss": 0.2132, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.4699248120300752, | |
| "grad_norm": 15.359735488891602, | |
| "learning_rate": 1.68671679197995e-05, | |
| "loss": 0.2101, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.6265664160401002, | |
| "grad_norm": 0.13909225165843964, | |
| "learning_rate": 1.5822890559732666e-05, | |
| "loss": 0.1868, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.7832080200501254, | |
| "grad_norm": 1.7620573043823242, | |
| "learning_rate": 1.4778613199665832e-05, | |
| "loss": 0.1824, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.9398496240601504, | |
| "grad_norm": 2.3290231227874756, | |
| "learning_rate": 1.3734335839598997e-05, | |
| "loss": 0.1678, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.15620405972003937, | |
| "eval_overall-accuracy": 0.9531360112755461, | |
| "eval_overall-f1": 0.9531360112755461, | |
| "eval_overall-precision": 0.9531360112755461, | |
| "eval_overall-recall": 0.9531360112755461, | |
| "eval_runtime": 5.7139, | |
| "eval_samples_per_second": 496.687, | |
| "eval_steps_per_second": 31.152, | |
| "step": 3192 | |
| }, | |
| { | |
| "epoch": 1.0964912280701755, | |
| "grad_norm": 0.4430443048477173, | |
| "learning_rate": 1.2690058479532166e-05, | |
| "loss": 0.1655, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.2531328320802004, | |
| "grad_norm": 5.565830707550049, | |
| "learning_rate": 1.1645781119465331e-05, | |
| "loss": 0.1499, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.4097744360902256, | |
| "grad_norm": 0.9018378257751465, | |
| "learning_rate": 1.0601503759398497e-05, | |
| "loss": 0.1443, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.5664160401002505, | |
| "grad_norm": 0.3591144382953644, | |
| "learning_rate": 9.557226399331662e-06, | |
| "loss": 0.1399, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.7230576441102756, | |
| "grad_norm": 0.4499484598636627, | |
| "learning_rate": 8.512949039264829e-06, | |
| "loss": 0.1559, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.8796992481203008, | |
| "grad_norm": 8.649208068847656, | |
| "learning_rate": 7.468671679197995e-06, | |
| "loss": 0.1522, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.1553138643503189, | |
| "eval_overall-accuracy": 0.9531360112755461, | |
| "eval_overall-f1": 0.9531360112755461, | |
| "eval_overall-precision": 0.9531360112755461, | |
| "eval_overall-recall": 0.9531360112755461, | |
| "eval_runtime": 5.7234, | |
| "eval_samples_per_second": 495.858, | |
| "eval_steps_per_second": 31.1, | |
| "step": 6384 | |
| }, | |
| { | |
| "epoch": 2.036340852130326, | |
| "grad_norm": 1.2995306253433228, | |
| "learning_rate": 6.424394319131162e-06, | |
| "loss": 0.1398, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 2.192982456140351, | |
| "grad_norm": 0.18944260478019714, | |
| "learning_rate": 5.380116959064328e-06, | |
| "loss": 0.1164, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.3496240601503757, | |
| "grad_norm": 4.408690929412842, | |
| "learning_rate": 4.335839598997494e-06, | |
| "loss": 0.1154, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 2.506265664160401, | |
| "grad_norm": 0.7239732146263123, | |
| "learning_rate": 3.29156223893066e-06, | |
| "loss": 0.1208, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.662907268170426, | |
| "grad_norm": 6.512196063995361, | |
| "learning_rate": 2.2472848788638263e-06, | |
| "loss": 0.1115, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 2.819548872180451, | |
| "grad_norm": 1.97010338306427, | |
| "learning_rate": 1.2030075187969925e-06, | |
| "loss": 0.1169, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 2.9761904761904763, | |
| "grad_norm": 1.1876590251922607, | |
| "learning_rate": 1.5873015873015874e-07, | |
| "loss": 0.1157, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.16947361826896667, | |
| "eval_overall-accuracy": 0.9534883720930233, | |
| "eval_overall-f1": 0.9534883720930233, | |
| "eval_overall-precision": 0.9534883720930233, | |
| "eval_overall-recall": 0.9534883720930233, | |
| "eval_runtime": 5.6944, | |
| "eval_samples_per_second": 498.388, | |
| "eval_steps_per_second": 31.259, | |
| "step": 9576 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 9576, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2641161396896352.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |