| { | |
| "best_metric": 1.0, | |
| "best_model_checkpoint": "DazMashaly/output/checkpoint-409", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 409, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.061124694376528114, | |
| "grad_norm": 1.064210295677185, | |
| "learning_rate": 5.000000000000001e-07, | |
| "loss": 6.0673, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.12224938875305623, | |
| "grad_norm": 0.982063889503479, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 6.0659, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.18337408312958436, | |
| "grad_norm": 0.9887572526931763, | |
| "learning_rate": 1.5e-06, | |
| "loss": 6.069, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.24449877750611246, | |
| "grad_norm": 1.076440691947937, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 6.0588, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3056234718826406, | |
| "grad_norm": 1.1176767349243164, | |
| "learning_rate": 2.5e-06, | |
| "loss": 6.0642, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.36674816625916873, | |
| "grad_norm": 1.0234830379486084, | |
| "learning_rate": 3e-06, | |
| "loss": 6.0708, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.4278728606356968, | |
| "grad_norm": 1.090944528579712, | |
| "learning_rate": 3.5e-06, | |
| "loss": 6.0339, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.4889975550122249, | |
| "grad_norm": 1.1804206371307373, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 6.0542, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5501222493887531, | |
| "grad_norm": 1.3007625341415405, | |
| "learning_rate": 4.5e-06, | |
| "loss": 6.0549, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.6112469437652812, | |
| "grad_norm": 1.2753345966339111, | |
| "learning_rate": 5e-06, | |
| "loss": 6.0535, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.6723716381418093, | |
| "grad_norm": 1.321979284286499, | |
| "learning_rate": 5.500000000000001e-06, | |
| "loss": 6.0401, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.7334963325183375, | |
| "grad_norm": 1.1843823194503784, | |
| "learning_rate": 6e-06, | |
| "loss": 6.0463, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7946210268948656, | |
| "grad_norm": 1.2534185647964478, | |
| "learning_rate": 6.5000000000000004e-06, | |
| "loss": 6.0248, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.8557457212713936, | |
| "grad_norm": 1.2556980848312378, | |
| "learning_rate": 7e-06, | |
| "loss": 6.045, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.9168704156479217, | |
| "grad_norm": 1.263355016708374, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 6.034, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.9779951100244498, | |
| "grad_norm": 1.1825202703475952, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 5.9866, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_cer": 1.0, | |
| "eval_loss": 5.615485191345215, | |
| "eval_runtime": 703.3832, | |
| "eval_samples_per_second": 3.126, | |
| "eval_steps_per_second": 0.026, | |
| "eval_wer": 1.0, | |
| "step": 409 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 8180, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 20, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.2893747052544e+18, | |
| "train_batch_size": 124, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |