| { | |
| "best_global_step": 590, | |
| "best_metric": 0.9585100412368774, | |
| "best_model_checkpoint": "./fine-tuned-model\\checkpoint-590", | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 590, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.847457627118644, | |
| "grad_norm": 2.3572731018066406, | |
| "learning_rate": 3.932203389830509e-05, | |
| "loss": 9.5716, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.5832620859146118, | |
| "eval_runtime": 5.4855, | |
| "eval_samples_per_second": 19.141, | |
| "eval_steps_per_second": 1.276, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 1.694915254237288, | |
| "grad_norm": 3.8656413555145264, | |
| "learning_rate": 3.8644067796610175e-05, | |
| "loss": 1.7466, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.1679714918136597, | |
| "eval_runtime": 5.364, | |
| "eval_samples_per_second": 19.575, | |
| "eval_steps_per_second": 1.305, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 2.542372881355932, | |
| "grad_norm": 2.582818031311035, | |
| "learning_rate": 3.796610169491526e-05, | |
| "loss": 1.5173, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.0937272310256958, | |
| "eval_runtime": 5.4735, | |
| "eval_samples_per_second": 19.183, | |
| "eval_steps_per_second": 1.279, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 3.389830508474576, | |
| "grad_norm": 0.9783422350883484, | |
| "learning_rate": 3.728813559322034e-05, | |
| "loss": 1.4233, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.0387905836105347, | |
| "eval_runtime": 5.354, | |
| "eval_samples_per_second": 19.612, | |
| "eval_steps_per_second": 1.307, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 4.237288135593221, | |
| "grad_norm": 0.6458675265312195, | |
| "learning_rate": 3.6610169491525426e-05, | |
| "loss": 1.3044, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 1.0661542415618896, | |
| "eval_runtime": 5.4235, | |
| "eval_samples_per_second": 19.36, | |
| "eval_steps_per_second": 1.291, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 5.084745762711864, | |
| "grad_norm": 1.3425668478012085, | |
| "learning_rate": 3.593220338983051e-05, | |
| "loss": 1.3608, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 5.932203389830509, | |
| "grad_norm": 1.331030011177063, | |
| "learning_rate": 3.52542372881356e-05, | |
| "loss": 1.2839, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.9894506335258484, | |
| "eval_runtime": 5.406, | |
| "eval_samples_per_second": 19.423, | |
| "eval_steps_per_second": 1.295, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 6.779661016949152, | |
| "grad_norm": 1.02914297580719, | |
| "learning_rate": 3.457627118644068e-05, | |
| "loss": 1.2485, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.9816469550132751, | |
| "eval_runtime": 5.4105, | |
| "eval_samples_per_second": 19.407, | |
| "eval_steps_per_second": 1.294, | |
| "step": 413 | |
| }, | |
| { | |
| "epoch": 7.627118644067797, | |
| "grad_norm": 1.8862000703811646, | |
| "learning_rate": 3.389830508474576e-05, | |
| "loss": 1.2426, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 1.0074799060821533, | |
| "eval_runtime": 5.423, | |
| "eval_samples_per_second": 19.362, | |
| "eval_steps_per_second": 1.291, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 8.474576271186441, | |
| "grad_norm": 0.9509351849555969, | |
| "learning_rate": 3.322033898305085e-05, | |
| "loss": 1.2903, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.9700178503990173, | |
| "eval_runtime": 5.388, | |
| "eval_samples_per_second": 19.488, | |
| "eval_steps_per_second": 1.299, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 9.322033898305085, | |
| "grad_norm": 1.861725926399231, | |
| "learning_rate": 3.2542372881355934e-05, | |
| "loss": 1.2588, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.9585100412368774, | |
| "eval_runtime": 5.409, | |
| "eval_samples_per_second": 19.412, | |
| "eval_steps_per_second": 1.294, | |
| "step": 590 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 2950, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 50, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "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": 1.86489122586624e+16, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |