| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0396039603960396, | |
| "eval_steps": 4, | |
| "global_step": 13, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07920792079207921, | |
| "grad_norm": 0.34757035970687866, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4936, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07920792079207921, | |
| "eval_loss": 0.5106021165847778, | |
| "eval_runtime": 6.3959, | |
| "eval_samples_per_second": 13.446, | |
| "eval_steps_per_second": 3.44, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.15841584158415842, | |
| "grad_norm": 0.3403119444847107, | |
| "learning_rate": 0.0001, | |
| "loss": 0.4952, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.2376237623762376, | |
| "grad_norm": 0.34800511598587036, | |
| "learning_rate": 9.797464868072488e-05, | |
| "loss": 0.4808, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.31683168316831684, | |
| "grad_norm": 0.3258466422557831, | |
| "learning_rate": 9.206267664155907e-05, | |
| "loss": 0.4481, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.31683168316831684, | |
| "eval_loss": 0.4298471510410309, | |
| "eval_runtime": 5.7098, | |
| "eval_samples_per_second": 15.062, | |
| "eval_steps_per_second": 3.853, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.39603960396039606, | |
| "grad_norm": 0.3400859534740448, | |
| "learning_rate": 8.274303669726426e-05, | |
| "loss": 0.4216, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.4752475247524752, | |
| "grad_norm": 0.32469430565834045, | |
| "learning_rate": 7.077075065009433e-05, | |
| "loss": 0.3775, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.5544554455445545, | |
| "grad_norm": 0.26995933055877686, | |
| "learning_rate": 5.7115741913664264e-05, | |
| "loss": 0.3423, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.6336633663366337, | |
| "grad_norm": 0.23887252807617188, | |
| "learning_rate": 4.288425808633575e-05, | |
| "loss": 0.3298, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.6336633663366337, | |
| "eval_loss": 0.3099712133407593, | |
| "eval_runtime": 5.7212, | |
| "eval_samples_per_second": 15.032, | |
| "eval_steps_per_second": 3.845, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.7128712871287128, | |
| "grad_norm": 0.22783613204956055, | |
| "learning_rate": 2.9229249349905684e-05, | |
| "loss": 0.3106, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.7920792079207921, | |
| "grad_norm": 0.20739153027534485, | |
| "learning_rate": 1.725696330273575e-05, | |
| "loss": 0.3008, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.8712871287128713, | |
| "grad_norm": 0.22219590842723846, | |
| "learning_rate": 7.937323358440935e-06, | |
| "loss": 0.2989, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.9504950495049505, | |
| "grad_norm": 0.2131638526916504, | |
| "learning_rate": 2.0253513192751373e-06, | |
| "loss": 0.3036, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.9504950495049505, | |
| "eval_loss": 0.2834540605545044, | |
| "eval_runtime": 5.7133, | |
| "eval_samples_per_second": 15.053, | |
| "eval_steps_per_second": 3.851, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.0396039603960396, | |
| "grad_norm": 0.3245333433151245, | |
| "learning_rate": 0.0, | |
| "loss": 0.4369, | |
| "step": 13 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 13, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 4, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.1524843048534016e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |