| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.08688097306689835, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0017376194613379669, | |
| "eval_loss": 2.3447093963623047, | |
| "eval_runtime": 16.2614, | |
| "eval_samples_per_second": 14.943, | |
| "eval_steps_per_second": 7.502, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008688097306689836, | |
| "grad_norm": 0.824364960193634, | |
| "learning_rate": 5e-05, | |
| "loss": 2.2515, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01737619461337967, | |
| "grad_norm": 0.957850992679596, | |
| "learning_rate": 0.0001, | |
| "loss": 2.2288, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01737619461337967, | |
| "eval_loss": 2.035438299179077, | |
| "eval_runtime": 16.4926, | |
| "eval_samples_per_second": 14.734, | |
| "eval_steps_per_second": 7.397, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.026064291920069503, | |
| "grad_norm": 0.746576189994812, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.8945, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03475238922675934, | |
| "grad_norm": 0.7681987881660461, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.7169, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03475238922675934, | |
| "eval_loss": 1.6828279495239258, | |
| "eval_runtime": 16.6, | |
| "eval_samples_per_second": 14.639, | |
| "eval_steps_per_second": 7.349, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.043440486533449174, | |
| "grad_norm": 0.7900924682617188, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.7015, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.052128583840139006, | |
| "grad_norm": 0.7530582547187805, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6979, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.052128583840139006, | |
| "eval_loss": 1.5826479196548462, | |
| "eval_runtime": 16.9166, | |
| "eval_samples_per_second": 14.365, | |
| "eval_steps_per_second": 7.212, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.060816681146828845, | |
| "grad_norm": 0.6359474062919617, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.5325, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.06950477845351868, | |
| "grad_norm": 0.6465645432472229, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.5266, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06950477845351868, | |
| "eval_loss": 1.5528888702392578, | |
| "eval_runtime": 16.9993, | |
| "eval_samples_per_second": 14.295, | |
| "eval_steps_per_second": 7.177, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07819287576020852, | |
| "grad_norm": 0.5526885390281677, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.5525, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.08688097306689835, | |
| "grad_norm": 0.5791680812835693, | |
| "learning_rate": 0.0, | |
| "loss": 1.5404, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08688097306689835, | |
| "eval_loss": 1.5478538274765015, | |
| "eval_runtime": 16.5528, | |
| "eval_samples_per_second": 14.68, | |
| "eval_steps_per_second": 7.37, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9598568528609280.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |