| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0016524828554903743, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.3049657109807487e-05, | |
| "eval_loss": 1.1126134395599365, | |
| "eval_runtime": 2015.562, | |
| "eval_samples_per_second": 6.321, | |
| "eval_steps_per_second": 3.16, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00016524828554903743, | |
| "grad_norm": 0.21275891363620758, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9941, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00033049657109807487, | |
| "grad_norm": 0.29368552565574646, | |
| "learning_rate": 0.0001, | |
| "loss": 0.9738, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00033049657109807487, | |
| "eval_loss": 1.0696473121643066, | |
| "eval_runtime": 2048.2336, | |
| "eval_samples_per_second": 6.22, | |
| "eval_steps_per_second": 3.11, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0004957448566471123, | |
| "grad_norm": 0.33622804284095764, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.018, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0006609931421961497, | |
| "grad_norm": 0.374787837266922, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.9683, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0006609931421961497, | |
| "eval_loss": 0.9721865057945251, | |
| "eval_runtime": 2046.2259, | |
| "eval_samples_per_second": 6.226, | |
| "eval_steps_per_second": 3.113, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0008262414277451872, | |
| "grad_norm": 0.4773717522621155, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.9747, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0009914897132942246, | |
| "grad_norm": 0.3675839304924011, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9272, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0009914897132942246, | |
| "eval_loss": 0.9233540296554565, | |
| "eval_runtime": 2045.7232, | |
| "eval_samples_per_second": 6.228, | |
| "eval_steps_per_second": 3.114, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.001156737998843262, | |
| "grad_norm": 0.40750598907470703, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.9225, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0013219862843922995, | |
| "grad_norm": 0.3466489315032959, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.8495, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0013219862843922995, | |
| "eval_loss": 0.9025662541389465, | |
| "eval_runtime": 2044.9468, | |
| "eval_samples_per_second": 6.23, | |
| "eval_steps_per_second": 3.115, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0014872345699413368, | |
| "grad_norm": 0.3929550349712372, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.899, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0016524828554903743, | |
| "grad_norm": 0.3898150622844696, | |
| "learning_rate": 0.0, | |
| "loss": 0.8792, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0016524828554903743, | |
| "eval_loss": 0.8988497257232666, | |
| "eval_runtime": 2042.8113, | |
| "eval_samples_per_second": 6.237, | |
| "eval_steps_per_second": 3.118, | |
| "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": 1.6246613030731776e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |