| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.18248175182481752, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0036496350364963502, | |
| "eval_loss": 2.616699695587158, | |
| "eval_runtime": 6.3179, | |
| "eval_samples_per_second": 18.361, | |
| "eval_steps_per_second": 9.18, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01824817518248175, | |
| "grad_norm": 1.6743769645690918, | |
| "learning_rate": 5e-05, | |
| "loss": 2.5534, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0364963503649635, | |
| "grad_norm": 1.8287861347198486, | |
| "learning_rate": 0.0001, | |
| "loss": 2.3519, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0364963503649635, | |
| "eval_loss": 2.002800464630127, | |
| "eval_runtime": 6.3103, | |
| "eval_samples_per_second": 18.383, | |
| "eval_steps_per_second": 9.191, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05474452554744526, | |
| "grad_norm": 2.0079925060272217, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.7359, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.072992700729927, | |
| "grad_norm": 2.5511863231658936, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.1344, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.072992700729927, | |
| "eval_loss": 0.8217958807945251, | |
| "eval_runtime": 6.4298, | |
| "eval_samples_per_second": 18.041, | |
| "eval_steps_per_second": 9.021, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09124087591240876, | |
| "grad_norm": 2.521385908126831, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.6589, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.10948905109489052, | |
| "grad_norm": 2.6327896118164062, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3088, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.10948905109489052, | |
| "eval_loss": 0.17604775726795197, | |
| "eval_runtime": 6.5101, | |
| "eval_samples_per_second": 17.818, | |
| "eval_steps_per_second": 8.909, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.12773722627737227, | |
| "grad_norm": 2.246385335922241, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.1334, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.145985401459854, | |
| "grad_norm": 1.123745322227478, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.064, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.145985401459854, | |
| "eval_loss": 0.043108660727739334, | |
| "eval_runtime": 6.4968, | |
| "eval_samples_per_second": 17.855, | |
| "eval_steps_per_second": 8.927, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.16423357664233576, | |
| "grad_norm": 1.209367036819458, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0385, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.18248175182481752, | |
| "grad_norm": 0.65992271900177, | |
| "learning_rate": 0.0, | |
| "loss": 0.0407, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.18248175182481752, | |
| "eval_loss": 0.03230349346995354, | |
| "eval_runtime": 6.4146, | |
| "eval_samples_per_second": 18.084, | |
| "eval_steps_per_second": 9.042, | |
| "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": 2500486653542400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |