| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.007417022065640645, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001483404413128129, | |
| "eval_loss": 5.5551042556762695, | |
| "eval_runtime": 134.6243, | |
| "eval_samples_per_second": 21.088, | |
| "eval_steps_per_second": 10.548, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007417022065640646, | |
| "grad_norm": 3.0284314155578613, | |
| "learning_rate": 5e-05, | |
| "loss": 5.1473, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0014834044131281292, | |
| "grad_norm": 2.8576478958129883, | |
| "learning_rate": 0.0001, | |
| "loss": 5.0422, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0014834044131281292, | |
| "eval_loss": 4.795658588409424, | |
| "eval_runtime": 132.4154, | |
| "eval_samples_per_second": 21.44, | |
| "eval_steps_per_second": 10.724, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0022251066196921935, | |
| "grad_norm": 2.446176052093506, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 4.2258, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0029668088262562583, | |
| "grad_norm": 2.810636281967163, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.9644, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0029668088262562583, | |
| "eval_loss": 3.6202757358551025, | |
| "eval_runtime": 133.5547, | |
| "eval_samples_per_second": 21.257, | |
| "eval_steps_per_second": 10.632, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0037085110328203227, | |
| "grad_norm": 4.14141321182251, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 3.5472, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004450213239384387, | |
| "grad_norm": 1.9365577697753906, | |
| "learning_rate": 5e-05, | |
| "loss": 3.3109, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004450213239384387, | |
| "eval_loss": 3.4258081912994385, | |
| "eval_runtime": 135.51, | |
| "eval_samples_per_second": 20.95, | |
| "eval_steps_per_second": 10.479, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005191915445948452, | |
| "grad_norm": 2.385741949081421, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 3.4774, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.005933617652512517, | |
| "grad_norm": 2.2971627712249756, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 3.0747, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.005933617652512517, | |
| "eval_loss": 3.355607271194458, | |
| "eval_runtime": 134.4867, | |
| "eval_samples_per_second": 21.11, | |
| "eval_steps_per_second": 10.559, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.006675319859076581, | |
| "grad_norm": 2.196897506713867, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 3.3445, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.007417022065640645, | |
| "grad_norm": 2.1248486042022705, | |
| "learning_rate": 0.0, | |
| "loss": 3.2248, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.007417022065640645, | |
| "eval_loss": 3.3501813411712646, | |
| "eval_runtime": 134.0762, | |
| "eval_samples_per_second": 21.175, | |
| "eval_steps_per_second": 10.591, | |
| "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": 3428033180467200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |