| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00030844205915918696, | |
| "eval_steps": 2, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.0844205915918693e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.0844205915918693e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 468.8432, | |
| "eval_samples_per_second": 29.116, | |
| "eval_steps_per_second": 14.559, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.168841183183739e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 6.168841183183739e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 467.4001, | |
| "eval_samples_per_second": 29.206, | |
| "eval_steps_per_second": 14.604, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 9.253261774775608e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00012337682366367477, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00012337682366367477, | |
| "eval_loss": NaN, | |
| "eval_runtime": 467.7941, | |
| "eval_samples_per_second": 29.182, | |
| "eval_steps_per_second": 14.592, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00015422102957959348, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00018506523549551216, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00018506523549551216, | |
| "eval_loss": NaN, | |
| "eval_runtime": 467.5617, | |
| "eval_samples_per_second": 29.196, | |
| "eval_steps_per_second": 14.599, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00021590944141143087, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00024675364732734955, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00024675364732734955, | |
| "eval_loss": NaN, | |
| "eval_runtime": 467.3563, | |
| "eval_samples_per_second": 29.209, | |
| "eval_steps_per_second": 14.606, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0002775978532432682, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00030844205915918696, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00030844205915918696, | |
| "eval_loss": NaN, | |
| "eval_runtime": 467.3596, | |
| "eval_samples_per_second": 29.209, | |
| "eval_steps_per_second": 14.605, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 20, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1023167913000960.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |