| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.012472715933894606, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0012472715933894605, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 11.206, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012472715933894605, | |
| "eval_loss": NaN, | |
| "eval_runtime": 187.4786, | |
| "eval_samples_per_second": 7.206, | |
| "eval_steps_per_second": 3.606, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002494543186778921, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 97.2073, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0037418147801683817, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0037418147801683817, | |
| "eval_loss": NaN, | |
| "eval_runtime": 47.0016, | |
| "eval_samples_per_second": 28.744, | |
| "eval_steps_per_second": 14.383, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004989086373557842, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 706.5162, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006236357966947303, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007483629560336763, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 45.5588, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.007483629560336763, | |
| "eval_loss": NaN, | |
| "eval_runtime": 47.1149, | |
| "eval_samples_per_second": 28.675, | |
| "eval_steps_per_second": 14.348, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008730901153726224, | |
| "grad_norm": NaN, | |
| "learning_rate": 7e-05, | |
| "loss": 0.558, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.009978172747115684, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.1006, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.011225444340505144, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 22.9263, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.011225444340505144, | |
| "eval_loss": NaN, | |
| "eval_runtime": 47.083, | |
| "eval_samples_per_second": 28.694, | |
| "eval_steps_per_second": 14.358, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.012472715933894606, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.0954192453632e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |