| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0003649035742305096, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.649035742305096e-05, | |
| "grad_norm": 1.0238981246948242, | |
| "learning_rate": 2e-05, | |
| "loss": 1.7931, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.649035742305096e-05, | |
| "eval_loss": 1.98862886428833, | |
| "eval_runtime": 701.2135, | |
| "eval_samples_per_second": 16.456, | |
| "eval_steps_per_second": 8.229, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.298071484610192e-05, | |
| "grad_norm": 1.4650105237960815, | |
| "learning_rate": 4e-05, | |
| "loss": 2.2947, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00010947107226915287, | |
| "grad_norm": 1.2507858276367188, | |
| "learning_rate": 6e-05, | |
| "loss": 2.2756, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00010947107226915287, | |
| "eval_loss": 1.979144811630249, | |
| "eval_runtime": 483.2723, | |
| "eval_samples_per_second": 23.877, | |
| "eval_steps_per_second": 11.939, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00014596142969220384, | |
| "grad_norm": 0.9717092514038086, | |
| "learning_rate": 8e-05, | |
| "loss": 1.7241, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0001824517871152548, | |
| "grad_norm": 1.0161713361740112, | |
| "learning_rate": 0.0001, | |
| "loss": 1.7689, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00021894214453830574, | |
| "grad_norm": 0.9307000637054443, | |
| "learning_rate": 0.00012, | |
| "loss": 1.6985, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00021894214453830574, | |
| "eval_loss": 1.840909719467163, | |
| "eval_runtime": 757.7667, | |
| "eval_samples_per_second": 15.228, | |
| "eval_steps_per_second": 7.614, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0002554325019613567, | |
| "grad_norm": 1.9005385637283325, | |
| "learning_rate": 0.00014, | |
| "loss": 1.9594, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00029192285938440767, | |
| "grad_norm": 1.6968870162963867, | |
| "learning_rate": 0.00016, | |
| "loss": 1.7966, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00032841321680745865, | |
| "grad_norm": 0.9660829901695251, | |
| "learning_rate": 0.00018, | |
| "loss": 1.7219, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00032841321680745865, | |
| "eval_loss": 1.6114068031311035, | |
| "eval_runtime": 751.3421, | |
| "eval_samples_per_second": 15.358, | |
| "eval_steps_per_second": 7.68, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0003649035742305096, | |
| "grad_norm": 1.4515999555587769, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7739, | |
| "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": 2164987275509760.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |