| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00016525784355039951, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.652578435503995e-05, | |
| "grad_norm": 1.5325522422790527, | |
| "learning_rate": 2e-05, | |
| "loss": 7.6901, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.652578435503995e-05, | |
| "eval_loss": 1.7071666717529297, | |
| "eval_runtime": 704.7663, | |
| "eval_samples_per_second": 36.152, | |
| "eval_steps_per_second": 18.077, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.30515687100799e-05, | |
| "grad_norm": 1.5695886611938477, | |
| "learning_rate": 4e-05, | |
| "loss": 8.3603, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 4.9577353065119854e-05, | |
| "grad_norm": 1.352525234222412, | |
| "learning_rate": 6e-05, | |
| "loss": 9.0301, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 4.9577353065119854e-05, | |
| "eval_loss": 1.706839919090271, | |
| "eval_runtime": 703.2411, | |
| "eval_samples_per_second": 36.231, | |
| "eval_steps_per_second": 18.116, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 6.61031374201598e-05, | |
| "grad_norm": 1.8064419031143188, | |
| "learning_rate": 8e-05, | |
| "loss": 7.9126, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 8.262892177519976e-05, | |
| "grad_norm": 2.013528347015381, | |
| "learning_rate": 0.0001, | |
| "loss": 8.5008, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 9.915470613023971e-05, | |
| "grad_norm": 1.589239478111267, | |
| "learning_rate": 0.00012, | |
| "loss": 7.1621, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 9.915470613023971e-05, | |
| "eval_loss": 1.6744303703308105, | |
| "eval_runtime": 705.3008, | |
| "eval_samples_per_second": 36.125, | |
| "eval_steps_per_second": 18.063, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00011568049048527966, | |
| "grad_norm": 2.3604519367218018, | |
| "learning_rate": 0.00014, | |
| "loss": 6.671, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0001322062748403196, | |
| "grad_norm": 3.248727798461914, | |
| "learning_rate": 0.00016, | |
| "loss": 6.5912, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00014873205919535955, | |
| "grad_norm": 4.850676536560059, | |
| "learning_rate": 0.00018, | |
| "loss": 6.5274, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00014873205919535955, | |
| "eval_loss": 1.4685440063476562, | |
| "eval_runtime": 704.7233, | |
| "eval_samples_per_second": 36.155, | |
| "eval_steps_per_second": 18.078, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00016525784355039951, | |
| "grad_norm": 5.651578426361084, | |
| "learning_rate": 0.0002, | |
| "loss": 7.4108, | |
| "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": 1632478030725120.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |