| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.013647219379051518, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001364721937905152, | |
| "grad_norm": 0.7194808721542358, | |
| "learning_rate": 2e-05, | |
| "loss": 1.2026, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001364721937905152, | |
| "eval_loss": 1.1820653676986694, | |
| "eval_runtime": 16.1588, | |
| "eval_samples_per_second": 19.123, | |
| "eval_steps_per_second": 9.592, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002729443875810304, | |
| "grad_norm": 0.6754392981529236, | |
| "learning_rate": 4e-05, | |
| "loss": 1.1711, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0040941658137154556, | |
| "grad_norm": 0.5344181060791016, | |
| "learning_rate": 6e-05, | |
| "loss": 1.0059, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0040941658137154556, | |
| "eval_loss": 1.1797362565994263, | |
| "eval_runtime": 14.7484, | |
| "eval_samples_per_second": 20.951, | |
| "eval_steps_per_second": 10.51, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005458887751620608, | |
| "grad_norm": 0.5185796022415161, | |
| "learning_rate": 8e-05, | |
| "loss": 1.1393, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006823609689525759, | |
| "grad_norm": 0.5814789533615112, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0876, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008188331627430911, | |
| "grad_norm": 0.6432326436042786, | |
| "learning_rate": 0.00012, | |
| "loss": 1.1491, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008188331627430911, | |
| "eval_loss": 1.1488300561904907, | |
| "eval_runtime": 14.7947, | |
| "eval_samples_per_second": 20.886, | |
| "eval_steps_per_second": 10.477, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009553053565336063, | |
| "grad_norm": 0.775752604007721, | |
| "learning_rate": 0.00014, | |
| "loss": 1.0951, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.010917775503241215, | |
| "grad_norm": 0.8913566470146179, | |
| "learning_rate": 0.00016, | |
| "loss": 1.084, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.012282497441146366, | |
| "grad_norm": 1.0514389276504517, | |
| "learning_rate": 0.00018, | |
| "loss": 0.9316, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.012282497441146366, | |
| "eval_loss": 0.9948333501815796, | |
| "eval_runtime": 14.7782, | |
| "eval_samples_per_second": 20.909, | |
| "eval_steps_per_second": 10.488, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.013647219379051518, | |
| "grad_norm": 1.0197826623916626, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9454, | |
| "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": 3166205430988800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |