| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0007800920508620017, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.800920508620017e-05, | |
| "grad_norm": 0.7295346856117249, | |
| "learning_rate": 2e-05, | |
| "loss": 2.2709, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.800920508620017e-05, | |
| "eval_loss": 2.206843376159668, | |
| "eval_runtime": 92.9432, | |
| "eval_samples_per_second": 58.078, | |
| "eval_steps_per_second": 29.039, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00015601841017240034, | |
| "grad_norm": 0.6880191564559937, | |
| "learning_rate": 4e-05, | |
| "loss": 2.5445, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0002340276152586005, | |
| "grad_norm": 0.48536598682403564, | |
| "learning_rate": 6e-05, | |
| "loss": 1.8952, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0002340276152586005, | |
| "eval_loss": 2.201993465423584, | |
| "eval_runtime": 92.0811, | |
| "eval_samples_per_second": 58.622, | |
| "eval_steps_per_second": 29.311, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0003120368203448007, | |
| "grad_norm": 0.6902179718017578, | |
| "learning_rate": 8e-05, | |
| "loss": 1.8569, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00039004602543100085, | |
| "grad_norm": 0.747987687587738, | |
| "learning_rate": 0.0001, | |
| "loss": 2.222, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.000468055230517201, | |
| "grad_norm": 0.8904348611831665, | |
| "learning_rate": 0.00012, | |
| "loss": 2.6302, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.000468055230517201, | |
| "eval_loss": 2.131985902786255, | |
| "eval_runtime": 92.1045, | |
| "eval_samples_per_second": 58.607, | |
| "eval_steps_per_second": 29.304, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005460644356034012, | |
| "grad_norm": 0.7404212951660156, | |
| "learning_rate": 0.00014, | |
| "loss": 1.7543, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0006240736406896014, | |
| "grad_norm": 1.000349760055542, | |
| "learning_rate": 0.00016, | |
| "loss": 2.1701, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0007020828457758015, | |
| "grad_norm": 0.6752015352249146, | |
| "learning_rate": 0.00018, | |
| "loss": 2.0607, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0007020828457758015, | |
| "eval_loss": 1.8826178312301636, | |
| "eval_runtime": 91.3973, | |
| "eval_samples_per_second": 59.061, | |
| "eval_steps_per_second": 29.53, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0007800920508620017, | |
| "grad_norm": 0.7087355852127075, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9307, | |
| "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": 340750063632384.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |