| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 48, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.32786885245901637, |
| "grad_norm": 2.208583354949951, |
| "learning_rate": 8e-05, |
| "loss": 1.5554590225219727, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.6557377049180327, |
| "grad_norm": 0.7603749632835388, |
| "learning_rate": 0.00018, |
| "loss": 0.9338971138000488, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.9836065573770492, |
| "grad_norm": 0.6266924142837524, |
| "learning_rate": 0.00019458172417006347, |
| "loss": 0.7913335800170899, |
| "step": 15 |
| }, |
| { |
| "epoch": 1.2622950819672132, |
| "grad_norm": 0.6399636268615723, |
| "learning_rate": 0.00017357239106731317, |
| "loss": 0.6818179607391357, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.5901639344262295, |
| "grad_norm": 0.5579779148101807, |
| "learning_rate": 0.00014016954246529696, |
| "loss": 0.6158201217651367, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.918032786885246, |
| "grad_norm": 0.5490267872810364, |
| "learning_rate": 0.0001, |
| "loss": 0.6146406650543212, |
| "step": 30 |
| }, |
| { |
| "epoch": 2.19672131147541, |
| "grad_norm": 0.4960053861141205, |
| "learning_rate": 5.983045753470308e-05, |
| "loss": 0.4959586143493652, |
| "step": 35 |
| }, |
| { |
| "epoch": 2.5245901639344264, |
| "grad_norm": 0.5879160761833191, |
| "learning_rate": 2.6427608932686843e-05, |
| "loss": 0.4384322166442871, |
| "step": 40 |
| }, |
| { |
| "epoch": 2.8524590163934427, |
| "grad_norm": 0.6677722930908203, |
| "learning_rate": 5.418275829936537e-06, |
| "loss": 0.4373603343963623, |
| "step": 45 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 48, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 50, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3.4454307337712666e+17, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
