| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.007736943907156673, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007736943907156673, | |
| "grad_norm": 1.6751151084899902, | |
| "learning_rate": 2e-05, | |
| "loss": 1.3016, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007736943907156673, | |
| "eval_loss": 1.2708077430725098, | |
| "eval_runtime": 22.4998, | |
| "eval_samples_per_second": 24.222, | |
| "eval_steps_per_second": 12.133, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015473887814313346, | |
| "grad_norm": 1.636838436126709, | |
| "learning_rate": 4e-05, | |
| "loss": 1.214, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0023210831721470018, | |
| "grad_norm": 1.4468919038772583, | |
| "learning_rate": 6e-05, | |
| "loss": 1.2064, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0023210831721470018, | |
| "eval_loss": 1.2574771642684937, | |
| "eval_runtime": 21.1112, | |
| "eval_samples_per_second": 25.816, | |
| "eval_steps_per_second": 12.932, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003094777562862669, | |
| "grad_norm": 1.5880744457244873, | |
| "learning_rate": 8e-05, | |
| "loss": 1.1794, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0038684719535783366, | |
| "grad_norm": 1.645495057106018, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1836, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0046421663442940036, | |
| "grad_norm": 1.5173259973526, | |
| "learning_rate": 0.00012, | |
| "loss": 1.1605, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0046421663442940036, | |
| "eval_loss": 1.088241696357727, | |
| "eval_runtime": 21.4613, | |
| "eval_samples_per_second": 25.395, | |
| "eval_steps_per_second": 12.721, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005415860735009671, | |
| "grad_norm": 1.8041791915893555, | |
| "learning_rate": 0.00014, | |
| "loss": 1.0979, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006189555125725338, | |
| "grad_norm": 1.5532431602478027, | |
| "learning_rate": 0.00016, | |
| "loss": 1.0294, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.006963249516441006, | |
| "grad_norm": 1.7013477087020874, | |
| "learning_rate": 0.00018, | |
| "loss": 1.0275, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006963249516441006, | |
| "eval_loss": 0.9031235575675964, | |
| "eval_runtime": 21.5551, | |
| "eval_samples_per_second": 25.284, | |
| "eval_steps_per_second": 12.665, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007736943907156673, | |
| "grad_norm": 1.476885437965393, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9226, | |
| "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": 2112182707814400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |