| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.024906600249066, |
| "eval_steps": 500, |
| "global_step": 20, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0, |
| "learning_rate": 2e-05, |
| "loss": 6.0767, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.0, |
| "learning_rate": 4e-05, |
| "loss": 6.1955, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.0, |
| "learning_rate": 6e-05, |
| "loss": 5.9645, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.0, |
| "learning_rate": 8e-05, |
| "loss": 5.6433, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.01, |
| "learning_rate": 0.0001, |
| "loss": 5.1777, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.01, |
| "learning_rate": 0.00012, |
| "loss": 4.982, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.01, |
| "learning_rate": 0.00014, |
| "loss": 4.4334, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.01, |
| "learning_rate": 0.00016, |
| "loss": 4.3696, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.01, |
| "learning_rate": 0.00018, |
| "loss": 4.227, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.01, |
| "learning_rate": 0.0002, |
| "loss": 4.3615, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.01, |
| "learning_rate": 0.00019510565162951537, |
| "loss": 4.3648, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.01, |
| "learning_rate": 0.00018090169943749476, |
| "loss": 4.0145, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.02, |
| "learning_rate": 0.00018090169943749476, |
| "loss": 4.1974, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.02, |
| "learning_rate": 0.00015877852522924732, |
| "loss": 4.0787, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.02, |
| "learning_rate": 0.00013090169943749476, |
| "loss": 4.0417, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.02, |
| "learning_rate": 0.0001, |
| "loss": 3.8075, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.02, |
| "learning_rate": 6.909830056250527e-05, |
| "loss": 3.9956, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.02, |
| "learning_rate": 4.12214747707527e-05, |
| "loss": 3.962, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.02, |
| "learning_rate": 1.9098300562505266e-05, |
| "loss": 3.8126, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.02, |
| "learning_rate": 1.9098300562505266e-05, |
| "loss": 3.9112, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.02, |
| "eval_loss": 2.6100547313690186, |
| "eval_runtime": 5.613, |
| "eval_samples_per_second": 463.21, |
| "eval_steps_per_second": 463.21, |
| "step": 20 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 20, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 500, |
| "total_flos": 994574063370240.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
