| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.016612675471384668, |
| "eval_steps": 10, |
| "global_step": 50, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.00033225350942769335, |
| "eval_loss": 1.356743574142456, |
| "eval_runtime": 69.6151, |
| "eval_samples_per_second": 18.214, |
| "eval_steps_per_second": 9.107, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.0016612675471384666, |
| "grad_norm": 1.057161569595337, |
| "learning_rate": 5e-05, |
| "loss": 1.2723, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.003322535094276933, |
| "grad_norm": 1.0211741924285889, |
| "learning_rate": 0.0001, |
| "loss": 1.2354, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.003322535094276933, |
| "eval_loss": 1.090079426765442, |
| "eval_runtime": 69.432, |
| "eval_samples_per_second": 18.262, |
| "eval_steps_per_second": 9.131, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.0049838026414154, |
| "grad_norm": 1.071433424949646, |
| "learning_rate": 9.619397662556435e-05, |
| "loss": 1.0207, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.006645070188553866, |
| "grad_norm": 1.2155852317810059, |
| "learning_rate": 8.535533905932738e-05, |
| "loss": 0.873, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.006645070188553866, |
| "eval_loss": 0.8100319504737854, |
| "eval_runtime": 70.2598, |
| "eval_samples_per_second": 18.047, |
| "eval_steps_per_second": 9.024, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.008306337735692334, |
| "grad_norm": 1.0802018642425537, |
| "learning_rate": 6.91341716182545e-05, |
| "loss": 0.8331, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.0099676052828308, |
| "grad_norm": 0.9234360456466675, |
| "learning_rate": 5e-05, |
| "loss": 0.7435, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.0099676052828308, |
| "eval_loss": 0.7390913963317871, |
| "eval_runtime": 69.6251, |
| "eval_samples_per_second": 18.212, |
| "eval_steps_per_second": 9.106, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.011628872829969267, |
| "grad_norm": 0.9415158629417419, |
| "learning_rate": 3.086582838174551e-05, |
| "loss": 0.7966, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.013290140377107733, |
| "grad_norm": 0.9960245490074158, |
| "learning_rate": 1.4644660940672627e-05, |
| "loss": 0.755, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.013290140377107733, |
| "eval_loss": 0.7165237665176392, |
| "eval_runtime": 70.0285, |
| "eval_samples_per_second": 18.107, |
| "eval_steps_per_second": 9.053, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.0149514079242462, |
| "grad_norm": 0.8190529942512512, |
| "learning_rate": 3.8060233744356633e-06, |
| "loss": 0.7666, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.016612675471384668, |
| "grad_norm": 0.927686870098114, |
| "learning_rate": 0.0, |
| "loss": 0.7215, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.016612675471384668, |
| "eval_loss": 0.7126367688179016, |
| "eval_runtime": 69.167, |
| "eval_samples_per_second": 18.332, |
| "eval_steps_per_second": 9.166, |
| "step": 50 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 50, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 13, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2500486653542400.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
