| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.0013505209634616553, |
| "eval_steps": 10, |
| "global_step": 50, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 2.7010419269233105e-05, |
| "eval_loss": 3.10772442817688, |
| "eval_runtime": 1187.1961, |
| "eval_samples_per_second": 13.131, |
| "eval_steps_per_second": 6.566, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.00013505209634616554, |
| "grad_norm": 3.13470721244812, |
| "learning_rate": 5e-05, |
| "loss": 2.9975, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.0002701041926923311, |
| "grad_norm": 3.5096006393432617, |
| "learning_rate": 0.0001, |
| "loss": 2.8866, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.0002701041926923311, |
| "eval_loss": 2.533891201019287, |
| "eval_runtime": 1192.6144, |
| "eval_samples_per_second": 13.071, |
| "eval_steps_per_second": 6.536, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.0004051562890384966, |
| "grad_norm": 2.7829275131225586, |
| "learning_rate": 9.619397662556435e-05, |
| "loss": 2.4226, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.0005402083853846621, |
| "grad_norm": 2.209815502166748, |
| "learning_rate": 8.535533905932738e-05, |
| "loss": 2.3744, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.0005402083853846621, |
| "eval_loss": 2.0983729362487793, |
| "eval_runtime": 1192.9184, |
| "eval_samples_per_second": 13.068, |
| "eval_steps_per_second": 6.534, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.0006752604817308277, |
| "grad_norm": 2.978599786758423, |
| "learning_rate": 6.91341716182545e-05, |
| "loss": 2.0518, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.0008103125780769932, |
| "grad_norm": 2.711549997329712, |
| "learning_rate": 5e-05, |
| "loss": 2.0796, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.0008103125780769932, |
| "eval_loss": 2.007845401763916, |
| "eval_runtime": 1193.4448, |
| "eval_samples_per_second": 13.062, |
| "eval_steps_per_second": 6.532, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.0009453646744231588, |
| "grad_norm": 2.468726873397827, |
| "learning_rate": 3.086582838174551e-05, |
| "loss": 2.106, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.0010804167707693243, |
| "grad_norm": 2.1198647022247314, |
| "learning_rate": 1.4644660940672627e-05, |
| "loss": 1.9398, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.0010804167707693243, |
| "eval_loss": 1.9728028774261475, |
| "eval_runtime": 1193.5239, |
| "eval_samples_per_second": 13.061, |
| "eval_steps_per_second": 6.531, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.0012154688671154898, |
| "grad_norm": 2.1173436641693115, |
| "learning_rate": 3.8060233744356633e-06, |
| "loss": 1.9808, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.0013505209634616553, |
| "grad_norm": 2.887991428375244, |
| "learning_rate": 0.0, |
| "loss": 2.0277, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.0013505209634616553, |
| "eval_loss": 1.966479778289795, |
| "eval_runtime": 1192.3329, |
| "eval_samples_per_second": 13.074, |
| "eval_steps_per_second": 6.538, |
| "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": 4809119319982080.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
