| { |
| "best_global_step": 10, |
| "best_metric": -0.1490575075149536, |
| "best_model_checkpoint": "/workspace/scripts/soutputs/5890fd80-dc75-4cdc-95ff-e0eaacb583db_0/checkpoint-10", |
| "epoch": 0.04854368932038835, |
| "eval_steps": 500, |
| "global_step": 10, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "clip_ratio/high_max": 0.0, |
| "clip_ratio/high_mean": 0.0, |
| "clip_ratio/low_mean": 0.0, |
| "clip_ratio/low_min": 0.0, |
| "clip_ratio/region_mean": 0.0, |
| "completions/clipped_ratio": 0.74, |
| "completions/max_length": 256.0, |
| "completions/max_terminated_length": 207.4, |
| "completions/mean_length": 209.14500732421874, |
| "completions/mean_terminated_length": 79.1390480041504, |
| "completions/min_length": 1.0, |
| "completions/min_terminated_length": 1.0, |
| "epoch": 0.024271844660194174, |
| "frac_reward_zero_std": 0.0, |
| "grad_norm": 1.6186683177947998, |
| "kl": 0.00032186579919653014, |
| "learning_rate": 9.142857142857142e-07, |
| "loss": -0.1198, |
| "num_tokens": 45127.0, |
| "reward": 155.98389587402343, |
| "reward_std": 51.56508560180664, |
| "rewards/wrapper/mean": 77.99194231033326, |
| "rewards/wrapper/std": 34.79756020009518, |
| "step": 5 |
| }, |
| { |
| "clip_ratio/high_max": 0.0, |
| "clip_ratio/high_mean": 0.0, |
| "clip_ratio/low_mean": 0.0, |
| "clip_ratio/low_min": 0.0, |
| "clip_ratio/region_mean": 0.0, |
| "completions/clipped_ratio": 0.6950000000000001, |
| "completions/max_length": 256.0, |
| "completions/max_terminated_length": 224.2, |
| "completions/mean_length": 203.29000549316407, |
| "completions/mean_terminated_length": 82.7972427368164, |
| "completions/min_length": 1.0, |
| "completions/min_terminated_length": 1.0, |
| "epoch": 0.04854368932038835, |
| "frac_reward_zero_std": 0.0, |
| "grad_norm": 1.6955170631408691, |
| "kl": 0.0006193328881636262, |
| "learning_rate": 2.057142857142857e-06, |
| "loss": -0.126, |
| "num_tokens": 88957.0, |
| "reward": 152.94253540039062, |
| "reward_std": 48.6057991027832, |
| "rewards/wrapper/mean": 76.47126719951629, |
| "rewards/wrapper/std": 35.78222155570984, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.04854368932038835, |
| "eval_clip_ratio/high_max": 0.0, |
| "eval_clip_ratio/high_mean": 0.0, |
| "eval_clip_ratio/low_mean": 0.0, |
| "eval_clip_ratio/low_min": 0.0, |
| "eval_clip_ratio/region_mean": 0.0, |
| "eval_completions/clipped_ratio": 0.7225, |
| "eval_completions/max_length": 255.19, |
| "eval_completions/max_terminated_length": 73.76, |
| "eval_completions/mean_length": 209.125, |
| "eval_completions/mean_terminated_length": 58.48083358764649, |
| "eval_completions/min_length": 114.45, |
| "eval_completions/min_terminated_length": 42.77, |
| "eval_frac_reward_zero_std": 0.0, |
| "eval_kl": 0.0007304183713858947, |
| "eval_loss": -0.1490575075149536, |
| "eval_num_tokens": 88957.0, |
| "eval_reward": 152.92680000305177, |
| "eval_reward_std": 52.7454217505455, |
| "eval_rewards/wrapper/mean": 76.46340038672089, |
| "eval_rewards/wrapper/std": 31.92882010869682, |
| "eval_runtime": 104.7007, |
| "eval_samples_per_second": 1.91, |
| "eval_steps_per_second": 0.478, |
| "step": 10 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 618, |
| "num_input_tokens_seen": 88957, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 0.0, |
| "train_batch_size": 10, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
