Hugging Face's logo

Jordansky
/
beta-testing

Text Generation
PEFT
Safetensors
Transformers
grpo
lora
trl
conversational
Model card Files
xet
 Community
beta-testing
File size: 2,084 Bytes
b5e88ac
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1e-05,
  "eval_steps": 500,
  "global_step": 1,
  "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": 0.0,
      "completions/max_length": 755.0,
      "completions/max_terminated_length": 755.0,
      "completions/mean_length": 697.875,
      "completions/mean_terminated_length": 697.875,
      "completions/min_length": 637.0,
      "completions/min_terminated_length": 637.0,
      "entropy": 0.15835951827466488,
      "epoch": 1e-05,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 3.3084652423858643,
      "kl": 0.0,
      "learning_rate": 0.0,
      "loss": -0.0006,
      "num_tokens": 49412.0,
      "reward": -2.054835796356201,
      "reward_std": 4.80037784576416,
      "rewards/rollout_reward_func/mean": -2.054835796356201,
      "rewards/rollout_reward_func/std": 7.210431098937988,
      "sampling/importance_sampling_ratio/max": 1.5730165243148804,
      "sampling/importance_sampling_ratio/mean": 1.0320667028427124,
      "sampling/importance_sampling_ratio/min": 0.6166286468505859,
      "sampling/sampling_logp_difference/max": 0.5753030776977539,
      "sampling/sampling_logp_difference/mean": 0.02080601453781128,
      "step": 1,
      "step_time": 16.957322160999865
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 200000,
  "num_input_tokens_seen": 49412,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}