Hugging Face's logo

Xtracta-Qiming
/
Damarcode_AB_v1_20241129_qwen

Transformers
Safetensors
Generated from Trainer
trl
sft
Inference Endpoints
Model card Files Community
Damarcode_AB_v1_20241129_qwen
File size: 2,215 Bytes 
31e6dde
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
 
{
  "best_metric": 0.5751409530639648,
  "best_model_checkpoint": "/home/paperspace/mmdoc/outputs/Damarcode_AB_v1_20241129_qwen/checkpoint-30",
  "epoch": 2.8363636363636364,
  "eval_steps": 10,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.16329370439052582,
      "learning_rate": 0.0002,
      "loss": 0.9083,
      "step": 10
    },
    {
      "epoch": 0.7272727272727273,
      "eval_loss": 0.8439409136772156,
      "eval_runtime": 21.1664,
      "eval_samples_per_second": 0.331,
      "eval_steps_per_second": 0.331,
      "step": 10
    },
    {
      "epoch": 1.4545454545454546,
      "grad_norm": 0.26372385025024414,
      "learning_rate": 0.0002,
      "loss": 0.7851,
      "step": 20
    },
    {
      "epoch": 1.4545454545454546,
      "eval_loss": 0.7270452380180359,
      "eval_runtime": 21.3022,
      "eval_samples_per_second": 0.329,
      "eval_steps_per_second": 0.329,
      "step": 20
    },
    {
      "epoch": 2.1818181818181817,
      "grad_norm": 1.2343300580978394,
      "learning_rate": 0.0002,
      "loss": 0.6795,
      "step": 30
    },
    {
      "epoch": 2.1818181818181817,
      "eval_loss": 0.5751409530639648,
      "eval_runtime": 21.5123,
      "eval_samples_per_second": 0.325,
      "eval_steps_per_second": 0.325,
      "step": 30
    },
    {
      "epoch": 2.8363636363636364,
      "step": 39,
      "total_flos": 3.417506073386496e+16,
      "train_loss": 0.7222367188869379,
      "train_runtime": 1361.6133,
      "train_samples_per_second": 0.242,
      "train_steps_per_second": 0.029
    }
  ],
  "logging_steps": 10,
  "max_steps": 39,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.417506073386496e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}