Hugging Face's logo

chauhoang
/
c935da6c-0baa-8480-c8c4-2461e4b2707c

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
c935da6c-0baa-8480-c8c4-2461e4b2707c
File size: 2,113 Bytes 
18b526e
 
 
2166bb7
8483a91
2166bb7
18b526e
 
 
 
 
 
 
2166bb7
 
 
18b526e
8483a91
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2166bb7
 
 
8483a91
4fb35cc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2166bb7
 
 
4fb35cc
 
 
 
 
 
 
 
18b526e
 
 
8483a91
18b526e
 
8483a91
18b526e
 
 
 
 
 
 
8483a91
18b526e
 
 
 
2166bb7
18b526e
 
 
 
 
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
89
90
91
92
93
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.002240751513584556,
  "eval_steps": 10,
  "global_step": 26,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.618275052248293e-05,
      "eval_loss": NaN,
      "eval_runtime": 331.7922,
      "eval_samples_per_second": 14.726,
      "eval_steps_per_second": 7.363,
      "step": 1
    },
    {
      "epoch": 0.0004309137526124146,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0008618275052248292,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.0008618275052248292,
      "eval_loss": NaN,
      "eval_runtime": 331.9842,
      "eval_samples_per_second": 14.718,
      "eval_steps_per_second": 7.359,
      "step": 10
    },
    {
      "epoch": 0.0012927412578372438,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0017236550104496584,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.0017236550104496584,
      "eval_loss": NaN,
      "eval_runtime": 331.1945,
      "eval_samples_per_second": 14.753,
      "eval_steps_per_second": 7.376,
      "step": 20
    },
    {
      "epoch": 0.002154568763062073,
      "grad_norm": NaN,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 25
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5271474039422976.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}