Hugging Face's logo

ivangrapher
/
2618e9a0-499a-404d-ac27-f57f0bf02bbc

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
2618e9a0-499a-404d-ac27-f57f0bf02bbc
File size: 3,317 Bytes 
93beb0e
 
 
f19f169
93beb0e
f19f169
93beb0e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1b23e08
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9faf060
 
 
 
 
 
 
 
 
 
 
 
 
 
9d80276
 
 
 
 
 
 
 
 
 
 
 
 
 
 
13888a1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f19f169
 
 
 
 
 
 
 
 
 
 
 
 
 
93beb0e
 
 
 
 
 
 
 
 
 
 
 
 
 
f19f169
93beb0e
 
 
 
f19f169
93beb0e
 
 
 
 
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
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.013836574679068337,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004612191559689446,
      "eval_loss": 2.5192465782165527,
      "eval_runtime": 70.9137,
      "eval_samples_per_second": 19.319,
      "eval_steps_per_second": 9.66,
      "step": 1
    },
    {
      "epoch": 0.0013836574679068337,
      "grad_norm": 1.2828813791275024,
      "learning_rate": 0.00012,
      "loss": 2.3526,
      "step": 3
    },
    {
      "epoch": 0.0027673149358136673,
      "grad_norm": 0.6379570364952087,
      "learning_rate": 0.0001992114701314478,
      "loss": 2.2248,
      "step": 6
    },
    {
      "epoch": 0.0036897532477515567,
      "eval_loss": 2.1423521041870117,
      "eval_runtime": 70.532,
      "eval_samples_per_second": 19.424,
      "eval_steps_per_second": 9.712,
      "step": 8
    },
    {
      "epoch": 0.004150972403720501,
      "grad_norm": 0.6265854239463806,
      "learning_rate": 0.00018763066800438636,
      "loss": 2.0725,
      "step": 9
    },
    {
      "epoch": 0.005534629871627335,
      "grad_norm": 0.6093112826347351,
      "learning_rate": 0.000163742398974869,
      "loss": 1.8182,
      "step": 12
    },
    {
      "epoch": 0.0069182873395341685,
      "grad_norm": 0.7321146726608276,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.9648,
      "step": 15
    },
    {
      "epoch": 0.0073795064955031135,
      "eval_loss": 1.894142746925354,
      "eval_runtime": 70.5427,
      "eval_samples_per_second": 19.421,
      "eval_steps_per_second": 9.71,
      "step": 16
    },
    {
      "epoch": 0.008301944807441002,
      "grad_norm": 0.6654065847396851,
      "learning_rate": 9.372094804706867e-05,
      "loss": 1.893,
      "step": 18
    },
    {
      "epoch": 0.009685602275347836,
      "grad_norm": 0.612069845199585,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 1.8113,
      "step": 21
    },
    {
      "epoch": 0.01106925974325467,
      "grad_norm": 0.6409688591957092,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 1.697,
      "step": 24
    },
    {
      "epoch": 0.01106925974325467,
      "eval_loss": 1.803785800933838,
      "eval_runtime": 70.5929,
      "eval_samples_per_second": 19.407,
      "eval_steps_per_second": 9.704,
      "step": 24
    },
    {
      "epoch": 0.012452917211161504,
      "grad_norm": 0.5429406762123108,
      "learning_rate": 7.022351411174866e-06,
      "loss": 1.8863,
      "step": 27
    },
    {
      "epoch": 0.013836574679068337,
      "grad_norm": 0.5207058787345886,
      "learning_rate": 0.0,
      "loss": 1.8584,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6238028100009984.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}