Hugging Face's logo

cwaud
/
a173544c-bd09-4c49-a8a6-d86ed0f603e8

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
a173544c-bd09-4c49-a8a6-d86ed0f603e8
File size: 3,221 Bytes 
ea4c28f
 
 
a4e28a7
ea4c28f
a4e28a7
ea4c28f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c643d8d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
107e827
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a4e28a7
 
 
 
 
 
 
ea4c28f
 
 
 
 
 
 
 
 
 
 
 
 
 
a4e28a7
ea4c28f
 
 
 
a4e28a7
ea4c28f
 
 
 
 
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": 0.0005027841673265709,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.0278416732657086e-05,
      "grad_norm": 0.2741275131702423,
      "learning_rate": 2e-05,
      "loss": 1.4864,
      "step": 1
    },
    {
      "epoch": 5.0278416732657086e-05,
      "eval_loss": 1.7782368659973145,
      "eval_runtime": 1156.3654,
      "eval_samples_per_second": 7.243,
      "eval_steps_per_second": 3.622,
      "step": 1
    },
    {
      "epoch": 0.00010055683346531417,
      "grad_norm": 0.4866497218608856,
      "learning_rate": 4e-05,
      "loss": 1.7741,
      "step": 2
    },
    {
      "epoch": 0.00015083525019797127,
      "grad_norm": 0.2840794026851654,
      "learning_rate": 6e-05,
      "loss": 1.9167,
      "step": 3
    },
    {
      "epoch": 0.00015083525019797127,
      "eval_loss": 1.7769949436187744,
      "eval_runtime": 1171.8749,
      "eval_samples_per_second": 7.147,
      "eval_steps_per_second": 3.574,
      "step": 3
    },
    {
      "epoch": 0.00020111366693062834,
      "grad_norm": 0.4316411018371582,
      "learning_rate": 8e-05,
      "loss": 1.7962,
      "step": 4
    },
    {
      "epoch": 0.00025139208366328547,
      "grad_norm": 0.34983840584754944,
      "learning_rate": 0.0001,
      "loss": 2.1419,
      "step": 5
    },
    {
      "epoch": 0.00030167050039594254,
      "grad_norm": 0.28104010224342346,
      "learning_rate": 0.00012,
      "loss": 1.8218,
      "step": 6
    },
    {
      "epoch": 0.00030167050039594254,
      "eval_loss": 1.7353360652923584,
      "eval_runtime": 1159.2615,
      "eval_samples_per_second": 7.224,
      "eval_steps_per_second": 3.613,
      "step": 6
    },
    {
      "epoch": 0.0003519489171285996,
      "grad_norm": 0.31961575150489807,
      "learning_rate": 0.00014,
      "loss": 1.777,
      "step": 7
    },
    {
      "epoch": 0.0004022273338612567,
      "grad_norm": 0.4506252110004425,
      "learning_rate": 0.00016,
      "loss": 1.7637,
      "step": 8
    },
    {
      "epoch": 0.0004525057505939138,
      "grad_norm": 0.5181860327720642,
      "learning_rate": 0.00018,
      "loss": 1.6113,
      "step": 9
    },
    {
      "epoch": 0.0004525057505939138,
      "eval_loss": 1.6632812023162842,
      "eval_runtime": 1157.8037,
      "eval_samples_per_second": 7.234,
      "eval_steps_per_second": 3.617,
      "step": 9
    },
    {
      "epoch": 0.0005027841673265709,
      "grad_norm": 0.5425806045532227,
      "learning_rate": 0.0002,
      "loss": 1.724,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2178295057612800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}