Hugging Face's logo

tuantmdev
/
63a8631c-54c7-470b-9aa5-f4c70666a956

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
63a8631c-54c7-470b-9aa5-f4c70666a956
File size: 3,750 Bytes 
0f7d276
 
 
0546149
3beb9ec
0546149
0f7d276
 
 
 
 
 
 
3beb9ec
 
 
0f7d276
3beb9ec
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cde5f18
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b9a79ff
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0546149
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0f7d276
 
 
3beb9ec
0f7d276
 
3beb9ec
0f7d276
 
 
 
 
 
 
0546149
0f7d276
 
 
 
0546149
0f7d276
 
 
 
 
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
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.021324234993069624,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00042648469986139245,
      "eval_loss": 11.933326721191406,
      "eval_runtime": 9.0029,
      "eval_samples_per_second": 109.742,
      "eval_steps_per_second": 54.871,
      "step": 1
    },
    {
      "epoch": 0.0021324234993069626,
      "grad_norm": 0.009308514185249805,
      "learning_rate": 5e-05,
      "loss": 11.9336,
      "step": 5
    },
    {
      "epoch": 0.004264846998613925,
      "grad_norm": 0.012845045886933804,
      "learning_rate": 0.0001,
      "loss": 11.9345,
      "step": 10
    },
    {
      "epoch": 0.004264846998613925,
      "eval_loss": 11.933305740356445,
      "eval_runtime": 9.1755,
      "eval_samples_per_second": 107.678,
      "eval_steps_per_second": 53.839,
      "step": 10
    },
    {
      "epoch": 0.006397270497920887,
      "grad_norm": 0.010501927696168423,
      "learning_rate": 9.619397662556435e-05,
      "loss": 11.9345,
      "step": 15
    },
    {
      "epoch": 0.00852969399722785,
      "grad_norm": 0.010710126720368862,
      "learning_rate": 8.535533905932738e-05,
      "loss": 11.9335,
      "step": 20
    },
    {
      "epoch": 0.00852969399722785,
      "eval_loss": 11.933269500732422,
      "eval_runtime": 9.2734,
      "eval_samples_per_second": 106.541,
      "eval_steps_per_second": 53.271,
      "step": 20
    },
    {
      "epoch": 0.010662117496534812,
      "grad_norm": 0.016991719603538513,
      "learning_rate": 6.91341716182545e-05,
      "loss": 11.9345,
      "step": 25
    },
    {
      "epoch": 0.012794540995841774,
      "grad_norm": 0.011298740282654762,
      "learning_rate": 5e-05,
      "loss": 11.9305,
      "step": 30
    },
    {
      "epoch": 0.012794540995841774,
      "eval_loss": 11.933237075805664,
      "eval_runtime": 9.3204,
      "eval_samples_per_second": 106.004,
      "eval_steps_per_second": 53.002,
      "step": 30
    },
    {
      "epoch": 0.014926964495148737,
      "grad_norm": 0.016434844583272934,
      "learning_rate": 3.086582838174551e-05,
      "loss": 11.9326,
      "step": 35
    },
    {
      "epoch": 0.0170593879944557,
      "grad_norm": 0.014193267561495304,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 11.9328,
      "step": 40
    },
    {
      "epoch": 0.0170593879944557,
      "eval_loss": 11.933220863342285,
      "eval_runtime": 9.3191,
      "eval_samples_per_second": 106.018,
      "eval_steps_per_second": 53.009,
      "step": 40
    },
    {
      "epoch": 0.019191811493762662,
      "grad_norm": 0.010223680175840855,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 11.9346,
      "step": 45
    },
    {
      "epoch": 0.021324234993069624,
      "grad_norm": 0.013457508757710457,
      "learning_rate": 0.0,
      "loss": 11.9313,
      "step": 50
    },
    {
      "epoch": 0.021324234993069624,
      "eval_loss": 11.933218002319336,
      "eval_runtime": 9.0369,
      "eval_samples_per_second": 109.329,
      "eval_steps_per_second": 54.665,
      "step": 50
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5996691456.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}