Hugging Face's logo

ugaoo
/
xp182

Safetensors
llama
4-bit precision
bitsandbytes
Model card Files
xet
 Community
xp182
File size: 4,442 Bytes
140b47e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.45,
  "eval_steps": 500,
  "global_step": 24,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.15,
      "grad_norm": 35.73806381225586,
      "learning_rate": 5.0000000000000004e-08,
      "loss": 3.2839,
      "step": 1
    },
    {
      "epoch": 0.3,
      "grad_norm": 35.236732482910156,
      "learning_rate": 1.0000000000000001e-07,
      "loss": 3.2281,
      "step": 2
    },
    {
      "epoch": 0.45,
      "grad_norm": 35.85063171386719,
      "learning_rate": 1.5000000000000002e-07,
      "loss": 3.2521,
      "step": 3
    },
    {
      "epoch": 0.6,
      "grad_norm": 35.62168884277344,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 3.2824,
      "step": 4
    },
    {
      "epoch": 0.75,
      "grad_norm": 36.429351806640625,
      "learning_rate": 2.5000000000000004e-07,
      "loss": 3.3533,
      "step": 5
    },
    {
      "epoch": 0.9,
      "grad_norm": 36.30988311767578,
      "learning_rate": 3.0000000000000004e-07,
      "loss": 3.3279,
      "step": 6
    },
    {
      "epoch": 1.0,
      "grad_norm": 36.30988311767578,
      "learning_rate": 3.5000000000000004e-07,
      "loss": 3.2644,
      "step": 7
    },
    {
      "epoch": 1.15,
      "grad_norm": 46.94998550415039,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 3.2235,
      "step": 8
    },
    {
      "epoch": 1.3,
      "grad_norm": 36.432373046875,
      "learning_rate": 4.5000000000000003e-07,
      "loss": 3.1799,
      "step": 9
    },
    {
      "epoch": 1.45,
      "grad_norm": 36.3123779296875,
      "learning_rate": 5.000000000000001e-07,
      "loss": 3.1618,
      "step": 10
    },
    {
      "epoch": 1.6,
      "grad_norm": 34.80661392211914,
      "learning_rate": 5.5e-07,
      "loss": 3.1557,
      "step": 11
    },
    {
      "epoch": 1.75,
      "grad_norm": 36.64874267578125,
      "learning_rate": 6.000000000000001e-07,
      "loss": 3.1375,
      "step": 12
    },
    {
      "epoch": 1.9,
      "grad_norm": 36.32555389404297,
      "learning_rate": 6.5e-07,
      "loss": 3.0565,
      "step": 13
    },
    {
      "epoch": 2.0,
      "grad_norm": 47.40998077392578,
      "learning_rate": 7.000000000000001e-07,
      "loss": 3.0395,
      "step": 14
    },
    {
      "epoch": 2.15,
      "grad_norm": 37.59382629394531,
      "learning_rate": 7.5e-07,
      "loss": 2.8641,
      "step": 15
    },
    {
      "epoch": 2.3,
      "grad_norm": 36.185447692871094,
      "learning_rate": 8.000000000000001e-07,
      "loss": 2.87,
      "step": 16
    },
    {
      "epoch": 2.45,
      "grad_norm": 36.60142135620117,
      "learning_rate": 8.500000000000001e-07,
      "loss": 2.6385,
      "step": 17
    },
    {
      "epoch": 2.6,
      "grad_norm": 34.09886169433594,
      "learning_rate": 9.000000000000001e-07,
      "loss": 2.5288,
      "step": 18
    },
    {
      "epoch": 2.75,
      "grad_norm": 34.80934143066406,
      "learning_rate": 9.500000000000001e-07,
      "loss": 2.3427,
      "step": 19
    },
    {
      "epoch": 2.9,
      "grad_norm": 33.58020782470703,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 2.2199,
      "step": 20
    },
    {
      "epoch": 3.0,
      "grad_norm": 44.49959945678711,
      "learning_rate": 1.0500000000000001e-06,
      "loss": 2.0696,
      "step": 21
    },
    {
      "epoch": 3.15,
      "grad_norm": 32.54341125488281,
      "learning_rate": 1.1e-06,
      "loss": 1.8847,
      "step": 22
    },
    {
      "epoch": 3.3,
      "grad_norm": 32.68830108642578,
      "learning_rate": 1.1500000000000002e-06,
      "loss": 1.75,
      "step": 23
    },
    {
      "epoch": 3.45,
      "grad_norm": 31.561199188232422,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 1.5479,
      "step": 24
    }
  ],
  "logging_steps": 1,
  "max_steps": 36,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 6,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.4635492074942628e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}