Hugging Face's logo

HassanSamo
/
Mistral7B-BrevDev

Safetensors
Model card Files Community
Mistral7B-BrevDev
File size: 4,271 Bytes 
0cd3c36
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3,
  "eval_steps": 10,
  "global_step": 120,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 2.4549098196392788e-05,
      "loss": 1.5765,
      "step": 10
    },
    {
      "epoch": 0.03,
      "eval_loss": 1.4641923904418945,
      "eval_runtime": 221.9956,
      "eval_samples_per_second": 0.901,
      "eval_steps_per_second": 0.113,
      "step": 10
    },
    {
      "epoch": 0.05,
      "learning_rate": 2.404809619238477e-05,
      "loss": 1.5681,
      "step": 20
    },
    {
      "epoch": 0.05,
      "eval_loss": 1.4410793781280518,
      "eval_runtime": 221.7333,
      "eval_samples_per_second": 0.902,
      "eval_steps_per_second": 0.113,
      "step": 20
    },
    {
      "epoch": 0.07,
      "learning_rate": 2.3547094188376757e-05,
      "loss": 1.2801,
      "step": 30
    },
    {
      "epoch": 0.07,
      "eval_loss": 1.4293081760406494,
      "eval_runtime": 221.7604,
      "eval_samples_per_second": 0.902,
      "eval_steps_per_second": 0.113,
      "step": 30
    },
    {
      "epoch": 0.1,
      "learning_rate": 2.304609218436874e-05,
      "loss": 1.5474,
      "step": 40
    },
    {
      "epoch": 0.1,
      "eval_loss": 1.430722951889038,
      "eval_runtime": 221.7555,
      "eval_samples_per_second": 0.902,
      "eval_steps_per_second": 0.113,
      "step": 40
    },
    {
      "epoch": 0.12,
      "learning_rate": 2.2545090180360722e-05,
      "loss": 1.3972,
      "step": 50
    },
    {
      "epoch": 0.12,
      "eval_loss": 1.4295932054519653,
      "eval_runtime": 221.7379,
      "eval_samples_per_second": 0.902,
      "eval_steps_per_second": 0.113,
      "step": 50
    },
    {
      "epoch": 0.15,
      "learning_rate": 2.2044088176352705e-05,
      "loss": 1.578,
      "step": 60
    },
    {
      "epoch": 0.15,
      "eval_loss": 1.425429344177246,
      "eval_runtime": 221.7329,
      "eval_samples_per_second": 0.902,
      "eval_steps_per_second": 0.113,
      "step": 60
    },
    {
      "epoch": 0.17,
      "learning_rate": 2.1543086172344688e-05,
      "loss": 1.3322,
      "step": 70
    },
    {
      "epoch": 0.17,
      "eval_loss": 1.4246026277542114,
      "eval_runtime": 221.7499,
      "eval_samples_per_second": 0.902,
      "eval_steps_per_second": 0.113,
      "step": 70
    },
    {
      "epoch": 0.2,
      "learning_rate": 2.1042084168336674e-05,
      "loss": 1.4031,
      "step": 80
    },
    {
      "epoch": 0.2,
      "eval_loss": 1.4232592582702637,
      "eval_runtime": 221.7409,
      "eval_samples_per_second": 0.902,
      "eval_steps_per_second": 0.113,
      "step": 80
    },
    {
      "epoch": 0.23,
      "learning_rate": 2.054108216432866e-05,
      "loss": 1.454,
      "step": 90
    },
    {
      "epoch": 0.23,
      "eval_loss": 1.4188882112503052,
      "eval_runtime": 221.7396,
      "eval_samples_per_second": 0.902,
      "eval_steps_per_second": 0.113,
      "step": 90
    },
    {
      "epoch": 0.25,
      "learning_rate": 2.0040080160320643e-05,
      "loss": 1.4341,
      "step": 100
    },
    {
      "epoch": 0.25,
      "eval_loss": 1.416797161102295,
      "eval_runtime": 221.7427,
      "eval_samples_per_second": 0.902,
      "eval_steps_per_second": 0.113,
      "step": 100
    },
    {
      "epoch": 0.28,
      "learning_rate": 1.9539078156312626e-05,
      "loss": 1.4684,
      "step": 110
    },
    {
      "epoch": 0.28,
      "eval_loss": 1.4176369905471802,
      "eval_runtime": 221.7309,
      "eval_samples_per_second": 0.902,
      "eval_steps_per_second": 0.113,
      "step": 110
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.903807615230461e-05,
      "loss": 1.2462,
      "step": 120
    },
    {
      "epoch": 0.3,
      "eval_loss": 1.4165884256362915,
      "eval_runtime": 221.7346,
      "eval_samples_per_second": 0.902,
      "eval_steps_per_second": 0.113,
      "step": 120
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 10,
  "total_flos": 2.072361959424e+16,
  "trial_name": null,
  "trial_params": null
}