Hugging Face's logo

theailearner
/
AIprofessions-doctor-v2-test

TensorBoard
Safetensors
Model card Files Metrics Community
AIprofessions-doctor-v2-test
File size: 4,574 Bytes 
da01cb7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 31.0,
  "eval_steps": 500,
  "global_step": 248,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.25,
      "grad_norm": 0.29974979162216187,
      "learning_rate": 0.0001992114701314478,
      "loss": 3.4405,
      "step": 10
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.3932454288005829,
      "learning_rate": 0.0001968583161128631,
      "loss": 3.3216,
      "step": 20
    },
    {
      "epoch": 3.75,
      "grad_norm": 0.42628756165504456,
      "learning_rate": 0.00019297764858882514,
      "loss": 3.1985,
      "step": 30
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.44253304600715637,
      "learning_rate": 0.00018763066800438636,
      "loss": 3.0415,
      "step": 40
    },
    {
      "epoch": 6.25,
      "grad_norm": 0.4085797071456909,
      "learning_rate": 0.00018090169943749476,
      "loss": 2.8932,
      "step": 50
    },
    {
      "epoch": 7.5,
      "grad_norm": 0.4421256184577942,
      "learning_rate": 0.00017289686274214118,
      "loss": 2.755,
      "step": 60
    },
    {
      "epoch": 8.75,
      "grad_norm": 0.44413742423057556,
      "learning_rate": 0.000163742398974869,
      "loss": 2.6121,
      "step": 70
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.4906141757965088,
      "learning_rate": 0.00015358267949789966,
      "loss": 2.4968,
      "step": 80
    },
    {
      "epoch": 11.25,
      "grad_norm": 0.4448947012424469,
      "learning_rate": 0.00014257792915650728,
      "loss": 2.3734,
      "step": 90
    },
    {
      "epoch": 12.5,
      "grad_norm": 0.40546461939811707,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.2633,
      "step": 100
    },
    {
      "epoch": 13.75,
      "grad_norm": 0.4101080000400543,
      "learning_rate": 0.00011873813145857249,
      "loss": 2.2142,
      "step": 110
    },
    {
      "epoch": 15.0,
      "grad_norm": 0.6073424220085144,
      "learning_rate": 0.00010627905195293135,
      "loss": 2.1403,
      "step": 120
    },
    {
      "epoch": 16.25,
      "grad_norm": 0.3520808815956116,
      "learning_rate": 9.372094804706867e-05,
      "loss": 2.1088,
      "step": 130
    },
    {
      "epoch": 17.5,
      "grad_norm": 0.37706121802330017,
      "learning_rate": 8.126186854142752e-05,
      "loss": 2.1054,
      "step": 140
    },
    {
      "epoch": 18.75,
      "grad_norm": 0.3702649474143982,
      "learning_rate": 6.909830056250527e-05,
      "loss": 2.0671,
      "step": 150
    },
    {
      "epoch": 20.0,
      "grad_norm": 0.47354856133461,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 2.0506,
      "step": 160
    },
    {
      "epoch": 21.25,
      "grad_norm": 0.35600489377975464,
      "learning_rate": 4.6417320502100316e-05,
      "loss": 2.0311,
      "step": 170
    },
    {
      "epoch": 22.5,
      "grad_norm": 0.3341175317764282,
      "learning_rate": 3.6257601025131026e-05,
      "loss": 2.0347,
      "step": 180
    },
    {
      "epoch": 23.75,
      "grad_norm": 0.3715374171733856,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 2.0274,
      "step": 190
    },
    {
      "epoch": 25.0,
      "grad_norm": 0.510712206363678,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 2.0153,
      "step": 200
    },
    {
      "epoch": 26.25,
      "grad_norm": 0.36683109402656555,
      "learning_rate": 1.2369331995613665e-05,
      "loss": 2.018,
      "step": 210
    },
    {
      "epoch": 27.5,
      "grad_norm": 0.3430872857570648,
      "learning_rate": 7.022351411174866e-06,
      "loss": 2.0266,
      "step": 220
    },
    {
      "epoch": 28.75,
      "grad_norm": 0.32684066891670227,
      "learning_rate": 3.1416838871368924e-06,
      "loss": 1.9921,
      "step": 230
    },
    {
      "epoch": 30.0,
      "grad_norm": 0.5148481726646423,
      "learning_rate": 7.885298685522235e-07,
      "loss": 2.0081,
      "step": 240
    }
  ],
  "logging_steps": 10,
  "max_steps": 250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 32,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 435969891385344.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}