Hugging Face's logo

robertou2
/
task-7-microsoft-Phi-3.5-mini-instruct

PEFT
Safetensors
Model card Files
xet
Community
task-7-microsoft-Phi-3.5-mini-instruct
File size: 6,232 Bytes
11f3e2d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
 
{
  "best_global_step": 27,
  "best_metric": 0.5779597759246826,
  "best_model_checkpoint": "//outputs/task7_microsoft/Phi-3.5-mini-instruct/checkpoint-27",
  "epoch": 11.0,
  "eval_steps": 500,
  "global_step": 99,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.5882352941176471,
      "grad_norm": 0.2979797124862671,
      "learning_rate": 0.00015,
      "loss": 0.7889,
      "step": 5
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.6737979650497437,
      "eval_runtime": 3.3675,
      "eval_samples_per_second": 4.454,
      "eval_steps_per_second": 0.594,
      "step": 9
    },
    {
      "epoch": 1.1176470588235294,
      "grad_norm": 0.20464661717414856,
      "learning_rate": 0.0003,
      "loss": 0.6771,
      "step": 10
    },
    {
      "epoch": 1.7058823529411766,
      "grad_norm": 0.1992536187171936,
      "learning_rate": 0.00029948767395100045,
      "loss": 0.6255,
      "step": 15
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.6006895303726196,
      "eval_runtime": 3.3642,
      "eval_samples_per_second": 4.459,
      "eval_steps_per_second": 0.594,
      "step": 18
    },
    {
      "epoch": 2.235294117647059,
      "grad_norm": 0.19050121307373047,
      "learning_rate": 0.00029795419551040833,
      "loss": 0.5302,
      "step": 20
    },
    {
      "epoch": 2.8235294117647056,
      "grad_norm": 0.17813433706760406,
      "learning_rate": 0.0002954100398908995,
      "loss": 0.4439,
      "step": 25
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.5779597759246826,
      "eval_runtime": 3.3656,
      "eval_samples_per_second": 4.457,
      "eval_steps_per_second": 0.594,
      "step": 27
    },
    {
      "epoch": 3.3529411764705883,
      "grad_norm": 0.23658457398414612,
      "learning_rate": 0.00029187258625509513,
      "loss": 0.4257,
      "step": 30
    },
    {
      "epoch": 3.9411764705882355,
      "grad_norm": 0.27489331364631653,
      "learning_rate": 0.00028736599899825856,
      "loss": 0.3254,
      "step": 35
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.5997567772865295,
      "eval_runtime": 3.3651,
      "eval_samples_per_second": 4.458,
      "eval_steps_per_second": 0.594,
      "step": 36
    },
    {
      "epoch": 4.470588235294118,
      "grad_norm": 0.3510420620441437,
      "learning_rate": 0.00028192106268097334,
      "loss": 0.2985,
      "step": 40
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.4653756320476532,
      "learning_rate": 0.00027557497173937923,
      "loss": 0.2828,
      "step": 45
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.6584295034408569,
      "eval_runtime": 3.3668,
      "eval_samples_per_second": 4.455,
      "eval_steps_per_second": 0.594,
      "step": 45
    },
    {
      "epoch": 5.588235294117647,
      "grad_norm": 0.3469710052013397,
      "learning_rate": 0.00026837107640945905,
      "loss": 0.2038,
      "step": 50
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.751620888710022,
      "eval_runtime": 3.3651,
      "eval_samples_per_second": 4.458,
      "eval_steps_per_second": 0.594,
      "step": 54
    },
    {
      "epoch": 6.117647058823529,
      "grad_norm": 0.3903103470802307,
      "learning_rate": 0.0002603585866009697,
      "loss": 0.1656,
      "step": 55
    },
    {
      "epoch": 6.705882352941177,
      "grad_norm": 0.38518330454826355,
      "learning_rate": 0.00025159223574386114,
      "loss": 0.1296,
      "step": 60
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.8753386735916138,
      "eval_runtime": 3.3654,
      "eval_samples_per_second": 4.457,
      "eval_steps_per_second": 0.594,
      "step": 63
    },
    {
      "epoch": 7.235294117647059,
      "grad_norm": 0.24312527477741241,
      "learning_rate": 0.00024213190690345018,
      "loss": 0.085,
      "step": 65
    },
    {
      "epoch": 7.823529411764706,
      "grad_norm": 0.3267911970615387,
      "learning_rate": 0.00023204222371836405,
      "loss": 0.0751,
      "step": 70
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.8750011920928955,
      "eval_runtime": 3.3678,
      "eval_samples_per_second": 4.454,
      "eval_steps_per_second": 0.594,
      "step": 72
    },
    {
      "epoch": 8.352941176470589,
      "grad_norm": 0.24549448490142822,
      "learning_rate": 0.00022139210895556104,
      "loss": 0.0576,
      "step": 75
    },
    {
      "epoch": 8.941176470588236,
      "grad_norm": 0.3071894347667694,
      "learning_rate": 0.0002102543136979454,
      "loss": 0.0475,
      "step": 80
    },
    {
      "epoch": 9.0,
      "eval_loss": 0.9990332126617432,
      "eval_runtime": 3.3671,
      "eval_samples_per_second": 4.455,
      "eval_steps_per_second": 0.594,
      "step": 81
    },
    {
      "epoch": 9.470588235294118,
      "grad_norm": 0.17012739181518555,
      "learning_rate": 0.00019870492038070252,
      "loss": 0.0282,
      "step": 85
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.2809393107891083,
      "learning_rate": 0.00018682282307111987,
      "loss": 0.0249,
      "step": 90
    },
    {
      "epoch": 10.0,
      "eval_loss": 1.022998571395874,
      "eval_runtime": 3.3665,
      "eval_samples_per_second": 4.456,
      "eval_steps_per_second": 0.594,
      "step": 90
    },
    {
      "epoch": 10.588235294117647,
      "grad_norm": 0.16731834411621094,
      "learning_rate": 0.00017468918854211007,
      "loss": 0.0151,
      "step": 95
    },
    {
      "epoch": 11.0,
      "eval_loss": 1.0694772005081177,
      "eval_runtime": 3.3662,
      "eval_samples_per_second": 4.456,
      "eval_steps_per_second": 0.594,
      "step": 99
    }
  ],
  "logging_steps": 5,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 25,
  "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": 5.146100297640346e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}