TinyPixel commited on
Commit
fce6e26
1 Parent(s): 7646311

Upload folder using huggingface_hub

Browse files
adapter_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "auto_mapping": null,
3
- "base_model_name_or_path": "stabilityai/stablelm-base-alpha-3b-v2",
4
  "bias": "none",
5
  "fan_in_fan_out": false,
6
  "inference_mode": true,
@@ -14,9 +14,13 @@
14
  "r": 16,
15
  "revision": null,
16
  "target_modules": [
17
- "qkv_proj",
 
 
 
18
  "gate_proj",
19
- "out_proj"
 
20
  ],
21
  "task_type": "CAUSAL_LM"
22
  }
 
1
  {
2
  "auto_mapping": null,
3
+ "base_model_name_or_path": "stabilityai/stablelm-3b-4e1t",
4
  "bias": "none",
5
  "fan_in_fan_out": false,
6
  "inference_mode": true,
 
14
  "r": 16,
15
  "revision": null,
16
  "target_modules": [
17
+ "q_proj",
18
+ "k_proj",
19
+ "o_proj",
20
+ "v_proj",
21
  "gate_proj",
22
+ "down_proj",
23
+ "up_proj"
24
  ],
25
  "task_type": "CAUSAL_LM"
26
  }
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c93e9e064e4836d718dd5817a31b8b922c096ac52b39320046ae8414fc3f164c
3
- size 84504330
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d2f9e238aa5a49d602e835a5896672d7a3190bfefa9629bb3bba1569670bfe3
3
+ size 100300298
optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c4e047dcb32ec0ae668d771ec35f3567a0e70b1c03c1a1963e3252fa05b9c9e3
3
- size 169035898
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90e39b978dcdf99edabb64ecd69bdf0397ca86edf1ff11e8f3608e417a9d55bb
3
+ size 200654930
rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d88943110975beabc6932e5d2c3d009f5f9a53729cb06aa62da38ef86bafb19
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce0d90839c1d2b909c1e5054d9a87b1c188f1ce2eeb0eec32bf435ffe51732a6
3
  size 14244
trainer_state.json CHANGED
@@ -11,307 +11,307 @@
11
  {
12
  "epoch": 0.06,
13
  "learning_rate": 3.6363636363636364e-05,
14
- "loss": 1.8667,
15
  "step": 2
16
  },
17
  {
18
  "epoch": 0.12,
19
  "learning_rate": 7.272727272727273e-05,
20
- "loss": 1.669,
21
  "step": 4
22
  },
23
  {
24
  "epoch": 0.18,
25
  "learning_rate": 0.00010909090909090909,
26
- "loss": 1.607,
27
  "step": 6
28
  },
29
  {
30
  "epoch": 0.23,
31
  "learning_rate": 0.00014545454545454546,
32
- "loss": 2.0734,
33
  "step": 8
34
  },
35
  {
36
  "epoch": 0.29,
37
  "learning_rate": 0.00018181818181818183,
38
- "loss": 1.5327,
39
  "step": 10
40
  },
41
  {
42
  "epoch": 0.35,
43
  "learning_rate": 0.0001978021978021978,
44
- "loss": 1.7996,
45
  "step": 12
46
  },
47
  {
48
  "epoch": 0.41,
49
  "learning_rate": 0.00019340659340659342,
50
- "loss": 1.6866,
51
  "step": 14
52
  },
53
  {
54
  "epoch": 0.47,
55
  "learning_rate": 0.00018901098901098903,
56
- "loss": 1.6299,
57
  "step": 16
58
  },
59
  {
60
  "epoch": 0.53,
61
  "learning_rate": 0.00018461538461538463,
62
- "loss": 1.8521,
63
  "step": 18
64
  },
65
  {
66
  "epoch": 0.58,
67
  "learning_rate": 0.00018021978021978024,
68
- "loss": 1.7468,
69
  "step": 20
70
  },
71
  {
72
  "epoch": 0.64,
73
  "learning_rate": 0.00017582417582417582,
74
- "loss": 1.8712,
75
  "step": 22
76
  },
77
  {
78
  "epoch": 0.7,
79
  "learning_rate": 0.00017142857142857143,
80
- "loss": 1.6447,
81
  "step": 24
82
  },
83
  {
84
  "epoch": 0.76,
85
  "learning_rate": 0.00016703296703296706,
86
- "loss": 1.7091,
87
  "step": 26
88
  },
89
  {
90
  "epoch": 0.82,
91
  "learning_rate": 0.00016263736263736264,
92
- "loss": 1.5068,
93
  "step": 28
94
  },
95
  {
96
  "epoch": 0.88,
97
  "learning_rate": 0.00015824175824175824,
98
- "loss": 1.7822,
99
  "step": 30
100
  },
101
  {
102
  "epoch": 0.93,
103
  "learning_rate": 0.00015384615384615385,
104
- "loss": 1.7897,
105
  "step": 32
106
  },
107
  {
108
  "epoch": 0.99,
109
  "learning_rate": 0.00014945054945054946,
110
- "loss": 1.5594,
111
  "step": 34
112
  },
113
  {
114
  "epoch": 1.05,
115
  "learning_rate": 0.00014505494505494506,
116
- "loss": 1.5073,
117
  "step": 36
118
  },
119
  {
120
  "epoch": 1.11,
121
  "learning_rate": 0.00014065934065934067,
122
- "loss": 2.0299,
123
  "step": 38
124
  },
125
  {
126
  "epoch": 1.17,
127
  "learning_rate": 0.00013626373626373628,
128
- "loss": 1.643,
129
  "step": 40
130
  },
131
  {
132
  "epoch": 1.23,
133
  "learning_rate": 0.00013186813186813188,
134
- "loss": 1.5875,
135
  "step": 42
136
  },
137
  {
138
  "epoch": 1.28,
139
  "learning_rate": 0.00012747252747252746,
140
- "loss": 1.5646,
141
  "step": 44
142
  },
143
  {
144
  "epoch": 1.34,
145
  "learning_rate": 0.0001230769230769231,
146
- "loss": 1.4487,
147
  "step": 46
148
  },
149
  {
150
  "epoch": 1.4,
151
  "learning_rate": 0.00011868131868131869,
152
- "loss": 1.7054,
153
  "step": 48
154
  },
155
  {
156
  "epoch": 1.46,
157
  "learning_rate": 0.00011428571428571428,
158
- "loss": 1.5121,
159
  "step": 50
160
  },
161
  {
162
  "epoch": 1.52,
163
  "learning_rate": 0.0001098901098901099,
164
- "loss": 1.2679,
165
  "step": 52
166
  },
167
  {
168
  "epoch": 1.58,
169
  "learning_rate": 0.0001054945054945055,
170
- "loss": 1.2186,
171
  "step": 54
172
  },
173
  {
174
  "epoch": 1.64,
175
  "learning_rate": 0.0001010989010989011,
176
- "loss": 1.7126,
177
  "step": 56
178
  },
179
  {
180
  "epoch": 1.69,
181
  "learning_rate": 9.670329670329671e-05,
182
- "loss": 1.4419,
183
  "step": 58
184
  },
185
  {
186
  "epoch": 1.75,
187
  "learning_rate": 9.230769230769232e-05,
188
- "loss": 1.4208,
189
  "step": 60
190
  },
191
  {
192
  "epoch": 1.81,
193
  "learning_rate": 8.791208791208791e-05,
194
- "loss": 1.5867,
195
  "step": 62
196
  },
197
  {
198
  "epoch": 1.87,
199
  "learning_rate": 8.351648351648353e-05,
200
- "loss": 1.4981,
201
  "step": 64
202
  },
203
  {
204
  "epoch": 1.93,
205
  "learning_rate": 7.912087912087912e-05,
206
- "loss": 1.5029,
207
  "step": 66
208
  },
209
  {
210
  "epoch": 1.99,
211
  "learning_rate": 7.472527472527473e-05,
212
- "loss": 1.2939,
213
  "step": 68
214
  },
215
  {
216
  "epoch": 2.04,
217
  "learning_rate": 7.032967032967034e-05,
218
- "loss": 1.6456,
219
  "step": 70
220
  },
221
  {
222
  "epoch": 2.1,
223
  "learning_rate": 6.593406593406594e-05,
224
- "loss": 1.5256,
225
  "step": 72
226
  },
227
  {
228
  "epoch": 2.16,
229
  "learning_rate": 6.153846153846155e-05,
230
- "loss": 1.2921,
231
  "step": 74
232
  },
233
  {
234
  "epoch": 2.22,
235
  "learning_rate": 5.714285714285714e-05,
236
- "loss": 1.292,
237
  "step": 76
238
  },
239
  {
240
  "epoch": 2.28,
241
  "learning_rate": 5.274725274725275e-05,
242
- "loss": 1.3151,
243
  "step": 78
244
  },
245
  {
246
  "epoch": 2.34,
247
  "learning_rate": 4.8351648351648355e-05,
248
- "loss": 1.8621,
249
  "step": 80
250
  },
251
  {
252
  "epoch": 2.39,
253
  "learning_rate": 4.3956043956043955e-05,
254
- "loss": 1.3737,
255
  "step": 82
256
  },
257
  {
258
  "epoch": 2.45,
259
  "learning_rate": 3.956043956043956e-05,
260
- "loss": 1.4477,
261
  "step": 84
262
  },
263
  {
264
  "epoch": 2.51,
265
  "learning_rate": 3.516483516483517e-05,
266
- "loss": 1.4073,
267
  "step": 86
268
  },
269
  {
270
  "epoch": 2.57,
271
  "learning_rate": 3.0769230769230774e-05,
272
- "loss": 1.4966,
273
  "step": 88
274
  },
275
  {
276
  "epoch": 2.63,
277
  "learning_rate": 2.6373626373626374e-05,
278
- "loss": 1.1487,
279
  "step": 90
280
  },
281
  {
282
  "epoch": 2.69,
283
  "learning_rate": 2.1978021978021977e-05,
284
- "loss": 1.3299,
285
  "step": 92
286
  },
287
  {
288
  "epoch": 2.74,
289
  "learning_rate": 1.7582417582417584e-05,
290
- "loss": 1.7217,
291
  "step": 94
292
  },
293
  {
294
  "epoch": 2.8,
295
  "learning_rate": 1.3186813186813187e-05,
296
- "loss": 1.2555,
297
  "step": 96
298
  },
299
  {
300
  "epoch": 2.86,
301
  "learning_rate": 8.791208791208792e-06,
302
- "loss": 1.3967,
303
  "step": 98
304
  },
305
  {
306
  "epoch": 2.92,
307
  "learning_rate": 4.395604395604396e-06,
308
- "loss": 1.5847,
309
  "step": 100
310
  },
311
  {
312
  "epoch": 2.98,
313
  "learning_rate": 0.0,
314
- "loss": 1.6002,
315
  "step": 102
316
  }
317
  ],
@@ -319,7 +319,7 @@
319
  "max_steps": 102,
320
  "num_train_epochs": 3,
321
  "save_steps": 500,
322
- "total_flos": 2.6947930854260736e+16,
323
  "trial_name": null,
324
  "trial_params": null
325
  }
 
11
  {
12
  "epoch": 0.06,
13
  "learning_rate": 3.6363636363636364e-05,
14
+ "loss": 1.8122,
15
  "step": 2
16
  },
17
  {
18
  "epoch": 0.12,
19
  "learning_rate": 7.272727272727273e-05,
20
+ "loss": 1.6058,
21
  "step": 4
22
  },
23
  {
24
  "epoch": 0.18,
25
  "learning_rate": 0.00010909090909090909,
26
+ "loss": 1.5108,
27
  "step": 6
28
  },
29
  {
30
  "epoch": 0.23,
31
  "learning_rate": 0.00014545454545454546,
32
+ "loss": 1.9854,
33
  "step": 8
34
  },
35
  {
36
  "epoch": 0.29,
37
  "learning_rate": 0.00018181818181818183,
38
+ "loss": 1.4263,
39
  "step": 10
40
  },
41
  {
42
  "epoch": 0.35,
43
  "learning_rate": 0.0001978021978021978,
44
+ "loss": 1.6944,
45
  "step": 12
46
  },
47
  {
48
  "epoch": 0.41,
49
  "learning_rate": 0.00019340659340659342,
50
+ "loss": 1.5822,
51
  "step": 14
52
  },
53
  {
54
  "epoch": 0.47,
55
  "learning_rate": 0.00018901098901098903,
56
+ "loss": 1.5416,
57
  "step": 16
58
  },
59
  {
60
  "epoch": 0.53,
61
  "learning_rate": 0.00018461538461538463,
62
+ "loss": 1.7547,
63
  "step": 18
64
  },
65
  {
66
  "epoch": 0.58,
67
  "learning_rate": 0.00018021978021978024,
68
+ "loss": 1.6478,
69
  "step": 20
70
  },
71
  {
72
  "epoch": 0.64,
73
  "learning_rate": 0.00017582417582417582,
74
+ "loss": 1.7881,
75
  "step": 22
76
  },
77
  {
78
  "epoch": 0.7,
79
  "learning_rate": 0.00017142857142857143,
80
+ "loss": 1.5457,
81
  "step": 24
82
  },
83
  {
84
  "epoch": 0.76,
85
  "learning_rate": 0.00016703296703296706,
86
+ "loss": 1.6142,
87
  "step": 26
88
  },
89
  {
90
  "epoch": 0.82,
91
  "learning_rate": 0.00016263736263736264,
92
+ "loss": 1.4016,
93
  "step": 28
94
  },
95
  {
96
  "epoch": 0.88,
97
  "learning_rate": 0.00015824175824175824,
98
+ "loss": 1.6815,
99
  "step": 30
100
  },
101
  {
102
  "epoch": 0.93,
103
  "learning_rate": 0.00015384615384615385,
104
+ "loss": 1.6923,
105
  "step": 32
106
  },
107
  {
108
  "epoch": 0.99,
109
  "learning_rate": 0.00014945054945054946,
110
+ "loss": 1.4493,
111
  "step": 34
112
  },
113
  {
114
  "epoch": 1.05,
115
  "learning_rate": 0.00014505494505494506,
116
+ "loss": 1.3942,
117
  "step": 36
118
  },
119
  {
120
  "epoch": 1.11,
121
  "learning_rate": 0.00014065934065934067,
122
+ "loss": 1.9206,
123
  "step": 38
124
  },
125
  {
126
  "epoch": 1.17,
127
  "learning_rate": 0.00013626373626373628,
128
+ "loss": 1.5305,
129
  "step": 40
130
  },
131
  {
132
  "epoch": 1.23,
133
  "learning_rate": 0.00013186813186813188,
134
+ "loss": 1.4763,
135
  "step": 42
136
  },
137
  {
138
  "epoch": 1.28,
139
  "learning_rate": 0.00012747252747252746,
140
+ "loss": 1.452,
141
  "step": 44
142
  },
143
  {
144
  "epoch": 1.34,
145
  "learning_rate": 0.0001230769230769231,
146
+ "loss": 1.322,
147
  "step": 46
148
  },
149
  {
150
  "epoch": 1.4,
151
  "learning_rate": 0.00011868131868131869,
152
+ "loss": 1.5994,
153
  "step": 48
154
  },
155
  {
156
  "epoch": 1.46,
157
  "learning_rate": 0.00011428571428571428,
158
+ "loss": 1.3866,
159
  "step": 50
160
  },
161
  {
162
  "epoch": 1.52,
163
  "learning_rate": 0.0001098901098901099,
164
+ "loss": 1.1438,
165
  "step": 52
166
  },
167
  {
168
  "epoch": 1.58,
169
  "learning_rate": 0.0001054945054945055,
170
+ "loss": 1.0993,
171
  "step": 54
172
  },
173
  {
174
  "epoch": 1.64,
175
  "learning_rate": 0.0001010989010989011,
176
+ "loss": 1.6039,
177
  "step": 56
178
  },
179
  {
180
  "epoch": 1.69,
181
  "learning_rate": 9.670329670329671e-05,
182
+ "loss": 1.3193,
183
  "step": 58
184
  },
185
  {
186
  "epoch": 1.75,
187
  "learning_rate": 9.230769230769232e-05,
188
+ "loss": 1.3037,
189
  "step": 60
190
  },
191
  {
192
  "epoch": 1.81,
193
  "learning_rate": 8.791208791208791e-05,
194
+ "loss": 1.4728,
195
  "step": 62
196
  },
197
  {
198
  "epoch": 1.87,
199
  "learning_rate": 8.351648351648353e-05,
200
+ "loss": 1.3756,
201
  "step": 64
202
  },
203
  {
204
  "epoch": 1.93,
205
  "learning_rate": 7.912087912087912e-05,
206
+ "loss": 1.3881,
207
  "step": 66
208
  },
209
  {
210
  "epoch": 1.99,
211
  "learning_rate": 7.472527472527473e-05,
212
+ "loss": 1.1797,
213
  "step": 68
214
  },
215
  {
216
  "epoch": 2.04,
217
  "learning_rate": 7.032967032967034e-05,
218
+ "loss": 1.5189,
219
  "step": 70
220
  },
221
  {
222
  "epoch": 2.1,
223
  "learning_rate": 6.593406593406594e-05,
224
+ "loss": 1.4004,
225
  "step": 72
226
  },
227
  {
228
  "epoch": 2.16,
229
  "learning_rate": 6.153846153846155e-05,
230
+ "loss": 1.1743,
231
  "step": 74
232
  },
233
  {
234
  "epoch": 2.22,
235
  "learning_rate": 5.714285714285714e-05,
236
+ "loss": 1.1663,
237
  "step": 76
238
  },
239
  {
240
  "epoch": 2.28,
241
  "learning_rate": 5.274725274725275e-05,
242
+ "loss": 1.1875,
243
  "step": 78
244
  },
245
  {
246
  "epoch": 2.34,
247
  "learning_rate": 4.8351648351648355e-05,
248
+ "loss": 1.7227,
249
  "step": 80
250
  },
251
  {
252
  "epoch": 2.39,
253
  "learning_rate": 4.3956043956043955e-05,
254
+ "loss": 1.2398,
255
  "step": 82
256
  },
257
  {
258
  "epoch": 2.45,
259
  "learning_rate": 3.956043956043956e-05,
260
+ "loss": 1.3196,
261
  "step": 84
262
  },
263
  {
264
  "epoch": 2.51,
265
  "learning_rate": 3.516483516483517e-05,
266
+ "loss": 1.2791,
267
  "step": 86
268
  },
269
  {
270
  "epoch": 2.57,
271
  "learning_rate": 3.0769230769230774e-05,
272
+ "loss": 1.3619,
273
  "step": 88
274
  },
275
  {
276
  "epoch": 2.63,
277
  "learning_rate": 2.6373626373626374e-05,
278
+ "loss": 1.0073,
279
  "step": 90
280
  },
281
  {
282
  "epoch": 2.69,
283
  "learning_rate": 2.1978021978021977e-05,
284
+ "loss": 1.1867,
285
  "step": 92
286
  },
287
  {
288
  "epoch": 2.74,
289
  "learning_rate": 1.7582417582417584e-05,
290
+ "loss": 1.605,
291
  "step": 94
292
  },
293
  {
294
  "epoch": 2.8,
295
  "learning_rate": 1.3186813186813187e-05,
296
+ "loss": 1.1101,
297
  "step": 96
298
  },
299
  {
300
  "epoch": 2.86,
301
  "learning_rate": 8.791208791208792e-06,
302
+ "loss": 1.2586,
303
  "step": 98
304
  },
305
  {
306
  "epoch": 2.92,
307
  "learning_rate": 4.395604395604396e-06,
308
+ "loss": 1.4676,
309
  "step": 100
310
  },
311
  {
312
  "epoch": 2.98,
313
  "learning_rate": 0.0,
314
+ "loss": 1.4705,
315
  "step": 102
316
  }
317
  ],
 
319
  "max_steps": 102,
320
  "num_train_epochs": 3,
321
  "save_steps": 500,
322
+ "total_flos": 2.6989001479028736e+16,
323
  "trial_name": null,
324
  "trial_params": null
325
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:26d1905ca3abf82ab3bf45211ffccc2ef759d09640a7293e39e0c1a0ddd98eb0
3
  size 4472
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e35e5509b7c25ac17c40a1eee45fbfbb580135d1a9777e8e43b88eb21c75dbea
3
  size 4472