DeepDream2045 commited on
Commit
e43d71c
·
verified ·
1 Parent(s): 7fcfeb7

Training in progress, step 30, checkpoint

Browse files
last-checkpoint/adapter_config.json CHANGED
@@ -21,12 +21,12 @@
21
  "revision": null,
22
  "target_modules": [
23
  "up_proj",
24
- "gate_proj",
25
  "v_proj",
26
  "down_proj",
27
  "o_proj",
28
  "q_proj",
29
- "k_proj"
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
21
  "revision": null,
22
  "target_modules": [
23
  "up_proj",
 
24
  "v_proj",
25
  "down_proj",
26
  "o_proj",
27
  "q_proj",
28
+ "k_proj",
29
+ "gate_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:56d434d598901331d000d69f27bf2d6a200a08071d7cddb9fcc74d618b8fdcb0
3
  size 203456160
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c0b02b117e67147afb3c7c3a338bdb17afdba34bc11a85fa2dfb3a6bcb0070c
3
  size 203456160
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:807c2c215b63a89b54f864694bcb59b5d66e08d35c2d3cb7b85205e700e1b415
3
  size 407121750
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f739240b4aea275ee6c6565aa20d628a24b80bd3232e1485686f49afea234a7
3
  size 407121750
last-checkpoint/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 1.0476467609405518,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
  "epoch": 3.1910828025477707,
5
  "eval_steps": 25,
@@ -10,7 +10,7 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.10191082802547771,
13
- "grad_norm": 0.3121834695339203,
14
  "learning_rate": 5e-05,
15
  "loss": 1.2924,
16
  "step": 1
@@ -18,220 +18,220 @@
18
  {
19
  "epoch": 0.10191082802547771,
20
  "eval_loss": 1.4096554517745972,
21
- "eval_runtime": 2.2711,
22
- "eval_samples_per_second": 29.061,
23
- "eval_steps_per_second": 3.963,
24
  "step": 1
25
  },
26
  {
27
  "epoch": 0.20382165605095542,
28
- "grad_norm": 0.2996855676174164,
29
  "learning_rate": 0.0001,
30
  "loss": 1.3123,
31
  "step": 2
32
  },
33
  {
34
  "epoch": 0.3057324840764331,
35
- "grad_norm": 0.3492814004421234,
36
  "learning_rate": 9.968561049466214e-05,
37
- "loss": 1.4114,
38
  "step": 3
39
  },
40
  {
41
  "epoch": 0.40764331210191085,
42
- "grad_norm": 0.2742891311645508,
43
  "learning_rate": 9.874639560909117e-05,
44
- "loss": 1.1823,
45
  "step": 4
46
  },
47
  {
48
  "epoch": 0.5095541401273885,
49
- "grad_norm": 0.3076689541339874,
50
  "learning_rate": 9.719416651541839e-05,
51
- "loss": 1.3595,
52
  "step": 5
53
  },
54
  {
55
  "epoch": 0.6114649681528662,
56
- "grad_norm": 0.3100813329219818,
57
  "learning_rate": 9.504844339512095e-05,
58
- "loss": 1.2393,
59
  "step": 6
60
  },
61
  {
62
  "epoch": 0.7133757961783439,
63
- "grad_norm": 0.24378710985183716,
64
  "learning_rate": 9.233620996141421e-05,
65
- "loss": 1.2006,
66
  "step": 7
67
  },
68
  {
69
  "epoch": 0.8152866242038217,
70
- "grad_norm": 0.30991846323013306,
71
  "learning_rate": 8.90915741234015e-05,
72
- "loss": 1.1693,
73
  "step": 8
74
  },
75
  {
76
  "epoch": 0.9171974522292994,
77
- "grad_norm": 0.298220694065094,
78
  "learning_rate": 8.535533905932738e-05,
79
- "loss": 1.1559,
80
  "step": 9
81
  },
82
  {
83
  "epoch": 1.0636942675159236,
84
- "grad_norm": 0.5674415826797485,
85
  "learning_rate": 8.117449009293668e-05,
86
- "loss": 1.7409,
87
  "step": 10
88
  },
89
  {
90
  "epoch": 1.1656050955414012,
91
- "grad_norm": 0.28200918436050415,
92
  "learning_rate": 7.660160382576683e-05,
93
- "loss": 0.9992,
94
  "step": 11
95
  },
96
  {
97
  "epoch": 1.267515923566879,
98
- "grad_norm": 0.25404325127601624,
99
  "learning_rate": 7.169418695587791e-05,
100
- "loss": 1.0336,
101
  "step": 12
102
  },
103
  {
104
  "epoch": 1.3694267515923566,
105
- "grad_norm": 0.2391156703233719,
106
  "learning_rate": 6.651395309775837e-05,
107
- "loss": 1.0757,
108
  "step": 13
109
  },
110
  {
111
  "epoch": 1.4713375796178343,
112
- "grad_norm": 0.2868117690086365,
113
  "learning_rate": 6.112604669781572e-05,
114
- "loss": 1.0221,
115
  "step": 14
116
  },
117
  {
118
  "epoch": 1.573248407643312,
119
- "grad_norm": 0.26096099615097046,
120
  "learning_rate": 5.559822380516539e-05,
121
- "loss": 1.1211,
122
  "step": 15
123
  },
124
  {
125
  "epoch": 1.6751592356687897,
126
- "grad_norm": 0.2496553361415863,
127
  "learning_rate": 5e-05,
128
- "loss": 1.0423,
129
  "step": 16
130
  },
131
  {
132
  "epoch": 1.7770700636942676,
133
- "grad_norm": 0.26016390323638916,
134
  "learning_rate": 4.4401776194834613e-05,
135
- "loss": 1.0078,
136
  "step": 17
137
  },
138
  {
139
  "epoch": 1.8789808917197452,
140
- "grad_norm": 0.23476140201091766,
141
  "learning_rate": 3.887395330218429e-05,
142
- "loss": 0.9879,
143
  "step": 18
144
  },
145
  {
146
  "epoch": 2.0254777070063694,
147
- "grad_norm": 0.3431682288646698,
148
  "learning_rate": 3.3486046902241664e-05,
149
- "loss": 1.6151,
150
  "step": 19
151
  },
152
  {
153
  "epoch": 2.127388535031847,
154
- "grad_norm": 0.21315336227416992,
155
  "learning_rate": 2.8305813044122097e-05,
156
- "loss": 0.9605,
157
  "step": 20
158
  },
159
  {
160
  "epoch": 2.229299363057325,
161
- "grad_norm": 0.20435573160648346,
162
  "learning_rate": 2.3398396174233178e-05,
163
  "loss": 0.925,
164
  "step": 21
165
  },
166
  {
167
  "epoch": 2.3312101910828025,
168
- "grad_norm": 0.2289644032716751,
169
  "learning_rate": 1.8825509907063327e-05,
170
- "loss": 1.032,
171
  "step": 22
172
  },
173
  {
174
  "epoch": 2.43312101910828,
175
- "grad_norm": 0.22667603194713593,
176
  "learning_rate": 1.4644660940672627e-05,
177
- "loss": 0.944,
178
  "step": 23
179
  },
180
  {
181
  "epoch": 2.535031847133758,
182
- "grad_norm": 0.21269646286964417,
183
  "learning_rate": 1.090842587659851e-05,
184
- "loss": 0.9952,
185
  "step": 24
186
  },
187
  {
188
  "epoch": 2.6369426751592355,
189
- "grad_norm": 0.21037527918815613,
190
  "learning_rate": 7.663790038585793e-06,
191
- "loss": 0.9544,
192
  "step": 25
193
  },
194
  {
195
  "epoch": 2.6369426751592355,
196
- "eval_loss": 1.0476467609405518,
197
- "eval_runtime": 2.2679,
198
- "eval_samples_per_second": 29.102,
199
- "eval_steps_per_second": 3.968,
200
  "step": 25
201
  },
202
  {
203
  "epoch": 2.738853503184713,
204
- "grad_norm": 0.2182152420282364,
205
  "learning_rate": 4.951556604879048e-06,
206
- "loss": 0.9549,
207
  "step": 26
208
  },
209
  {
210
  "epoch": 2.840764331210191,
211
- "grad_norm": 0.20187175273895264,
212
  "learning_rate": 2.8058334845816213e-06,
213
- "loss": 0.9287,
214
  "step": 27
215
  },
216
  {
217
  "epoch": 2.9426751592356686,
218
- "grad_norm": 0.4659386873245239,
219
  "learning_rate": 1.2536043909088191e-06,
220
- "loss": 1.4175,
221
  "step": 28
222
  },
223
  {
224
  "epoch": 3.089171974522293,
225
- "grad_norm": 0.2993531823158264,
226
  "learning_rate": 3.143895053378698e-07,
227
- "loss": 1.082,
228
  "step": 29
229
  },
230
  {
231
  "epoch": 3.1910828025477707,
232
- "grad_norm": 0.25595200061798096,
233
  "learning_rate": 0.0,
234
- "loss": 0.8877,
235
  "step": 30
236
  }
237
  ],
 
1
  {
2
+ "best_metric": 1.0479129552841187,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
  "epoch": 3.1910828025477707,
5
  "eval_steps": 25,
 
10
  "log_history": [
11
  {
12
  "epoch": 0.10191082802547771,
13
+ "grad_norm": 0.315826952457428,
14
  "learning_rate": 5e-05,
15
  "loss": 1.2924,
16
  "step": 1
 
18
  {
19
  "epoch": 0.10191082802547771,
20
  "eval_loss": 1.4096554517745972,
21
+ "eval_runtime": 2.2855,
22
+ "eval_samples_per_second": 28.878,
23
+ "eval_steps_per_second": 3.938,
24
  "step": 1
25
  },
26
  {
27
  "epoch": 0.20382165605095542,
28
+ "grad_norm": 0.30153176188468933,
29
  "learning_rate": 0.0001,
30
  "loss": 1.3123,
31
  "step": 2
32
  },
33
  {
34
  "epoch": 0.3057324840764331,
35
+ "grad_norm": 0.35216328501701355,
36
  "learning_rate": 9.968561049466214e-05,
37
+ "loss": 1.4112,
38
  "step": 3
39
  },
40
  {
41
  "epoch": 0.40764331210191085,
42
+ "grad_norm": 0.27521029114723206,
43
  "learning_rate": 9.874639560909117e-05,
44
+ "loss": 1.1817,
45
  "step": 4
46
  },
47
  {
48
  "epoch": 0.5095541401273885,
49
+ "grad_norm": 0.3043312728404999,
50
  "learning_rate": 9.719416651541839e-05,
51
+ "loss": 1.3587,
52
  "step": 5
53
  },
54
  {
55
  "epoch": 0.6114649681528662,
56
+ "grad_norm": 0.3067076504230499,
57
  "learning_rate": 9.504844339512095e-05,
58
+ "loss": 1.2378,
59
  "step": 6
60
  },
61
  {
62
  "epoch": 0.7133757961783439,
63
+ "grad_norm": 0.24411499500274658,
64
  "learning_rate": 9.233620996141421e-05,
65
+ "loss": 1.2001,
66
  "step": 7
67
  },
68
  {
69
  "epoch": 0.8152866242038217,
70
+ "grad_norm": 0.31167352199554443,
71
  "learning_rate": 8.90915741234015e-05,
72
+ "loss": 1.1681,
73
  "step": 8
74
  },
75
  {
76
  "epoch": 0.9171974522292994,
77
+ "grad_norm": 0.2961890995502472,
78
  "learning_rate": 8.535533905932738e-05,
79
+ "loss": 1.1551,
80
  "step": 9
81
  },
82
  {
83
  "epoch": 1.0636942675159236,
84
+ "grad_norm": 0.5746045112609863,
85
  "learning_rate": 8.117449009293668e-05,
86
+ "loss": 1.7392,
87
  "step": 10
88
  },
89
  {
90
  "epoch": 1.1656050955414012,
91
+ "grad_norm": 0.28287041187286377,
92
  "learning_rate": 7.660160382576683e-05,
93
+ "loss": 0.9983,
94
  "step": 11
95
  },
96
  {
97
  "epoch": 1.267515923566879,
98
+ "grad_norm": 0.26368194818496704,
99
  "learning_rate": 7.169418695587791e-05,
100
+ "loss": 1.0329,
101
  "step": 12
102
  },
103
  {
104
  "epoch": 1.3694267515923566,
105
+ "grad_norm": 0.24134495854377747,
106
  "learning_rate": 6.651395309775837e-05,
107
+ "loss": 1.0751,
108
  "step": 13
109
  },
110
  {
111
  "epoch": 1.4713375796178343,
112
+ "grad_norm": 0.28836143016815186,
113
  "learning_rate": 6.112604669781572e-05,
114
+ "loss": 1.022,
115
  "step": 14
116
  },
117
  {
118
  "epoch": 1.573248407643312,
119
+ "grad_norm": 0.2660194933414459,
120
  "learning_rate": 5.559822380516539e-05,
121
+ "loss": 1.1208,
122
  "step": 15
123
  },
124
  {
125
  "epoch": 1.6751592356687897,
126
+ "grad_norm": 0.24954141676425934,
127
  "learning_rate": 5e-05,
128
+ "loss": 1.0427,
129
  "step": 16
130
  },
131
  {
132
  "epoch": 1.7770700636942676,
133
+ "grad_norm": 0.26790428161621094,
134
  "learning_rate": 4.4401776194834613e-05,
135
+ "loss": 1.0076,
136
  "step": 17
137
  },
138
  {
139
  "epoch": 1.8789808917197452,
140
+ "grad_norm": 0.23538947105407715,
141
  "learning_rate": 3.887395330218429e-05,
142
+ "loss": 0.9877,
143
  "step": 18
144
  },
145
  {
146
  "epoch": 2.0254777070063694,
147
+ "grad_norm": 0.346373051404953,
148
  "learning_rate": 3.3486046902241664e-05,
149
+ "loss": 1.6144,
150
  "step": 19
151
  },
152
  {
153
  "epoch": 2.127388535031847,
154
+ "grad_norm": 0.21446581184864044,
155
  "learning_rate": 2.8305813044122097e-05,
156
+ "loss": 0.9596,
157
  "step": 20
158
  },
159
  {
160
  "epoch": 2.229299363057325,
161
+ "grad_norm": 0.20357617735862732,
162
  "learning_rate": 2.3398396174233178e-05,
163
  "loss": 0.925,
164
  "step": 21
165
  },
166
  {
167
  "epoch": 2.3312101910828025,
168
+ "grad_norm": 0.2289550006389618,
169
  "learning_rate": 1.8825509907063327e-05,
170
+ "loss": 1.0315,
171
  "step": 22
172
  },
173
  {
174
  "epoch": 2.43312101910828,
175
+ "grad_norm": 0.22605831921100616,
176
  "learning_rate": 1.4644660940672627e-05,
177
+ "loss": 0.9437,
178
  "step": 23
179
  },
180
  {
181
  "epoch": 2.535031847133758,
182
+ "grad_norm": 0.21340759098529816,
183
  "learning_rate": 1.090842587659851e-05,
184
+ "loss": 0.9948,
185
  "step": 24
186
  },
187
  {
188
  "epoch": 2.6369426751592355,
189
+ "grad_norm": 0.21240516006946564,
190
  "learning_rate": 7.663790038585793e-06,
191
+ "loss": 0.954,
192
  "step": 25
193
  },
194
  {
195
  "epoch": 2.6369426751592355,
196
+ "eval_loss": 1.0479129552841187,
197
+ "eval_runtime": 2.2831,
198
+ "eval_samples_per_second": 28.908,
199
+ "eval_steps_per_second": 3.942,
200
  "step": 25
201
  },
202
  {
203
  "epoch": 2.738853503184713,
204
+ "grad_norm": 0.21941721439361572,
205
  "learning_rate": 4.951556604879048e-06,
206
+ "loss": 0.9543,
207
  "step": 26
208
  },
209
  {
210
  "epoch": 2.840764331210191,
211
+ "grad_norm": 0.19712556898593903,
212
  "learning_rate": 2.8058334845816213e-06,
213
+ "loss": 0.9282,
214
  "step": 27
215
  },
216
  {
217
  "epoch": 2.9426751592356686,
218
+ "grad_norm": 0.4711575210094452,
219
  "learning_rate": 1.2536043909088191e-06,
220
+ "loss": 1.4179,
221
  "step": 28
222
  },
223
  {
224
  "epoch": 3.089171974522293,
225
+ "grad_norm": 0.30187803506851196,
226
  "learning_rate": 3.143895053378698e-07,
227
+ "loss": 1.0809,
228
  "step": 29
229
  },
230
  {
231
  "epoch": 3.1910828025477707,
232
+ "grad_norm": 0.25770440697669983,
233
  "learning_rate": 0.0,
234
+ "loss": 0.8874,
235
  "step": 30
236
  }
237
  ],
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9feb44dd06351a4ebb3399d9273df0fe7c81cda65ffedc861c36f176fba73ef5
3
  size 6776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11310abb03160086896271409f285f645e098cc1d2c620a9c8e344ab93359699
3
  size 6776