DeepDream2045 commited on
Commit
eb6333e
1 Parent(s): a2f239a

Training in progress, step 50, checkpoint

Browse files
last-checkpoint/adapter_config.json CHANGED
@@ -20,13 +20,13 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "up_proj",
24
- "k_proj",
25
- "gate_proj",
26
  "q_proj",
 
 
27
  "down_proj",
28
- "v_proj",
29
- "o_proj"
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
 
 
23
  "q_proj",
24
+ "gate_proj",
25
+ "o_proj",
26
  "down_proj",
27
+ "up_proj",
28
+ "k_proj",
29
+ "v_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 sha256:0ff36bf9c3d605bf4fd2f18ad5d7ba9a006eaf187d403e11fe9655678f2ccaaf
3
  size 432223744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cdad695471ac5ebe1288a36a991fb68aa3a4df78e52765c1b084596c758dd4d
3
  size 432223744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f2db582d2898890a5a35f9ea78fe2eeb1738011c8d6ebbd89fdda3c22f73a42
3
  size 864785974
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07084887e9f9ab1c4f8931c6516ecd1497bb7307b3232f0def48593f713e74a1
3
  size 864785974
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c3d3b7a4a0b65f1ef2a79121dcc36f0f46eec4e9c1f11e716bee10a5e99ef92f
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ecdfeb4ea872cf0b22fba2a4a5b49827313d1db0a60ec289a0450ef8689f90b
3
  size 15024
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d621dd152a81ceefcc6d5bc8b659af40b059d8f66901d5617810de558ea00786
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72c9642b537a002260f157de61a35183ce8c31d54ef4a119842de582faf6851b
3
  size 15024
last-checkpoint/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a72dbdd06a160ef49790154c5ffb1bdabd6bc430d3425ac68abaddefc26f687a
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9623f940cc98fa5ce48c7c451ba6138228d9924f883248f3ad6342bbfa49453
3
  size 15024
last-checkpoint/rng_state_3.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ab0db3accd686bcb39bcef79ea6b326c5ddeba4f6221bc32e79fe54bd5ade06
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e71c64ff5dc134b563f75857c691dc2d3e69683266ad3b7566169a083142d621
3
  size 15024
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,16 +1,16 @@
1
  {
2
- "best_metric": 0.7922340035438538,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.7326007326007326,
5
  "eval_steps": 25,
6
- "global_step": 25,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
  "epoch": 0.029304029304029304,
13
- "grad_norm": 42.315101623535156,
14
  "learning_rate": 5e-05,
15
  "loss": 10.8108,
16
  "step": 1
@@ -18,186 +18,369 @@
18
  {
19
  "epoch": 0.029304029304029304,
20
  "eval_loss": 11.66943359375,
21
- "eval_runtime": 12.0921,
22
- "eval_samples_per_second": 19.021,
23
- "eval_steps_per_second": 2.398,
24
  "step": 1
25
  },
26
  {
27
  "epoch": 0.05860805860805861,
28
- "grad_norm": 43.577064514160156,
29
  "learning_rate": 0.0001,
30
  "loss": 11.4368,
31
  "step": 2
32
  },
33
  {
34
  "epoch": 0.08791208791208792,
35
- "grad_norm": 31.090862274169922,
36
  "learning_rate": 9.989294616193017e-05,
37
- "loss": 8.1051,
38
  "step": 3
39
  },
40
  {
41
  "epoch": 0.11721611721611722,
42
- "grad_norm": 17.739784240722656,
43
  "learning_rate": 9.957224306869053e-05,
44
- "loss": 3.8912,
45
  "step": 4
46
  },
47
  {
48
  "epoch": 0.14652014652014653,
49
- "grad_norm": 10.802330017089844,
50
  "learning_rate": 9.903926402016153e-05,
51
- "loss": 2.2566,
52
  "step": 5
53
  },
54
  {
55
  "epoch": 0.17582417582417584,
56
- "grad_norm": 4.046825408935547,
57
  "learning_rate": 9.829629131445342e-05,
58
- "loss": 1.178,
59
  "step": 6
60
  },
61
  {
62
  "epoch": 0.20512820512820512,
63
- "grad_norm": 4.262223720550537,
64
  "learning_rate": 9.73465064747553e-05,
65
- "loss": 1.0102,
66
  "step": 7
67
  },
68
  {
69
  "epoch": 0.23443223443223443,
70
- "grad_norm": 2.372178792953491,
71
  "learning_rate": 9.619397662556435e-05,
72
- "loss": 0.9741,
73
  "step": 8
74
  },
75
  {
76
  "epoch": 0.26373626373626374,
77
- "grad_norm": 1.6314536333084106,
78
  "learning_rate": 9.484363707663442e-05,
79
- "loss": 0.8676,
80
  "step": 9
81
  },
82
  {
83
  "epoch": 0.29304029304029305,
84
- "grad_norm": 1.1375904083251953,
85
  "learning_rate": 9.330127018922194e-05,
86
- "loss": 0.7656,
87
  "step": 10
88
  },
89
  {
90
  "epoch": 0.32234432234432236,
91
- "grad_norm": 0.7322179675102234,
92
  "learning_rate": 9.157348061512727e-05,
93
- "loss": 0.738,
94
  "step": 11
95
  },
96
  {
97
  "epoch": 0.3516483516483517,
98
- "grad_norm": 1.6381927728652954,
99
  "learning_rate": 8.966766701456177e-05,
100
- "loss": 0.8121,
101
  "step": 12
102
  },
103
  {
104
  "epoch": 0.38095238095238093,
105
- "grad_norm": 1.6779375076293945,
106
  "learning_rate": 8.759199037394887e-05,
107
- "loss": 0.7658,
108
  "step": 13
109
  },
110
  {
111
  "epoch": 0.41025641025641024,
112
- "grad_norm": 0.8208694458007812,
113
  "learning_rate": 8.535533905932738e-05,
114
- "loss": 0.8118,
115
  "step": 14
116
  },
117
  {
118
  "epoch": 0.43956043956043955,
119
- "grad_norm": 0.7266029119491577,
120
  "learning_rate": 8.296729075500344e-05,
121
- "loss": 0.8152,
122
  "step": 15
123
  },
124
  {
125
  "epoch": 0.46886446886446886,
126
- "grad_norm": 0.49156033992767334,
127
  "learning_rate": 8.043807145043604e-05,
128
- "loss": 0.8198,
129
  "step": 16
130
  },
131
  {
132
  "epoch": 0.4981684981684982,
133
- "grad_norm": 0.6357100009918213,
134
  "learning_rate": 7.777851165098012e-05,
135
- "loss": 0.8063,
136
  "step": 17
137
  },
138
  {
139
  "epoch": 0.5274725274725275,
140
- "grad_norm": 0.6192078590393066,
141
  "learning_rate": 7.500000000000001e-05,
142
- "loss": 0.7221,
143
  "step": 18
144
  },
145
  {
146
  "epoch": 0.5567765567765568,
147
- "grad_norm": 0.23790700733661652,
148
  "learning_rate": 7.211443451095007e-05,
149
- "loss": 0.7403,
150
  "step": 19
151
  },
152
  {
153
  "epoch": 0.5860805860805861,
154
- "grad_norm": 0.3375350534915924,
155
  "learning_rate": 6.91341716182545e-05,
156
- "loss": 0.7381,
157
  "step": 20
158
  },
159
  {
160
  "epoch": 0.6153846153846154,
161
- "grad_norm": 0.7117923498153687,
162
  "learning_rate": 6.607197326515808e-05,
163
- "loss": 0.7848,
164
  "step": 21
165
  },
166
  {
167
  "epoch": 0.6446886446886447,
168
- "grad_norm": 1.3936290740966797,
169
  "learning_rate": 6.294095225512603e-05,
170
- "loss": 0.8916,
171
  "step": 22
172
  },
173
  {
174
  "epoch": 0.673992673992674,
175
- "grad_norm": 0.8301817178726196,
176
  "learning_rate": 5.9754516100806423e-05,
177
- "loss": 0.83,
178
  "step": 23
179
  },
180
  {
181
  "epoch": 0.7032967032967034,
182
- "grad_norm": 0.2933414578437805,
183
  "learning_rate": 5.6526309611002594e-05,
184
- "loss": 0.8132,
185
  "step": 24
186
  },
187
  {
188
  "epoch": 0.7326007326007326,
189
- "grad_norm": 0.3536495268344879,
190
  "learning_rate": 5.327015646150716e-05,
191
- "loss": 0.8106,
192
  "step": 25
193
  },
194
  {
195
  "epoch": 0.7326007326007326,
196
- "eval_loss": 0.7922340035438538,
197
- "eval_runtime": 12.0794,
198
- "eval_samples_per_second": 19.041,
199
- "eval_steps_per_second": 2.401,
200
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
201
  }
202
  ],
203
  "logging_steps": 1,
@@ -221,12 +404,12 @@
221
  "should_evaluate": false,
222
  "should_log": false,
223
  "should_save": true,
224
- "should_training_stop": false
225
  },
226
  "attributes": {}
227
  }
228
  },
229
- "total_flos": 3.315690861756416e+17,
230
  "train_batch_size": 2,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.7666683197021484,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 1.4652014652014653,
5
  "eval_steps": 25,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
  "epoch": 0.029304029304029304,
13
+ "grad_norm": 42.63615417480469,
14
  "learning_rate": 5e-05,
15
  "loss": 10.8108,
16
  "step": 1
 
18
  {
19
  "epoch": 0.029304029304029304,
20
  "eval_loss": 11.66943359375,
21
+ "eval_runtime": 12.0274,
22
+ "eval_samples_per_second": 19.123,
23
+ "eval_steps_per_second": 2.411,
24
  "step": 1
25
  },
26
  {
27
  "epoch": 0.05860805860805861,
28
+ "grad_norm": 43.70536804199219,
29
  "learning_rate": 0.0001,
30
  "loss": 11.4368,
31
  "step": 2
32
  },
33
  {
34
  "epoch": 0.08791208791208792,
35
+ "grad_norm": 30.874406814575195,
36
  "learning_rate": 9.989294616193017e-05,
37
+ "loss": 8.1072,
38
  "step": 3
39
  },
40
  {
41
  "epoch": 0.11721611721611722,
42
+ "grad_norm": 17.766359329223633,
43
  "learning_rate": 9.957224306869053e-05,
44
+ "loss": 3.914,
45
  "step": 4
46
  },
47
  {
48
  "epoch": 0.14652014652014653,
49
+ "grad_norm": 10.942605972290039,
50
  "learning_rate": 9.903926402016153e-05,
51
+ "loss": 2.2661,
52
  "step": 5
53
  },
54
  {
55
  "epoch": 0.17582417582417584,
56
+ "grad_norm": 4.077508926391602,
57
  "learning_rate": 9.829629131445342e-05,
58
+ "loss": 1.1809,
59
  "step": 6
60
  },
61
  {
62
  "epoch": 0.20512820512820512,
63
+ "grad_norm": 4.200634479522705,
64
  "learning_rate": 9.73465064747553e-05,
65
+ "loss": 1.0111,
66
  "step": 7
67
  },
68
  {
69
  "epoch": 0.23443223443223443,
70
+ "grad_norm": 2.5703258514404297,
71
  "learning_rate": 9.619397662556435e-05,
72
+ "loss": 0.9798,
73
  "step": 8
74
  },
75
  {
76
  "epoch": 0.26373626373626374,
77
+ "grad_norm": 1.4646650552749634,
78
  "learning_rate": 9.484363707663442e-05,
79
+ "loss": 0.8646,
80
  "step": 9
81
  },
82
  {
83
  "epoch": 0.29304029304029305,
84
+ "grad_norm": 1.0245696306228638,
85
  "learning_rate": 9.330127018922194e-05,
86
+ "loss": 0.7594,
87
  "step": 10
88
  },
89
  {
90
  "epoch": 0.32234432234432236,
91
+ "grad_norm": 0.7607440948486328,
92
  "learning_rate": 9.157348061512727e-05,
93
+ "loss": 0.7369,
94
  "step": 11
95
  },
96
  {
97
  "epoch": 0.3516483516483517,
98
+ "grad_norm": 1.600371241569519,
99
  "learning_rate": 8.966766701456177e-05,
100
+ "loss": 0.8084,
101
  "step": 12
102
  },
103
  {
104
  "epoch": 0.38095238095238093,
105
+ "grad_norm": 1.577329397201538,
106
  "learning_rate": 8.759199037394887e-05,
107
+ "loss": 0.7607,
108
  "step": 13
109
  },
110
  {
111
  "epoch": 0.41025641025641024,
112
+ "grad_norm": 1.0018422603607178,
113
  "learning_rate": 8.535533905932738e-05,
114
+ "loss": 0.8165,
115
  "step": 14
116
  },
117
  {
118
  "epoch": 0.43956043956043955,
119
+ "grad_norm": 0.8424701690673828,
120
  "learning_rate": 8.296729075500344e-05,
121
+ "loss": 0.8129,
122
  "step": 15
123
  },
124
  {
125
  "epoch": 0.46886446886446886,
126
+ "grad_norm": 0.5086039900779724,
127
  "learning_rate": 8.043807145043604e-05,
128
+ "loss": 0.8195,
129
  "step": 16
130
  },
131
  {
132
  "epoch": 0.4981684981684982,
133
+ "grad_norm": 0.6842309236526489,
134
  "learning_rate": 7.777851165098012e-05,
135
+ "loss": 0.8075,
136
  "step": 17
137
  },
138
  {
139
  "epoch": 0.5274725274725275,
140
+ "grad_norm": 0.6705095767974854,
141
  "learning_rate": 7.500000000000001e-05,
142
+ "loss": 0.7247,
143
  "step": 18
144
  },
145
  {
146
  "epoch": 0.5567765567765568,
147
+ "grad_norm": 0.24981459975242615,
148
  "learning_rate": 7.211443451095007e-05,
149
+ "loss": 0.741,
150
  "step": 19
151
  },
152
  {
153
  "epoch": 0.5860805860805861,
154
+ "grad_norm": 0.3129333257675171,
155
  "learning_rate": 6.91341716182545e-05,
156
+ "loss": 0.7393,
157
  "step": 20
158
  },
159
  {
160
  "epoch": 0.6153846153846154,
161
+ "grad_norm": 0.7338513135910034,
162
  "learning_rate": 6.607197326515808e-05,
163
+ "loss": 0.7904,
164
  "step": 21
165
  },
166
  {
167
  "epoch": 0.6446886446886447,
168
+ "grad_norm": 1.3784418106079102,
169
  "learning_rate": 6.294095225512603e-05,
170
+ "loss": 0.8909,
171
  "step": 22
172
  },
173
  {
174
  "epoch": 0.673992673992674,
175
+ "grad_norm": 0.8394548296928406,
176
  "learning_rate": 5.9754516100806423e-05,
177
+ "loss": 0.8305,
178
  "step": 23
179
  },
180
  {
181
  "epoch": 0.7032967032967034,
182
+ "grad_norm": 0.29354768991470337,
183
  "learning_rate": 5.6526309611002594e-05,
184
+ "loss": 0.8116,
185
  "step": 24
186
  },
187
  {
188
  "epoch": 0.7326007326007326,
189
+ "grad_norm": 0.3640207350254059,
190
  "learning_rate": 5.327015646150716e-05,
191
+ "loss": 0.8095,
192
  "step": 25
193
  },
194
  {
195
  "epoch": 0.7326007326007326,
196
+ "eval_loss": 0.789313018321991,
197
+ "eval_runtime": 12.0233,
198
+ "eval_samples_per_second": 19.13,
199
+ "eval_steps_per_second": 2.412,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.7619047619047619,
204
+ "grad_norm": 0.6007457375526428,
205
+ "learning_rate": 5e-05,
206
+ "loss": 0.8029,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.7912087912087912,
211
+ "grad_norm": 1.0814050436019897,
212
+ "learning_rate": 4.6729843538492847e-05,
213
+ "loss": 0.7535,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.8205128205128205,
218
+ "grad_norm": 0.8970361351966858,
219
+ "learning_rate": 4.347369038899744e-05,
220
+ "loss": 0.7552,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.8498168498168498,
225
+ "grad_norm": 0.5584169030189514,
226
+ "learning_rate": 4.0245483899193595e-05,
227
+ "loss": 0.772,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.8791208791208791,
232
+ "grad_norm": 0.19214436411857605,
233
+ "learning_rate": 3.705904774487396e-05,
234
+ "loss": 0.7811,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.9084249084249084,
239
+ "grad_norm": 0.4855462312698364,
240
+ "learning_rate": 3.392802673484193e-05,
241
+ "loss": 0.8256,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.9377289377289377,
246
+ "grad_norm": 0.5026677250862122,
247
+ "learning_rate": 3.086582838174551e-05,
248
+ "loss": 0.8139,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.967032967032967,
253
+ "grad_norm": 1.100959062576294,
254
+ "learning_rate": 2.7885565489049946e-05,
255
+ "loss": 0.8822,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.9963369963369964,
260
+ "grad_norm": 0.678441047668457,
261
+ "learning_rate": 2.500000000000001e-05,
262
+ "loss": 0.8372,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 1.0256410256410255,
267
+ "grad_norm": 1.023532748222351,
268
+ "learning_rate": 2.2221488349019903e-05,
269
+ "loss": 1.4417,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 1.054945054945055,
274
+ "grad_norm": 0.5481376647949219,
275
+ "learning_rate": 1.9561928549563968e-05,
276
+ "loss": 0.7156,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 1.0842490842490842,
281
+ "grad_norm": 0.5916444659233093,
282
+ "learning_rate": 1.703270924499656e-05,
283
+ "loss": 0.7388,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 1.1135531135531136,
288
+ "grad_norm": 0.48780718445777893,
289
+ "learning_rate": 1.4644660940672627e-05,
290
+ "loss": 0.7178,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 1.1428571428571428,
295
+ "grad_norm": 0.8632380366325378,
296
+ "learning_rate": 1.2408009626051137e-05,
297
+ "loss": 0.8168,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 1.1721611721611722,
302
+ "grad_norm": 0.6176807284355164,
303
+ "learning_rate": 1.0332332985438248e-05,
304
+ "loss": 0.8144,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 1.2014652014652014,
309
+ "grad_norm": 0.3913164436817169,
310
+ "learning_rate": 8.426519384872733e-06,
311
+ "loss": 0.7581,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 1.2307692307692308,
316
+ "grad_norm": 0.5620902180671692,
317
+ "learning_rate": 6.698729810778065e-06,
318
+ "loss": 0.8182,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 1.26007326007326,
323
+ "grad_norm": 0.5761415362358093,
324
+ "learning_rate": 5.156362923365588e-06,
325
+ "loss": 0.793,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 1.2893772893772895,
330
+ "grad_norm": 0.623988926410675,
331
+ "learning_rate": 3.8060233744356633e-06,
332
+ "loss": 0.7259,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 1.3186813186813187,
337
+ "grad_norm": 0.6083937287330627,
338
+ "learning_rate": 2.653493525244721e-06,
339
+ "loss": 0.7406,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 1.347985347985348,
344
+ "grad_norm": 0.6067966818809509,
345
+ "learning_rate": 1.70370868554659e-06,
346
+ "loss": 0.7433,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 1.3772893772893773,
351
+ "grad_norm": 0.5738537311553955,
352
+ "learning_rate": 9.607359798384785e-07,
353
+ "loss": 0.7611,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 1.4065934065934065,
358
+ "grad_norm": 0.5093715190887451,
359
+ "learning_rate": 4.277569313094809e-07,
360
+ "loss": 0.7872,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 1.435897435897436,
365
+ "grad_norm": 0.4598458707332611,
366
+ "learning_rate": 1.0705383806982606e-07,
367
+ "loss": 0.804,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 1.4652014652014653,
372
+ "grad_norm": 0.6957669258117676,
373
+ "learning_rate": 0.0,
374
+ "loss": 0.8004,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 1.4652014652014653,
379
+ "eval_loss": 0.7666683197021484,
380
+ "eval_runtime": 12.0189,
381
+ "eval_samples_per_second": 19.137,
382
+ "eval_steps_per_second": 2.413,
383
+ "step": 50
384
  }
385
  ],
386
  "logging_steps": 1,
 
404
  "should_evaluate": false,
405
  "should_log": false,
406
  "should_save": true,
407
+ "should_training_stop": true
408
  },
409
  "attributes": {}
410
  }
411
  },
412
+ "total_flos": 6.631381723512832e+17,
413
  "train_batch_size": 2,
414
  "trial_name": null,
415
  "trial_params": null
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:071494bbe95931a08631bf47f2dba38f70b866d5bb370d5380baf7279eff516c
3
  size 6776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:768050f293879227102c7c91bc296e82e7ed39164763de483fc202082d0b9cf5
3
  size 6776