neginr commited on
Commit
12eef21
·
verified ·
1 Parent(s): 9223a0d

Training in progress, epoch 5

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3bc918f9d513794d256a27dddb9e84a9b7d6a27cd51bc2daf6d0b9d60a6cf8a5
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9567c0f87542e5db4273c97cdb18de47bcd656a9afa9b411df2dbb2954f04086
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3fe70bc2fe80d5327ab34208c9d3416dc8d61acd5a3d01093d9232980b3446d4
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d44041a21ae7ade9da55fe3f3aa3f675c85e69da7a67684c91bcdcc50773de6c
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:47cec3f27639824f0365cf284921afd611117afe0bd538194c758c43787d6898
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:967811c0aeba0ca8c4efba0164f2e68a3c1a183717178e64cb24d2a3970e0570
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a7db0b4d05d1a6d7a122b4264bde486ea4eb8da47b46e3c98e7d31bdecea76fd
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e1ee9a616eb17eb39dbab23e0767af4a5f41274dc10e5d4b244509080e9a909
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -137,3 +137,36 @@
137
  {"current_steps": 137, "total_steps": 231, "loss": 0.3083, "lr": 8.56319634123092e-06, "epoch": 4.151515151515151, "percentage": 59.31, "elapsed_time": "1:01:56", "remaining_time": "0:42:29"}
138
  {"current_steps": 138, "total_steps": 231, "loss": 0.2441, "lr": 8.413174535437486e-06, "epoch": 4.181818181818182, "percentage": 59.74, "elapsed_time": "1:02:19", "remaining_time": "0:41:59"}
139
  {"current_steps": 139, "total_steps": 231, "loss": 0.3123, "lr": 8.263518223330698e-06, "epoch": 4.212121212121212, "percentage": 60.17, "elapsed_time": "1:02:47", "remaining_time": "0:41:33"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
137
  {"current_steps": 137, "total_steps": 231, "loss": 0.3083, "lr": 8.56319634123092e-06, "epoch": 4.151515151515151, "percentage": 59.31, "elapsed_time": "1:01:56", "remaining_time": "0:42:29"}
138
  {"current_steps": 138, "total_steps": 231, "loss": 0.2441, "lr": 8.413174535437486e-06, "epoch": 4.181818181818182, "percentage": 59.74, "elapsed_time": "1:02:19", "remaining_time": "0:41:59"}
139
  {"current_steps": 139, "total_steps": 231, "loss": 0.3123, "lr": 8.263518223330698e-06, "epoch": 4.212121212121212, "percentage": 60.17, "elapsed_time": "1:02:47", "remaining_time": "0:41:33"}
140
+ {"current_steps": 140, "total_steps": 231, "loss": 0.2743, "lr": 8.114261875265643e-06, "epoch": 4.242424242424242, "percentage": 60.61, "elapsed_time": "1:03:11", "remaining_time": "0:41:04"}
141
+ {"current_steps": 141, "total_steps": 231, "loss": 0.2624, "lr": 7.965439869473664e-06, "epoch": 4.2727272727272725, "percentage": 61.04, "elapsed_time": "1:03:34", "remaining_time": "0:40:34"}
142
+ {"current_steps": 142, "total_steps": 231, "loss": 0.2715, "lr": 7.817086484143987e-06, "epoch": 4.303030303030303, "percentage": 61.47, "elapsed_time": "1:03:59", "remaining_time": "0:40:06"}
143
+ {"current_steps": 143, "total_steps": 231, "loss": 0.2575, "lr": 7.669235889528436e-06, "epoch": 4.333333333333333, "percentage": 61.9, "elapsed_time": "1:04:26", "remaining_time": "0:39:39"}
144
+ {"current_steps": 144, "total_steps": 231, "loss": 0.2988, "lr": 7.521922140071003e-06, "epoch": 4.363636363636363, "percentage": 62.34, "elapsed_time": "1:04:51", "remaining_time": "0:39:10"}
145
+ {"current_steps": 145, "total_steps": 231, "loss": 0.2926, "lr": 7.375179166564062e-06, "epoch": 4.393939393939394, "percentage": 62.77, "elapsed_time": "1:05:14", "remaining_time": "0:38:41"}
146
+ {"current_steps": 146, "total_steps": 231, "loss": 0.2383, "lr": 7.2290407683331154e-06, "epoch": 4.424242424242424, "percentage": 63.2, "elapsed_time": "1:05:34", "remaining_time": "0:38:10"}
147
+ {"current_steps": 147, "total_steps": 231, "loss": 0.287, "lr": 7.0835406054517505e-06, "epoch": 4.454545454545454, "percentage": 63.64, "elapsed_time": "1:06:02", "remaining_time": "0:37:44"}
148
+ {"current_steps": 148, "total_steps": 231, "loss": 0.2588, "lr": 6.93871219098876e-06, "epoch": 4.484848484848484, "percentage": 64.07, "elapsed_time": "1:06:22", "remaining_time": "0:37:13"}
149
+ {"current_steps": 149, "total_steps": 231, "loss": 0.244, "lr": 6.79458888328903e-06, "epoch": 4.515151515151516, "percentage": 64.5, "elapsed_time": "1:06:45", "remaining_time": "0:36:44"}
150
+ {"current_steps": 150, "total_steps": 231, "loss": 0.2465, "lr": 6.651203878290139e-06, "epoch": 4.545454545454545, "percentage": 64.94, "elapsed_time": "1:07:02", "remaining_time": "0:36:12"}
151
+ {"current_steps": 151, "total_steps": 231, "loss": 0.2803, "lr": 6.508590201876317e-06, "epoch": 4.575757575757576, "percentage": 65.37, "elapsed_time": "1:07:28", "remaining_time": "0:35:44"}
152
+ {"current_steps": 152, "total_steps": 231, "loss": 0.2594, "lr": 6.366780702271589e-06, "epoch": 4.606060606060606, "percentage": 65.8, "elapsed_time": "1:07:50", "remaining_time": "0:35:15"}
153
+ {"current_steps": 153, "total_steps": 231, "loss": 0.2487, "lr": 6.225808042473857e-06, "epoch": 4.636363636363637, "percentage": 66.23, "elapsed_time": "1:08:16", "remaining_time": "0:34:48"}
154
+ {"current_steps": 154, "total_steps": 231, "loss": 0.3245, "lr": 6.085704692731609e-06, "epoch": 4.666666666666667, "percentage": 66.67, "elapsed_time": "1:08:38", "remaining_time": "0:34:19"}
155
+ {"current_steps": 155, "total_steps": 231, "loss": 0.2676, "lr": 5.946502923065054e-06, "epoch": 4.696969696969697, "percentage": 67.1, "elapsed_time": "1:09:01", "remaining_time": "0:33:50"}
156
+ {"current_steps": 156, "total_steps": 231, "loss": 0.2264, "lr": 5.8082347958333625e-06, "epoch": 4.7272727272727275, "percentage": 67.53, "elapsed_time": "1:09:22", "remaining_time": "0:33:21"}
157
+ {"current_steps": 157, "total_steps": 231, "loss": 0.24, "lr": 5.670932158349732e-06, "epoch": 4.757575757575758, "percentage": 67.97, "elapsed_time": "1:09:46", "remaining_time": "0:32:53"}
158
+ {"current_steps": 158, "total_steps": 231, "loss": 0.2404, "lr": 5.534626635546e-06, "epoch": 4.787878787878788, "percentage": 68.4, "elapsed_time": "1:10:09", "remaining_time": "0:32:24"}
159
+ {"current_steps": 159, "total_steps": 231, "loss": 0.3006, "lr": 5.399349622688479e-06, "epoch": 4.818181818181818, "percentage": 68.83, "elapsed_time": "1:10:32", "remaining_time": "0:31:56"}
160
+ {"current_steps": 160, "total_steps": 231, "loss": 0.2884, "lr": 5.2651322781466606e-06, "epoch": 4.848484848484849, "percentage": 69.26, "elapsed_time": "1:10:52", "remaining_time": "0:31:27"}
161
+ {"current_steps": 161, "total_steps": 231, "loss": 0.269, "lr": 5.132005516216512e-06, "epoch": 4.878787878787879, "percentage": 69.7, "elapsed_time": "1:11:10", "remaining_time": "0:30:56"}
162
+ {"current_steps": 162, "total_steps": 231, "loss": 0.2861, "lr": 5.000000000000003e-06, "epoch": 4.909090909090909, "percentage": 70.13, "elapsed_time": "1:11:36", "remaining_time": "0:30:30"}
163
+ {"current_steps": 163, "total_steps": 231, "loss": 0.2571, "lr": 4.869146134342426e-06, "epoch": 4.9393939393939394, "percentage": 70.56, "elapsed_time": "1:12:05", "remaining_time": "0:30:04"}
164
+ {"current_steps": 164, "total_steps": 231, "loss": 0.2268, "lr": 4.739474058829288e-06, "epoch": 4.96969696969697, "percentage": 71.0, "elapsed_time": "1:12:29", "remaining_time": "0:29:37"}
165
+ {"current_steps": 165, "total_steps": 231, "loss": 0.2533, "lr": 4.611013640844245e-06, "epoch": 5.0, "percentage": 71.43, "elapsed_time": "1:12:49", "remaining_time": "0:29:07"}
166
+ {"current_steps": 166, "total_steps": 231, "loss": 0.2212, "lr": 4.483794468689728e-06, "epoch": 5.03030303030303, "percentage": 71.86, "elapsed_time": "1:15:03", "remaining_time": "0:29:23"}
167
+ {"current_steps": 167, "total_steps": 231, "loss": 0.2588, "lr": 4.357845844771881e-06, "epoch": 5.0606060606060606, "percentage": 72.29, "elapsed_time": "1:15:27", "remaining_time": "0:28:55"}
168
+ {"current_steps": 168, "total_steps": 231, "loss": 0.2184, "lr": 4.2331967788513295e-06, "epoch": 5.090909090909091, "percentage": 72.73, "elapsed_time": "1:15:50", "remaining_time": "0:28:26"}
169
+ {"current_steps": 169, "total_steps": 231, "loss": 0.2147, "lr": 4.109875981361363e-06, "epoch": 5.121212121212121, "percentage": 73.16, "elapsed_time": "1:16:14", "remaining_time": "0:27:58"}
170
+ {"current_steps": 170, "total_steps": 231, "loss": 0.2309, "lr": 3.987911856795047e-06, "epoch": 5.151515151515151, "percentage": 73.59, "elapsed_time": "1:16:38", "remaining_time": "0:27:29"}
171
+ {"current_steps": 171, "total_steps": 231, "loss": 0.2142, "lr": 3.867332497162836e-06, "epoch": 5.181818181818182, "percentage": 74.03, "elapsed_time": "1:17:01", "remaining_time": "0:27:01"}
172
+ {"current_steps": 172, "total_steps": 231, "loss": 0.1937, "lr": 3.748165675522113e-06, "epoch": 5.212121212121212, "percentage": 74.46, "elapsed_time": "1:17:22", "remaining_time": "0:26:32"}