ryanmarten commited on
Commit
5fddc6f
·
verified ·
1 Parent(s): 379664f

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 sha256:4449545d6d1c95ce8921074af4d59e4c98bbfd61032c79bcb229e86bf73a475c
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e6a8c36232b57183f7e013e1ecd560cb8f89e4a500dbd3300edd6aee641d19a
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:b2631035c06ed0ce1f96e9f32fb15f43864b9543e3e8d23916757eafd23c6d16
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9b083404178c90c34dd660a10f11b6d73df620cc1f0022ba09aa3ecb542918e
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:27c74a91ee61d38f468516255a1a2eee5d109cbca1125e5aa5f57da1cc22822f
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:305f96f6722c9bba2c7b2f40b4d82d73529a41e66bf584bc13a0669f45506fbb
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:b9ef62e46e0a6512ac63d13725c7a22b62c50b0ee9156eb36d37dfd3ce993fed
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2351d525acd45d6e2e201b8de11b015a75bca17f00aea376227d729123a560e0
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -179,3 +179,36 @@
179
  {"current_steps": 162, "total_steps": 224, "loss": 0.2928, "lr": 4.339158297870469e-06, "epoch": 4.951898734177215, "percentage": 72.32, "elapsed_time": "5:15:52", "remaining_time": "2:00:53"}
180
  {"current_steps": 163, "total_steps": 224, "loss": 0.3122, "lr": 4.211011002040885e-06, "epoch": 4.982278481012658, "percentage": 72.77, "elapsed_time": "5:17:59", "remaining_time": "1:59:00"}
181
  {"current_steps": 164, "total_steps": 224, "loss": 0.2844, "lr": 4.084277875864776e-06, "epoch": 5.020253164556962, "percentage": 73.21, "elapsed_time": "5:20:58", "remaining_time": "1:57:25"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
179
  {"current_steps": 162, "total_steps": 224, "loss": 0.2928, "lr": 4.339158297870469e-06, "epoch": 4.951898734177215, "percentage": 72.32, "elapsed_time": "5:15:52", "remaining_time": "2:00:53"}
180
  {"current_steps": 163, "total_steps": 224, "loss": 0.3122, "lr": 4.211011002040885e-06, "epoch": 4.982278481012658, "percentage": 72.77, "elapsed_time": "5:17:59", "remaining_time": "1:59:00"}
181
  {"current_steps": 164, "total_steps": 224, "loss": 0.2844, "lr": 4.084277875864776e-06, "epoch": 5.020253164556962, "percentage": 73.21, "elapsed_time": "5:20:58", "remaining_time": "1:57:25"}
182
+ {"current_steps": 165, "total_steps": 224, "loss": 0.272, "lr": 3.958989878485644e-06, "epoch": 5.050632911392405, "percentage": 73.66, "elapsed_time": "5:22:57", "remaining_time": "1:55:28"}
183
+ {"current_steps": 166, "total_steps": 224, "loss": 0.2675, "lr": 3.83517761602209e-06, "epoch": 5.0810126582278485, "percentage": 74.11, "elapsed_time": "5:24:53", "remaining_time": "1:53:31"}
184
+ {"current_steps": 167, "total_steps": 224, "loss": 0.273, "lr": 3.712871334091154e-06, "epoch": 5.111392405063291, "percentage": 74.55, "elapsed_time": "5:26:48", "remaining_time": "1:51:32"}
185
+ {"current_steps": 168, "total_steps": 224, "loss": 0.276, "lr": 3.592100910419738e-06, "epoch": 5.141772151898734, "percentage": 75.0, "elapsed_time": "5:28:53", "remaining_time": "1:49:37"}
186
+ {"current_steps": 169, "total_steps": 224, "loss": 0.2608, "lr": 3.4728958475459052e-06, "epoch": 5.172151898734177, "percentage": 75.45, "elapsed_time": "5:30:41", "remaining_time": "1:47:37"}
187
+ {"current_steps": 170, "total_steps": 224, "loss": 0.2729, "lr": 3.355285265611784e-06, "epoch": 5.2025316455696204, "percentage": 75.89, "elapsed_time": "5:32:23", "remaining_time": "1:45:34"}
188
+ {"current_steps": 171, "total_steps": 224, "loss": 0.2678, "lr": 3.2392978952499553e-06, "epoch": 5.232911392405064, "percentage": 76.34, "elapsed_time": "5:34:17", "remaining_time": "1:43:36"}
189
+ {"current_steps": 172, "total_steps": 224, "loss": 0.2718, "lr": 3.1249620705649417e-06, "epoch": 5.263291139240506, "percentage": 76.79, "elapsed_time": "5:36:17", "remaining_time": "1:41:40"}
190
+ {"current_steps": 173, "total_steps": 224, "loss": 0.2684, "lr": 3.0123057222115835e-06, "epoch": 5.293670886075949, "percentage": 77.23, "elapsed_time": "5:38:18", "remaining_time": "1:39:44"}
191
+ {"current_steps": 174, "total_steps": 224, "loss": 0.2585, "lr": 2.9013563705719673e-06, "epoch": 5.324050632911392, "percentage": 77.68, "elapsed_time": "5:40:04", "remaining_time": "1:37:43"}
192
+ {"current_steps": 175, "total_steps": 224, "loss": 0.2776, "lr": 2.7921411190325753e-06, "epoch": 5.3544303797468356, "percentage": 78.12, "elapsed_time": "5:42:04", "remaining_time": "1:35:46"}
193
+ {"current_steps": 176, "total_steps": 224, "loss": 0.2737, "lr": 2.6846866473633126e-06, "epoch": 5.384810126582279, "percentage": 78.57, "elapsed_time": "5:44:02", "remaining_time": "1:33:49"}
194
+ {"current_steps": 177, "total_steps": 224, "loss": 0.2716, "lr": 2.579019205199992e-06, "epoch": 5.415189873417722, "percentage": 79.02, "elapsed_time": "5:45:56", "remaining_time": "1:31:51"}
195
+ {"current_steps": 178, "total_steps": 224, "loss": 0.2586, "lr": 2.4751646056319334e-06, "epoch": 5.445569620253164, "percentage": 79.46, "elapsed_time": "5:47:55", "remaining_time": "1:29:54"}
196
+ {"current_steps": 179, "total_steps": 224, "loss": 0.2786, "lr": 2.373148218896182e-06, "epoch": 5.4759493670886075, "percentage": 79.91, "elapsed_time": "5:49:47", "remaining_time": "1:27:56"}
197
+ {"current_steps": 180, "total_steps": 224, "loss": 0.2788, "lr": 2.2729949661798876e-06, "epoch": 5.506329113924051, "percentage": 80.36, "elapsed_time": "5:51:45", "remaining_time": "1:25:59"}
198
+ {"current_steps": 181, "total_steps": 224, "loss": 0.2665, "lr": 2.174729313532433e-06, "epoch": 5.536708860759494, "percentage": 80.8, "elapsed_time": "5:53:35", "remaining_time": "1:24:00"}
199
+ {"current_steps": 182, "total_steps": 224, "loss": 0.2714, "lr": 2.078375265888707e-06, "epoch": 5.567088607594937, "percentage": 81.25, "elapsed_time": "5:55:34", "remaining_time": "1:22:03"}
200
+ {"current_steps": 183, "total_steps": 224, "loss": 0.291, "lr": 1.9839563612050273e-06, "epoch": 5.597468354430379, "percentage": 81.7, "elapsed_time": "5:57:35", "remaining_time": "1:20:06"}
201
+ {"current_steps": 184, "total_steps": 224, "loss": 0.2595, "lr": 1.8914956647091497e-06, "epoch": 5.627848101265823, "percentage": 82.14, "elapsed_time": "5:59:26", "remaining_time": "1:18:08"}
202
+ {"current_steps": 185, "total_steps": 224, "loss": 0.2687, "lr": 1.8010157632657544e-06, "epoch": 5.658227848101266, "percentage": 82.59, "elapsed_time": "6:01:19", "remaining_time": "1:16:10"}
203
+ {"current_steps": 186, "total_steps": 224, "loss": 0.2918, "lr": 1.7125387598587862e-06, "epoch": 5.688607594936709, "percentage": 83.04, "elapsed_time": "6:03:07", "remaining_time": "1:14:11"}
204
+ {"current_steps": 187, "total_steps": 224, "loss": 0.2734, "lr": 1.6260862681919965e-06, "epoch": 5.718987341772152, "percentage": 83.48, "elapsed_time": "6:05:11", "remaining_time": "1:12:15"}
205
+ {"current_steps": 188, "total_steps": 224, "loss": 0.2584, "lr": 1.5416794074090258e-06, "epoch": 5.749367088607595, "percentage": 83.93, "elapsed_time": "6:07:04", "remaining_time": "1:10:17"}
206
+ {"current_steps": 189, "total_steps": 224, "loss": 0.2648, "lr": 1.459338796934293e-06, "epoch": 5.779746835443038, "percentage": 84.38, "elapsed_time": "6:09:04", "remaining_time": "1:08:20"}
207
+ {"current_steps": 190, "total_steps": 224, "loss": 0.2799, "lr": 1.3790845514359363e-06, "epoch": 5.810126582278481, "percentage": 84.82, "elapsed_time": "6:11:02", "remaining_time": "1:06:23"}
208
+ {"current_steps": 191, "total_steps": 224, "loss": 0.2614, "lr": 1.300936275912098e-06, "epoch": 5.840506329113924, "percentage": 85.27, "elapsed_time": "6:12:54", "remaining_time": "1:04:25"}
209
+ {"current_steps": 192, "total_steps": 224, "loss": 0.292, "lr": 1.224913060901688e-06, "epoch": 5.870886075949367, "percentage": 85.71, "elapsed_time": "6:14:58", "remaining_time": "1:02:29"}
210
+ {"current_steps": 193, "total_steps": 224, "loss": 0.2759, "lr": 1.1510334778208332e-06, "epoch": 5.9012658227848105, "percentage": 86.16, "elapsed_time": "6:16:57", "remaining_time": "1:00:32"}
211
+ {"current_steps": 194, "total_steps": 224, "loss": 0.2867, "lr": 1.0793155744261352e-06, "epoch": 5.931645569620253, "percentage": 86.61, "elapsed_time": "6:18:55", "remaining_time": "0:58:35"}
212
+ {"current_steps": 195, "total_steps": 224, "loss": 0.2764, "lr": 1.0097768704058542e-06, "epoch": 5.962025316455696, "percentage": 87.05, "elapsed_time": "6:20:49", "remaining_time": "0:56:38"}
213
+ {"current_steps": 196, "total_steps": 224, "loss": 0.2661, "lr": 9.424343531000968e-07, "epoch": 5.992405063291139, "percentage": 87.5, "elapsed_time": "6:22:44", "remaining_time": "0:54:40"}
214
+ {"current_steps": 197, "total_steps": 224, "loss": 0.2701, "lr": 8.773044733510338e-07, "epoch": 6.030379746835443, "percentage": 87.95, "elapsed_time": "6:25:36", "remaining_time": "0:52:51"}