ryanmarten commited on
Commit
01384c1
·
verified ·
1 Parent(s): 86449f4

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 sha256:23bc230b55a23c409fc9fcdc3a6bfa93887af7b377ec9fdc626aa5ce99726ad2
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:157c7d597023edca221ddd93d7fb68e95c892d8c214169b47d54e4a950123043
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:d93f7535dbabff6c2f106dc7c2f00a91f7dfe60732701e5cc0d3c06ec110b019
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e959c698463a5fd6a3ed6189d2e8e818fbf85d6435ed771a439030bb76c0f9ce
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:84f4ff9456ddef2342ad55000fd83bd3c4885229287a60d5c9abdbee333d5d35
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6788164bff9f33b0fe2a456d95c24667974ea85e71523351905f2f710df0a4f
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:caf712e1b9038d7e68d3ab791f4b149ffd4966da2095b634bf35f1a87add39da
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4466a11ae1c489ebc30e77d8fdba8974d64b2c6d47fec82d62fbb598e7cbe9b
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -162,3 +162,36 @@
162
  {"current_steps": 162, "total_steps": 224, "loss": 0.4377, "lr": 4.339158297870469e-06, "epoch": 4.951898734177215, "percentage": 72.32, "elapsed_time": "5:32:21", "remaining_time": "2:07:12"}
163
  {"current_steps": 163, "total_steps": 224, "loss": 0.4507, "lr": 4.211011002040885e-06, "epoch": 4.982278481012658, "percentage": 72.77, "elapsed_time": "5:34:19", "remaining_time": "2:05:06"}
164
  {"current_steps": 164, "total_steps": 224, "loss": 0.436, "lr": 4.084277875864776e-06, "epoch": 5.020253164556962, "percentage": 73.21, "elapsed_time": "5:37:08", "remaining_time": "2:03:20"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
162
  {"current_steps": 162, "total_steps": 224, "loss": 0.4377, "lr": 4.339158297870469e-06, "epoch": 4.951898734177215, "percentage": 72.32, "elapsed_time": "5:32:21", "remaining_time": "2:07:12"}
163
  {"current_steps": 163, "total_steps": 224, "loss": 0.4507, "lr": 4.211011002040885e-06, "epoch": 4.982278481012658, "percentage": 72.77, "elapsed_time": "5:34:19", "remaining_time": "2:05:06"}
164
  {"current_steps": 164, "total_steps": 224, "loss": 0.436, "lr": 4.084277875864776e-06, "epoch": 5.020253164556962, "percentage": 73.21, "elapsed_time": "5:37:08", "remaining_time": "2:03:20"}
165
+ {"current_steps": 165, "total_steps": 224, "loss": 0.3982, "lr": 3.958989878485644e-06, "epoch": 5.050632911392405, "percentage": 73.66, "elapsed_time": "5:39:11", "remaining_time": "2:01:17"}
166
+ {"current_steps": 166, "total_steps": 224, "loss": 0.4199, "lr": 3.83517761602209e-06, "epoch": 5.0810126582278485, "percentage": 74.11, "elapsed_time": "5:41:08", "remaining_time": "1:59:11"}
167
+ {"current_steps": 167, "total_steps": 224, "loss": 0.3998, "lr": 3.712871334091154e-06, "epoch": 5.111392405063291, "percentage": 74.55, "elapsed_time": "5:43:07", "remaining_time": "1:57:06"}
168
+ {"current_steps": 168, "total_steps": 224, "loss": 0.4291, "lr": 3.592100910419738e-06, "epoch": 5.141772151898734, "percentage": 75.0, "elapsed_time": "5:45:18", "remaining_time": "1:55:06"}
169
+ {"current_steps": 169, "total_steps": 224, "loss": 0.4099, "lr": 3.4728958475459052e-06, "epoch": 5.172151898734177, "percentage": 75.45, "elapsed_time": "5:47:07", "remaining_time": "1:52:58"}
170
+ {"current_steps": 170, "total_steps": 224, "loss": 0.4284, "lr": 3.355285265611784e-06, "epoch": 5.2025316455696204, "percentage": 75.89, "elapsed_time": "5:49:13", "remaining_time": "1:50:55"}
171
+ {"current_steps": 171, "total_steps": 224, "loss": 0.4154, "lr": 3.2392978952499553e-06, "epoch": 5.232911392405064, "percentage": 76.34, "elapsed_time": "5:51:21", "remaining_time": "1:48:54"}
172
+ {"current_steps": 172, "total_steps": 224, "loss": 0.3972, "lr": 3.1249620705649417e-06, "epoch": 5.263291139240506, "percentage": 76.79, "elapsed_time": "5:53:12", "remaining_time": "1:46:46"}
173
+ {"current_steps": 173, "total_steps": 224, "loss": 0.434, "lr": 3.0123057222115835e-06, "epoch": 5.293670886075949, "percentage": 77.23, "elapsed_time": "5:55:18", "remaining_time": "1:44:44"}
174
+ {"current_steps": 174, "total_steps": 224, "loss": 0.4057, "lr": 2.9013563705719673e-06, "epoch": 5.324050632911392, "percentage": 77.68, "elapsed_time": "5:57:31", "remaining_time": "1:42:44"}
175
+ {"current_steps": 175, "total_steps": 224, "loss": 0.4196, "lr": 2.7921411190325753e-06, "epoch": 5.3544303797468356, "percentage": 78.12, "elapsed_time": "5:59:31", "remaining_time": "1:40:39"}
176
+ {"current_steps": 176, "total_steps": 224, "loss": 0.4104, "lr": 2.6846866473633126e-06, "epoch": 5.384810126582279, "percentage": 78.57, "elapsed_time": "6:01:23", "remaining_time": "1:38:33"}
177
+ {"current_steps": 177, "total_steps": 224, "loss": 0.3989, "lr": 2.579019205199992e-06, "epoch": 5.415189873417722, "percentage": 79.02, "elapsed_time": "6:03:13", "remaining_time": "1:36:27"}
178
+ {"current_steps": 178, "total_steps": 224, "loss": 0.4091, "lr": 2.4751646056319334e-06, "epoch": 5.445569620253164, "percentage": 79.46, "elapsed_time": "6:05:19", "remaining_time": "1:34:24"}
179
+ {"current_steps": 179, "total_steps": 224, "loss": 0.4089, "lr": 2.373148218896182e-06, "epoch": 5.4759493670886075, "percentage": 79.91, "elapsed_time": "6:07:23", "remaining_time": "1:32:21"}
180
+ {"current_steps": 180, "total_steps": 224, "loss": 0.4098, "lr": 2.2729949661798876e-06, "epoch": 5.506329113924051, "percentage": 80.36, "elapsed_time": "6:09:43", "remaining_time": "1:30:22"}
181
+ {"current_steps": 181, "total_steps": 224, "loss": 0.4224, "lr": 2.174729313532433e-06, "epoch": 5.536708860759494, "percentage": 80.8, "elapsed_time": "6:11:44", "remaining_time": "1:28:18"}
182
+ {"current_steps": 182, "total_steps": 224, "loss": 0.3987, "lr": 2.078375265888707e-06, "epoch": 5.567088607594937, "percentage": 81.25, "elapsed_time": "6:13:49", "remaining_time": "1:26:16"}
183
+ {"current_steps": 183, "total_steps": 224, "loss": 0.4084, "lr": 1.9839563612050273e-06, "epoch": 5.597468354430379, "percentage": 81.7, "elapsed_time": "6:15:49", "remaining_time": "1:24:11"}
184
+ {"current_steps": 184, "total_steps": 224, "loss": 0.4163, "lr": 1.8914956647091497e-06, "epoch": 5.627848101265823, "percentage": 82.14, "elapsed_time": "6:17:43", "remaining_time": "1:22:06"}
185
+ {"current_steps": 185, "total_steps": 224, "loss": 0.3717, "lr": 1.8010157632657544e-06, "epoch": 5.658227848101266, "percentage": 82.59, "elapsed_time": "6:19:49", "remaining_time": "1:20:04"}
186
+ {"current_steps": 186, "total_steps": 224, "loss": 0.4032, "lr": 1.7125387598587862e-06, "epoch": 5.688607594936709, "percentage": 83.04, "elapsed_time": "6:21:54", "remaining_time": "1:18:01"}
187
+ {"current_steps": 187, "total_steps": 224, "loss": 0.4064, "lr": 1.6260862681919965e-06, "epoch": 5.718987341772152, "percentage": 83.48, "elapsed_time": "6:23:47", "remaining_time": "1:15:56"}
188
+ {"current_steps": 188, "total_steps": 224, "loss": 0.4108, "lr": 1.5416794074090258e-06, "epoch": 5.749367088607595, "percentage": 83.93, "elapsed_time": "6:25:44", "remaining_time": "1:13:51"}
189
+ {"current_steps": 189, "total_steps": 224, "loss": 0.4172, "lr": 1.459338796934293e-06, "epoch": 5.779746835443038, "percentage": 84.38, "elapsed_time": "6:27:39", "remaining_time": "1:11:47"}
190
+ {"current_steps": 190, "total_steps": 224, "loss": 0.3864, "lr": 1.3790845514359363e-06, "epoch": 5.810126582278481, "percentage": 84.82, "elapsed_time": "6:29:43", "remaining_time": "1:09:44"}
191
+ {"current_steps": 191, "total_steps": 224, "loss": 0.4131, "lr": 1.300936275912098e-06, "epoch": 5.840506329113924, "percentage": 85.27, "elapsed_time": "6:31:46", "remaining_time": "1:07:41"}
192
+ {"current_steps": 192, "total_steps": 224, "loss": 0.4339, "lr": 1.224913060901688e-06, "epoch": 5.870886075949367, "percentage": 85.71, "elapsed_time": "6:33:57", "remaining_time": "1:05:39"}
193
+ {"current_steps": 193, "total_steps": 224, "loss": 0.4208, "lr": 1.1510334778208332e-06, "epoch": 5.9012658227848105, "percentage": 86.16, "elapsed_time": "6:35:54", "remaining_time": "1:03:35"}
194
+ {"current_steps": 194, "total_steps": 224, "loss": 0.4245, "lr": 1.0793155744261352e-06, "epoch": 5.931645569620253, "percentage": 86.61, "elapsed_time": "6:37:57", "remaining_time": "1:01:32"}
195
+ {"current_steps": 195, "total_steps": 224, "loss": 0.4121, "lr": 1.0097768704058542e-06, "epoch": 5.962025316455696, "percentage": 87.05, "elapsed_time": "6:40:06", "remaining_time": "0:59:30"}
196
+ {"current_steps": 196, "total_steps": 224, "loss": 0.4195, "lr": 9.424343531000968e-07, "epoch": 5.992405063291139, "percentage": 87.5, "elapsed_time": "6:42:02", "remaining_time": "0:57:26"}
197
+ {"current_steps": 197, "total_steps": 224, "loss": 0.3984, "lr": 8.773044733510338e-07, "epoch": 6.030379746835443, "percentage": 87.95, "elapsed_time": "6:45:12", "remaining_time": "0:55:32"}