neginr commited on
Commit
3ced448
·
verified ·
1 Parent(s): afe8e78

Training in progress, epoch 3

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:96a275c4071bd822608c33a3d09f2132c2c046fece3b26d121d9b1c958360d86
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5e9e3ac44aedba39912598aa824ade201a8e71a71654af6300965622f79a93e
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:d7d15818dc5c30cc8710387346de1540b79cc0f386cab9736c0c8afa55f74309
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a35b72a43d6658544237ddf7a2509584a557e3296e7afeac359261aebea2bcd
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0180ffacfdfc86a078d9520f6f28d433b1b2f7b87f185900159ef61541c03524
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2a3389f2cd4b8f2e4c53a035aec259a017cc6d33ef9320aa5dcf8f266356dcf
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:12f3a895f20265337227320519ba927ae18911d3b1c52a610615d7c868c5093c
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4ad915f55e13083f20e42ec09aecf5fb278512d8d9b849d55fcfa6438ff59d4
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -140,3 +140,49 @@
140
  {"current_steps": 135, "total_steps": 225, "loss": 0.3927, "lr": 3.3190257771104055e-05, "epoch": 2.962962962962963, "percentage": 60.0, "elapsed_time": "4:02:11", "remaining_time": "2:41:27"}
141
  {"current_steps": 136, "total_steps": 225, "loss": 0.3855, "lr": 3.257808984682027e-05, "epoch": 2.9849108367626886, "percentage": 60.44, "elapsed_time": "4:03:57", "remaining_time": "2:39:38"}
142
  {"current_steps": 137, "total_steps": 225, "loss": 0.3837, "lr": 3.196771708577127e-05, "epoch": 3.006858710562414, "percentage": 60.89, "elapsed_time": "4:07:31", "remaining_time": "2:38:59"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
140
  {"current_steps": 135, "total_steps": 225, "loss": 0.3927, "lr": 3.3190257771104055e-05, "epoch": 2.962962962962963, "percentage": 60.0, "elapsed_time": "4:02:11", "remaining_time": "2:41:27"}
141
  {"current_steps": 136, "total_steps": 225, "loss": 0.3855, "lr": 3.257808984682027e-05, "epoch": 2.9849108367626886, "percentage": 60.44, "elapsed_time": "4:03:57", "remaining_time": "2:39:38"}
142
  {"current_steps": 137, "total_steps": 225, "loss": 0.3837, "lr": 3.196771708577127e-05, "epoch": 3.006858710562414, "percentage": 60.89, "elapsed_time": "4:07:31", "remaining_time": "2:38:59"}
143
+ {"current_steps": 138, "total_steps": 225, "loss": 0.359, "lr": 3.135928712094067e-05, "epoch": 3.02880658436214, "percentage": 61.33, "elapsed_time": "4:09:14", "remaining_time": "2:37:08"}
144
+ {"current_steps": 139, "total_steps": 225, "loss": 0.3557, "lr": 3.075294711540123e-05, "epoch": 3.0507544581618657, "percentage": 61.78, "elapsed_time": "4:10:59", "remaining_time": "2:35:17"}
145
+ {"current_steps": 140, "total_steps": 225, "loss": 0.3516, "lr": 3.0148843726719953e-05, "epoch": 3.072702331961591, "percentage": 62.22, "elapsed_time": "4:12:45", "remaining_time": "2:33:27"}
146
+ {"current_steps": 141, "total_steps": 225, "loss": 0.3532, "lr": 2.9547123071485586e-05, "epoch": 3.094650205761317, "percentage": 62.67, "elapsed_time": "4:14:30", "remaining_time": "2:31:37"}
147
+ {"current_steps": 142, "total_steps": 225, "loss": 0.3598, "lr": 2.8947930689966798e-05, "epoch": 3.1165980795610424, "percentage": 63.11, "elapsed_time": "4:16:15", "remaining_time": "2:29:47"}
148
+ {"current_steps": 143, "total_steps": 225, "loss": 0.3567, "lr": 2.8351411510909926e-05, "epoch": 3.1385459533607682, "percentage": 63.56, "elapsed_time": "4:17:59", "remaining_time": "2:27:56"}
149
+ {"current_steps": 144, "total_steps": 225, "loss": 0.3634, "lr": 2.7757709816484512e-05, "epoch": 3.1604938271604937, "percentage": 64.0, "elapsed_time": "4:19:46", "remaining_time": "2:26:07"}
150
+ {"current_steps": 145, "total_steps": 225, "loss": 0.3542, "lr": 2.71669692073853e-05, "epoch": 3.1824417009602195, "percentage": 64.44, "elapsed_time": "4:21:31", "remaining_time": "2:24:17"}
151
+ {"current_steps": 146, "total_steps": 225, "loss": 0.3576, "lr": 2.6579332568099006e-05, "epoch": 3.2043895747599453, "percentage": 64.89, "elapsed_time": "4:23:17", "remaining_time": "2:22:27"}
152
+ {"current_steps": 147, "total_steps": 225, "loss": 0.357, "lr": 2.5994942032344376e-05, "epoch": 3.2263374485596708, "percentage": 65.33, "elapsed_time": "4:25:02", "remaining_time": "2:20:38"}
153
+ {"current_steps": 148, "total_steps": 225, "loss": 0.3559, "lr": 2.54139389486938e-05, "epoch": 3.2482853223593966, "percentage": 65.78, "elapsed_time": "4:26:47", "remaining_time": "2:18:48"}
154
+ {"current_steps": 149, "total_steps": 225, "loss": 0.3529, "lr": 2.4836463846384832e-05, "epoch": 3.270233196159122, "percentage": 66.22, "elapsed_time": "4:28:33", "remaining_time": "2:16:58"}
155
+ {"current_steps": 150, "total_steps": 225, "loss": 0.359, "lr": 2.4262656401329913e-05, "epoch": 3.292181069958848, "percentage": 66.67, "elapsed_time": "4:30:17", "remaining_time": "2:15:08"}
156
+ {"current_steps": 151, "total_steps": 225, "loss": 0.3565, "lr": 2.3692655402332455e-05, "epoch": 3.3141289437585733, "percentage": 67.11, "elapsed_time": "4:32:02", "remaining_time": "2:13:18"}
157
+ {"current_steps": 152, "total_steps": 225, "loss": 0.3508, "lr": 2.3126598717517514e-05, "epoch": 3.336076817558299, "percentage": 67.56, "elapsed_time": "4:33:48", "remaining_time": "2:11:29"}
158
+ {"current_steps": 153, "total_steps": 225, "loss": 0.3558, "lr": 2.256462326098516e-05, "epoch": 3.3580246913580245, "percentage": 68.0, "elapsed_time": "4:35:32", "remaining_time": "2:09:39"}
159
+ {"current_steps": 154, "total_steps": 225, "loss": 0.3546, "lr": 2.200686495969457e-05, "epoch": 3.3799725651577504, "percentage": 68.44, "elapsed_time": "4:37:17", "remaining_time": "2:07:50"}
160
+ {"current_steps": 155, "total_steps": 225, "loss": 0.3562, "lr": 2.1453458720586902e-05, "epoch": 3.401920438957476, "percentage": 68.89, "elapsed_time": "4:39:02", "remaining_time": "2:06:01"}
161
+ {"current_steps": 156, "total_steps": 225, "loss": 0.3595, "lr": 2.0904538397954913e-05, "epoch": 3.4238683127572016, "percentage": 69.33, "elapsed_time": "4:40:47", "remaining_time": "2:04:11"}
162
+ {"current_steps": 157, "total_steps": 225, "loss": 0.3572, "lr": 2.0360236761067117e-05, "epoch": 3.4458161865569275, "percentage": 69.78, "elapsed_time": "4:42:33", "remaining_time": "2:02:22"}
163
+ {"current_steps": 158, "total_steps": 225, "loss": 0.3608, "lr": 1.9820685462054413e-05, "epoch": 3.467764060356653, "percentage": 70.22, "elapsed_time": "4:44:18", "remaining_time": "2:00:33"}
164
+ {"current_steps": 159, "total_steps": 225, "loss": 0.3571, "lr": 1.9286015004066984e-05, "epoch": 3.4897119341563787, "percentage": 70.67, "elapsed_time": "4:46:03", "remaining_time": "1:58:44"}
165
+ {"current_steps": 160, "total_steps": 225, "loss": 0.3593, "lr": 1.8756354709708998e-05, "epoch": 3.511659807956104, "percentage": 71.11, "elapsed_time": "4:47:48", "remaining_time": "1:56:55"}
166
+ {"current_steps": 161, "total_steps": 225, "loss": 0.3528, "lr": 1.8231832689758903e-05, "epoch": 3.53360768175583, "percentage": 71.56, "elapsed_time": "4:49:33", "remaining_time": "1:55:06"}
167
+ {"current_steps": 162, "total_steps": 225, "loss": 0.3562, "lr": 1.771257581218287e-05, "epoch": 3.5555555555555554, "percentage": 72.0, "elapsed_time": "4:51:19", "remaining_time": "1:53:17"}
168
+ {"current_steps": 163, "total_steps": 225, "loss": 0.3568, "lr": 1.7198709671448696e-05, "epoch": 3.577503429355281, "percentage": 72.44, "elapsed_time": "4:53:04", "remaining_time": "1:51:28"}
169
+ {"current_steps": 164, "total_steps": 225, "loss": 0.3522, "lr": 1.6690358558147967e-05, "epoch": 3.599451303155007, "percentage": 72.89, "elapsed_time": "4:54:49", "remaining_time": "1:49:39"}
170
+ {"current_steps": 165, "total_steps": 225, "loss": 0.3584, "lr": 1.6187645428933372e-05, "epoch": 3.6213991769547325, "percentage": 73.33, "elapsed_time": "4:56:34", "remaining_time": "1:47:50"}
171
+ {"current_steps": 166, "total_steps": 225, "loss": 0.3622, "lr": 1.5690691876778746e-05, "epoch": 3.6433470507544583, "percentage": 73.78, "elapsed_time": "4:58:19", "remaining_time": "1:46:02"}
172
+ {"current_steps": 167, "total_steps": 225, "loss": 0.3544, "lr": 1.5199618101569003e-05, "epoch": 3.6652949245541837, "percentage": 74.22, "elapsed_time": "5:00:04", "remaining_time": "1:44:13"}
173
+ {"current_steps": 168, "total_steps": 225, "loss": 0.3519, "lr": 1.4714542881026947e-05, "epoch": 3.6872427983539096, "percentage": 74.67, "elapsed_time": "5:01:49", "remaining_time": "1:42:24"}
174
+ {"current_steps": 169, "total_steps": 225, "loss": 0.3621, "lr": 1.4235583541984092e-05, "epoch": 3.709190672153635, "percentage": 75.11, "elapsed_time": "5:03:33", "remaining_time": "1:40:35"}
175
+ {"current_steps": 170, "total_steps": 225, "loss": 0.3554, "lr": 1.3762855932002404e-05, "epoch": 3.731138545953361, "percentage": 75.56, "elapsed_time": "5:05:18", "remaining_time": "1:38:46"}
176
+ {"current_steps": 171, "total_steps": 225, "loss": 0.3602, "lr": 1.3296474391353854e-05, "epoch": 3.753086419753086, "percentage": 76.0, "elapsed_time": "5:07:03", "remaining_time": "1:36:58"}
177
+ {"current_steps": 172, "total_steps": 225, "loss": 0.3489, "lr": 1.2836551725364572e-05, "epoch": 3.775034293552812, "percentage": 76.44, "elapsed_time": "5:08:49", "remaining_time": "1:35:09"}
178
+ {"current_steps": 173, "total_steps": 225, "loss": 0.3536, "lr": 1.2383199177130135e-05, "epoch": 3.796982167352538, "percentage": 76.89, "elapsed_time": "5:10:34", "remaining_time": "1:33:21"}
179
+ {"current_steps": 174, "total_steps": 225, "loss": 0.3517, "lr": 1.1936526400608938e-05, "epoch": 3.8189300411522633, "percentage": 77.33, "elapsed_time": "5:12:19", "remaining_time": "1:31:32"}
180
+ {"current_steps": 175, "total_steps": 225, "loss": 0.3499, "lr": 1.1496641434099725e-05, "epoch": 3.840877914951989, "percentage": 77.78, "elapsed_time": "5:14:03", "remaining_time": "1:29:43"}
181
+ {"current_steps": 176, "total_steps": 225, "loss": 0.3562, "lr": 1.1063650674110011e-05, "epoch": 3.8628257887517146, "percentage": 78.22, "elapsed_time": "5:15:49", "remaining_time": "1:27:55"}
182
+ {"current_steps": 177, "total_steps": 225, "loss": 0.3521, "lr": 1.0637658849621593e-05, "epoch": 3.8847736625514404, "percentage": 78.67, "elapsed_time": "5:17:33", "remaining_time": "1:26:06"}
183
+ {"current_steps": 178, "total_steps": 225, "loss": 0.3528, "lr": 1.0218768996759399e-05, "epoch": 3.9067215363511663, "percentage": 79.11, "elapsed_time": "5:19:17", "remaining_time": "1:24:18"}
184
+ {"current_steps": 179, "total_steps": 225, "loss": 0.359, "lr": 9.807082433869727e-06, "epoch": 3.9286694101508917, "percentage": 79.56, "elapsed_time": "5:21:01", "remaining_time": "1:22:29"}
185
+ {"current_steps": 180, "total_steps": 225, "loss": 0.3643, "lr": 9.402698737014098e-06, "epoch": 3.950617283950617, "percentage": 80.0, "elapsed_time": "5:22:46", "remaining_time": "1:20:41"}
186
+ {"current_steps": 181, "total_steps": 225, "loss": 0.3564, "lr": 9.005715715884409e-06, "epoch": 3.972565157750343, "percentage": 80.44, "elapsed_time": "5:24:31", "remaining_time": "1:18:53"}
187
+ {"current_steps": 182, "total_steps": 225, "loss": 0.3561, "lr": 8.616229390145361e-06, "epoch": 3.9945130315500688, "percentage": 80.89, "elapsed_time": "5:26:12", "remaining_time": "1:17:04"}
188
+ {"current_steps": 183, "total_steps": 225, "loss": 0.3455, "lr": 8.23433396620986e-06, "epoch": 4.016460905349795, "percentage": 81.33, "elapsed_time": "5:29:41", "remaining_time": "1:15:39"}