gsmyrnis commited on
Commit
0571e67
·
verified ·
1 Parent(s): d802dcf

Training in progress, epoch 2

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:40f38a285767f7686e72c50f455741c77f9deedbe105578804c8d6d46f8c0bdf
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5498870bc41bf2ac22dac2e4006deeec6f8d12f3f929e3202f99225949076da7
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0409cc62d5b17b02e76042416c02256037e7779755228ef58c064f33f5e68ccc
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa7e39f9bd5f4c315fb2db05bf9602eafaed498e899fb098e89976e6fabd243f
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6aeaa421c8a78e3d50140d2c04608a44a2b1080982dd51529e56e9cfa6103a2e
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af412ce55b7e68191639cbc9c2c5970e4857c2155e4907363556d722edd7f96e
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9272e0f4fcce8b5ba3aaba56a0f832b45e9beb921fa0216a92af4eb7c52508b2
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d5b9ec23d740082d4ae3b835dc516e45bdee68e4ffe925e3f0304b96af538d8
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -165,3 +165,71 @@
165
  {"current_steps": 165, "total_steps": 234, "loss": 0.6422, "lr": 2.43550361297047e-06, "epoch": 2.106382978723404, "percentage": 70.51, "elapsed_time": "0:40:46", "remaining_time": "0:17:03"}
166
  {"current_steps": 166, "total_steps": 234, "loss": 0.7221, "lr": 2.371581150947476e-06, "epoch": 2.119148936170213, "percentage": 70.94, "elapsed_time": "0:41:00", "remaining_time": "0:16:47"}
167
  {"current_steps": 167, "total_steps": 234, "loss": 0.6881, "lr": 2.3082469195465893e-06, "epoch": 2.1319148936170214, "percentage": 71.37, "elapsed_time": "0:41:13", "remaining_time": "0:16:32"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
165
  {"current_steps": 165, "total_steps": 234, "loss": 0.6422, "lr": 2.43550361297047e-06, "epoch": 2.106382978723404, "percentage": 70.51, "elapsed_time": "0:40:46", "remaining_time": "0:17:03"}
166
  {"current_steps": 166, "total_steps": 234, "loss": 0.7221, "lr": 2.371581150947476e-06, "epoch": 2.119148936170213, "percentage": 70.94, "elapsed_time": "0:41:00", "remaining_time": "0:16:47"}
167
  {"current_steps": 167, "total_steps": 234, "loss": 0.6881, "lr": 2.3082469195465893e-06, "epoch": 2.1319148936170214, "percentage": 71.37, "elapsed_time": "0:41:13", "remaining_time": "0:16:32"}
168
+ {"current_steps": 168, "total_steps": 234, "loss": 0.714, "lr": 2.245515092739488e-06, "epoch": 2.1446808510638298, "percentage": 71.79, "elapsed_time": "0:41:27", "remaining_time": "0:16:17"}
169
+ {"current_steps": 169, "total_steps": 234, "loss": 0.8456, "lr": 2.1833997096818897e-06, "epoch": 2.157446808510638, "percentage": 72.22, "elapsed_time": "0:41:44", "remaining_time": "0:16:03"}
170
+ {"current_steps": 170, "total_steps": 234, "loss": 0.6249, "lr": 2.1219146715716332e-06, "epoch": 2.1702127659574466, "percentage": 72.65, "elapsed_time": "0:42:00", "remaining_time": "0:15:48"}
171
+ {"current_steps": 171, "total_steps": 234, "loss": 0.7802, "lr": 2.061073738537635e-06, "epoch": 2.1829787234042555, "percentage": 73.08, "elapsed_time": "0:42:17", "remaining_time": "0:15:35"}
172
+ {"current_steps": 172, "total_steps": 234, "loss": 0.5842, "lr": 2.0008905265604316e-06, "epoch": 2.195744680851064, "percentage": 73.5, "elapsed_time": "0:42:29", "remaining_time": "0:15:18"}
173
+ {"current_steps": 173, "total_steps": 234, "loss": 0.8071, "lr": 1.941378504424968e-06, "epoch": 2.2085106382978723, "percentage": 73.93, "elapsed_time": "0:42:43", "remaining_time": "0:15:03"}
174
+ {"current_steps": 174, "total_steps": 234, "loss": 0.7655, "lr": 1.8825509907063328e-06, "epoch": 2.2212765957446807, "percentage": 74.36, "elapsed_time": "0:42:56", "remaining_time": "0:14:48"}
175
+ {"current_steps": 175, "total_steps": 234, "loss": 0.6509, "lr": 1.8244211507891064e-06, "epoch": 2.2340425531914896, "percentage": 74.79, "elapsed_time": "0:43:12", "remaining_time": "0:14:34"}
176
+ {"current_steps": 176, "total_steps": 234, "loss": 0.6761, "lr": 1.7670019939210025e-06, "epoch": 2.246808510638298, "percentage": 75.21, "elapsed_time": "0:43:23", "remaining_time": "0:14:17"}
177
+ {"current_steps": 177, "total_steps": 234, "loss": 0.752, "lr": 1.7103063703014372e-06, "epoch": 2.2595744680851064, "percentage": 75.64, "elapsed_time": "0:43:38", "remaining_time": "0:14:03"}
178
+ {"current_steps": 178, "total_steps": 234, "loss": 0.7025, "lr": 1.6543469682057105e-06, "epoch": 2.272340425531915, "percentage": 76.07, "elapsed_time": "0:43:51", "remaining_time": "0:13:47"}
179
+ {"current_steps": 179, "total_steps": 234, "loss": 0.6167, "lr": 1.5991363111454023e-06, "epoch": 2.2851063829787233, "percentage": 76.5, "elapsed_time": "0:44:07", "remaining_time": "0:13:33"}
180
+ {"current_steps": 180, "total_steps": 234, "loss": 0.5999, "lr": 1.544686755065677e-06, "epoch": 2.297872340425532, "percentage": 76.92, "elapsed_time": "0:44:19", "remaining_time": "0:13:17"}
181
+ {"current_steps": 181, "total_steps": 234, "loss": 0.7743, "lr": 1.4910104855800429e-06, "epoch": 2.3106382978723405, "percentage": 77.35, "elapsed_time": "0:44:36", "remaining_time": "0:13:03"}
182
+ {"current_steps": 182, "total_steps": 234, "loss": 0.735, "lr": 1.438119515243277e-06, "epoch": 2.323404255319149, "percentage": 77.78, "elapsed_time": "0:44:48", "remaining_time": "0:12:48"}
183
+ {"current_steps": 183, "total_steps": 234, "loss": 0.6105, "lr": 1.3860256808630429e-06, "epoch": 2.3361702127659574, "percentage": 78.21, "elapsed_time": "0:45:02", "remaining_time": "0:12:33"}
184
+ {"current_steps": 184, "total_steps": 234, "loss": 0.7582, "lr": 1.3347406408508695e-06, "epoch": 2.348936170212766, "percentage": 78.63, "elapsed_time": "0:45:18", "remaining_time": "0:12:18"}
185
+ {"current_steps": 185, "total_steps": 234, "loss": 0.8307, "lr": 1.2842758726130283e-06, "epoch": 2.3617021276595747, "percentage": 79.06, "elapsed_time": "0:45:34", "remaining_time": "0:12:04"}
186
+ {"current_steps": 186, "total_steps": 234, "loss": 0.6998, "lr": 1.234642669981946e-06, "epoch": 2.374468085106383, "percentage": 79.49, "elapsed_time": "0:45:50", "remaining_time": "0:11:49"}
187
+ {"current_steps": 187, "total_steps": 234, "loss": 0.8048, "lr": 1.1858521406886674e-06, "epoch": 2.3872340425531915, "percentage": 79.91, "elapsed_time": "0:46:06", "remaining_time": "0:11:35"}
188
+ {"current_steps": 188, "total_steps": 234, "loss": 0.6056, "lr": 1.137915203877003e-06, "epoch": 2.4, "percentage": 80.34, "elapsed_time": "0:46:15", "remaining_time": "0:11:19"}
189
+ {"current_steps": 189, "total_steps": 234, "loss": 0.6458, "lr": 1.0908425876598512e-06, "epoch": 2.4127659574468083, "percentage": 80.77, "elapsed_time": "0:46:24", "remaining_time": "0:11:03"}
190
+ {"current_steps": 190, "total_steps": 234, "loss": 0.7236, "lr": 1.044644826718295e-06, "epoch": 2.425531914893617, "percentage": 81.2, "elapsed_time": "0:46:38", "remaining_time": "0:10:48"}
191
+ {"current_steps": 191, "total_steps": 234, "loss": 0.688, "lr": 9.993322599439692e-07, "epoch": 2.4382978723404256, "percentage": 81.62, "elapsed_time": "0:46:53", "remaining_time": "0:10:33"}
192
+ {"current_steps": 192, "total_steps": 234, "loss": 0.7615, "lr": 9.549150281252633e-07, "epoch": 2.451063829787234, "percentage": 82.05, "elapsed_time": "0:47:05", "remaining_time": "0:10:18"}
193
+ {"current_steps": 193, "total_steps": 234, "loss": 0.6917, "lr": 9.114030716778433e-07, "epoch": 2.4638297872340424, "percentage": 82.48, "elapsed_time": "0:47:18", "remaining_time": "0:10:02"}
194
+ {"current_steps": 194, "total_steps": 234, "loss": 0.7123, "lr": 8.688061284200266e-07, "epoch": 2.476595744680851, "percentage": 82.91, "elapsed_time": "0:47:31", "remaining_time": "0:09:47"}
195
+ {"current_steps": 195, "total_steps": 234, "loss": 0.6604, "lr": 8.271337313934869e-07, "epoch": 2.4893617021276597, "percentage": 83.33, "elapsed_time": "0:47:45", "remaining_time": "0:09:33"}
196
+ {"current_steps": 196, "total_steps": 234, "loss": 0.7049, "lr": 7.863952067298042e-07, "epoch": 2.502127659574468, "percentage": 83.76, "elapsed_time": "0:47:59", "remaining_time": "0:09:18"}
197
+ {"current_steps": 197, "total_steps": 234, "loss": 0.6966, "lr": 7.465996715633028e-07, "epoch": 2.5148936170212766, "percentage": 84.19, "elapsed_time": "0:48:14", "remaining_time": "0:09:03"}
198
+ {"current_steps": 198, "total_steps": 234, "loss": 0.7798, "lr": 7.077560319906696e-07, "epoch": 2.527659574468085, "percentage": 84.62, "elapsed_time": "0:48:26", "remaining_time": "0:08:48"}
199
+ {"current_steps": 199, "total_steps": 234, "loss": 0.7255, "lr": 6.698729810778065e-07, "epoch": 2.5404255319148934, "percentage": 85.04, "elapsed_time": "0:48:43", "remaining_time": "0:08:34"}
200
+ {"current_steps": 200, "total_steps": 234, "loss": 0.6144, "lr": 6.329589969143518e-07, "epoch": 2.5531914893617023, "percentage": 85.47, "elapsed_time": "0:48:53", "remaining_time": "0:08:18"}
201
+ {"current_steps": 201, "total_steps": 234, "loss": 0.7007, "lr": 5.9702234071631e-07, "epoch": 2.5659574468085107, "percentage": 85.9, "elapsed_time": "0:49:07", "remaining_time": "0:08:03"}
202
+ {"current_steps": 202, "total_steps": 234, "loss": 0.6856, "lr": 5.620710549772295e-07, "epoch": 2.578723404255319, "percentage": 86.32, "elapsed_time": "0:49:20", "remaining_time": "0:07:48"}
203
+ {"current_steps": 203, "total_steps": 234, "loss": 0.6839, "lr": 5.281129616683167e-07, "epoch": 2.5914893617021275, "percentage": 86.75, "elapsed_time": "0:49:33", "remaining_time": "0:07:34"}
204
+ {"current_steps": 204, "total_steps": 234, "loss": 0.7011, "lr": 4.951556604879049e-07, "epoch": 2.604255319148936, "percentage": 87.18, "elapsed_time": "0:49:46", "remaining_time": "0:07:19"}
205
+ {"current_steps": 205, "total_steps": 234, "loss": 0.7438, "lr": 4.632065271606756e-07, "epoch": 2.617021276595745, "percentage": 87.61, "elapsed_time": "0:50:01", "remaining_time": "0:07:04"}
206
+ {"current_steps": 206, "total_steps": 234, "loss": 0.6271, "lr": 4.322727117869951e-07, "epoch": 2.629787234042553, "percentage": 88.03, "elapsed_time": "0:50:17", "remaining_time": "0:06:50"}
207
+ {"current_steps": 207, "total_steps": 234, "loss": 0.7694, "lr": 4.0236113724274716e-07, "epoch": 2.6425531914893616, "percentage": 88.46, "elapsed_time": "0:50:35", "remaining_time": "0:06:35"}
208
+ {"current_steps": 208, "total_steps": 234, "loss": 0.8376, "lr": 3.734784976300165e-07, "epoch": 2.65531914893617, "percentage": 88.89, "elapsed_time": "0:50:49", "remaining_time": "0:06:21"}
209
+ {"current_steps": 209, "total_steps": 234, "loss": 0.6243, "lr": 3.4563125677897936e-07, "epoch": 2.6680851063829785, "percentage": 89.32, "elapsed_time": "0:51:00", "remaining_time": "0:06:06"}
210
+ {"current_steps": 210, "total_steps": 234, "loss": 0.7003, "lr": 3.18825646801314e-07, "epoch": 2.6808510638297873, "percentage": 89.74, "elapsed_time": "0:51:16", "remaining_time": "0:05:51"}
211
+ {"current_steps": 211, "total_steps": 234, "loss": 0.7206, "lr": 2.930676666954846e-07, "epoch": 2.6936170212765957, "percentage": 90.17, "elapsed_time": "0:51:32", "remaining_time": "0:05:37"}
212
+ {"current_steps": 212, "total_steps": 234, "loss": 0.6196, "lr": 2.6836308100417874e-07, "epoch": 2.706382978723404, "percentage": 90.6, "elapsed_time": "0:51:43", "remaining_time": "0:05:22"}
213
+ {"current_steps": 213, "total_steps": 234, "loss": 0.7903, "lr": 2.447174185242324e-07, "epoch": 2.719148936170213, "percentage": 91.03, "elapsed_time": "0:51:58", "remaining_time": "0:05:07"}
214
+ {"current_steps": 214, "total_steps": 234, "loss": 0.6996, "lr": 2.2213597106929608e-07, "epoch": 2.731914893617021, "percentage": 91.45, "elapsed_time": "0:52:12", "remaining_time": "0:04:52"}
215
+ {"current_steps": 215, "total_steps": 234, "loss": 0.706, "lr": 2.006237922855553e-07, "epoch": 2.74468085106383, "percentage": 91.88, "elapsed_time": "0:52:25", "remaining_time": "0:04:37"}
216
+ {"current_steps": 216, "total_steps": 234, "loss": 0.6336, "lr": 1.801856965207338e-07, "epoch": 2.7574468085106383, "percentage": 92.31, "elapsed_time": "0:52:38", "remaining_time": "0:04:23"}
217
+ {"current_steps": 217, "total_steps": 234, "loss": 0.6656, "lr": 1.6082625774666793e-07, "epoch": 2.7702127659574467, "percentage": 92.74, "elapsed_time": "0:52:52", "remaining_time": "0:04:08"}
218
+ {"current_steps": 218, "total_steps": 234, "loss": 0.7266, "lr": 1.4254980853566248e-07, "epoch": 2.7829787234042556, "percentage": 93.16, "elapsed_time": "0:53:08", "remaining_time": "0:03:54"}
219
+ {"current_steps": 219, "total_steps": 234, "loss": 0.6562, "lr": 1.253604390908819e-07, "epoch": 2.795744680851064, "percentage": 93.59, "elapsed_time": "0:53:22", "remaining_time": "0:03:39"}
220
+ {"current_steps": 220, "total_steps": 234, "loss": 0.6747, "lr": 1.0926199633097156e-07, "epoch": 2.8085106382978724, "percentage": 94.02, "elapsed_time": "0:53:34", "remaining_time": "0:03:24"}
221
+ {"current_steps": 221, "total_steps": 234, "loss": 0.6722, "lr": 9.42580830291373e-08, "epoch": 2.821276595744681, "percentage": 94.44, "elapsed_time": "0:53:45", "remaining_time": "0:03:09"}
222
+ {"current_steps": 222, "total_steps": 234, "loss": 0.7334, "lr": 8.035205700685167e-08, "epoch": 2.8340425531914892, "percentage": 94.87, "elapsed_time": "0:54:00", "remaining_time": "0:02:55"}
223
+ {"current_steps": 223, "total_steps": 234, "loss": 0.6765, "lr": 6.75470303823933e-08, "epoch": 2.846808510638298, "percentage": 95.3, "elapsed_time": "0:54:15", "remaining_time": "0:02:40"}
224
+ {"current_steps": 224, "total_steps": 234, "loss": 0.6531, "lr": 5.584586887435739e-08, "epoch": 2.8595744680851065, "percentage": 95.73, "elapsed_time": "0:54:28", "remaining_time": "0:02:25"}
225
+ {"current_steps": 225, "total_steps": 234, "loss": 0.7047, "lr": 4.52511911603265e-08, "epoch": 2.872340425531915, "percentage": 96.15, "elapsed_time": "0:54:41", "remaining_time": "0:02:11"}
226
+ {"current_steps": 226, "total_steps": 234, "loss": 0.7151, "lr": 3.576536829081323e-08, "epoch": 2.8851063829787233, "percentage": 96.58, "elapsed_time": "0:54:55", "remaining_time": "0:01:56"}
227
+ {"current_steps": 227, "total_steps": 234, "loss": 0.7742, "lr": 2.7390523158633552e-08, "epoch": 2.8978723404255318, "percentage": 97.01, "elapsed_time": "0:55:09", "remaining_time": "0:01:42"}
228
+ {"current_steps": 228, "total_steps": 234, "loss": 0.6379, "lr": 2.012853002380466e-08, "epoch": 2.9106382978723406, "percentage": 97.44, "elapsed_time": "0:55:21", "remaining_time": "0:01:27"}
229
+ {"current_steps": 229, "total_steps": 234, "loss": 0.7514, "lr": 1.3981014094099354e-08, "epoch": 2.923404255319149, "percentage": 97.86, "elapsed_time": "0:55:37", "remaining_time": "0:01:12"}
230
+ {"current_steps": 230, "total_steps": 234, "loss": 0.7313, "lr": 8.949351161324227e-09, "epoch": 2.9361702127659575, "percentage": 98.29, "elapsed_time": "0:55:51", "remaining_time": "0:00:58"}
231
+ {"current_steps": 231, "total_steps": 234, "loss": 0.5988, "lr": 5.034667293427053e-09, "epoch": 2.948936170212766, "percentage": 98.72, "elapsed_time": "0:56:08", "remaining_time": "0:00:43"}
232
+ {"current_steps": 232, "total_steps": 234, "loss": 0.7718, "lr": 2.237838582483387e-09, "epoch": 2.9617021276595743, "percentage": 99.15, "elapsed_time": "0:56:22", "remaining_time": "0:00:29"}
233
+ {"current_steps": 233, "total_steps": 234, "loss": 0.6915, "lr": 5.594909486328348e-10, "epoch": 2.974468085106383, "percentage": 99.57, "elapsed_time": "0:56:37", "remaining_time": "0:00:14"}
234
+ {"current_steps": 234, "total_steps": 234, "loss": 0.7312, "lr": 0.0, "epoch": 2.9872340425531916, "percentage": 100.0, "elapsed_time": "0:56:51", "remaining_time": "0:00:00"}
235
+ {"current_steps": 234, "total_steps": 234, "epoch": 2.9872340425531916, "percentage": 100.0, "elapsed_time": "0:58:54", "remaining_time": "0:00:00"}