gsmyrnis commited on
Commit
d6e0ac3
·
verified ·
1 Parent(s): 3d58e05

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 sha256:7af73746593b96d6afba9df3dd58e5fec81f644348e67e834d7eeb4efa0d4fdf
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c03b780b8f606572d7541645ccfdbeda66badfc65e55c5e7d3f5c4bcbe831b0
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2b01c60f6a9f4c530e732e8413d15588820e10d0c913ec6561b709fafa2e6c22
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77c3182c00519c057cfb3ebac53a86754abb5b1782fbae7ea217648851116fb1
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:78c29daf3c03bdc8023e8f4ab09f1dd8f0cf9cb9f009c0a49bf59be9a876b33b
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bb9cf3e42776a349b2d29d8339c2756e1de2ab54425cdbd4c204051006b4dbf
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:ecff724064526b09f8290dab5ecbe2dbfed508c2465d992a750de8dc06826127
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f261a9457639675730e409f1877bb78c06503099f57a9838a68e56e02fb207c
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -156,3 +156,62 @@
156
  {"current_steps": 156, "total_steps": 216, "loss": 0.3362, "lr": 2.1802148507454675e-06, "epoch": 2.1566820276497696, "percentage": 72.22, "elapsed_time": "0:30:38", "remaining_time": "0:11:47"}
157
  {"current_steps": 157, "total_steps": 216, "loss": 0.3712, "lr": 2.1137230548049042e-06, "epoch": 2.1705069124423964, "percentage": 72.69, "elapsed_time": "0:30:51", "remaining_time": "0:11:35"}
158
  {"current_steps": 158, "total_steps": 216, "loss": 0.3289, "lr": 2.0479881349703885e-06, "epoch": 2.184331797235023, "percentage": 73.15, "elapsed_time": "0:31:01", "remaining_time": "0:11:23"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
156
  {"current_steps": 156, "total_steps": 216, "loss": 0.3362, "lr": 2.1802148507454675e-06, "epoch": 2.1566820276497696, "percentage": 72.22, "elapsed_time": "0:30:38", "remaining_time": "0:11:47"}
157
  {"current_steps": 157, "total_steps": 216, "loss": 0.3712, "lr": 2.1137230548049042e-06, "epoch": 2.1705069124423964, "percentage": 72.69, "elapsed_time": "0:30:51", "remaining_time": "0:11:35"}
158
  {"current_steps": 158, "total_steps": 216, "loss": 0.3289, "lr": 2.0479881349703885e-06, "epoch": 2.184331797235023, "percentage": 73.15, "elapsed_time": "0:31:01", "remaining_time": "0:11:23"}
159
+ {"current_steps": 159, "total_steps": 216, "loss": 0.3648, "lr": 1.983027329085377e-06, "epoch": 2.19815668202765, "percentage": 73.61, "elapsed_time": "0:31:13", "remaining_time": "0:11:11"}
160
+ {"current_steps": 160, "total_steps": 216, "loss": 0.2849, "lr": 1.9188576719953635e-06, "epoch": 2.2119815668202767, "percentage": 74.07, "elapsed_time": "0:31:26", "remaining_time": "0:11:00"}
161
+ {"current_steps": 161, "total_steps": 216, "loss": 0.3695, "lr": 1.8554959910807773e-06, "epoch": 2.225806451612903, "percentage": 74.54, "elapsed_time": "0:31:35", "remaining_time": "0:10:47"}
162
+ {"current_steps": 162, "total_steps": 216, "loss": 0.3504, "lr": 1.7929589018443016e-06, "epoch": 2.23963133640553, "percentage": 75.0, "elapsed_time": "0:31:46", "remaining_time": "0:10:35"}
163
+ {"current_steps": 163, "total_steps": 216, "loss": 0.332, "lr": 1.7312628035537388e-06, "epoch": 2.2534562211981566, "percentage": 75.46, "elapsed_time": "0:31:57", "remaining_time": "0:10:23"}
164
+ {"current_steps": 164, "total_steps": 216, "loss": 0.3387, "lr": 1.6704238749415958e-06, "epoch": 2.2672811059907834, "percentage": 75.93, "elapsed_time": "0:32:11", "remaining_time": "0:10:12"}
165
+ {"current_steps": 165, "total_steps": 216, "loss": 0.3592, "lr": 1.6104580699624839e-06, "epoch": 2.28110599078341, "percentage": 76.39, "elapsed_time": "0:32:21", "remaining_time": "0:10:00"}
166
+ {"current_steps": 166, "total_steps": 216, "loss": 0.3063, "lr": 1.5513811136094786e-06, "epoch": 2.294930875576037, "percentage": 76.85, "elapsed_time": "0:32:31", "remaining_time": "0:09:47"}
167
+ {"current_steps": 167, "total_steps": 216, "loss": 0.3254, "lr": 1.4932084977905043e-06, "epoch": 2.3087557603686637, "percentage": 77.31, "elapsed_time": "0:32:41", "remaining_time": "0:09:35"}
168
+ {"current_steps": 168, "total_steps": 216, "loss": 0.3774, "lr": 1.4359554772658551e-06, "epoch": 2.3225806451612905, "percentage": 77.78, "elapsed_time": "0:32:54", "remaining_time": "0:09:24"}
169
+ {"current_steps": 169, "total_steps": 216, "loss": 0.3325, "lr": 1.3796370656478936e-06, "epoch": 2.3364055299539173, "percentage": 78.24, "elapsed_time": "0:33:03", "remaining_time": "0:09:11"}
170
+ {"current_steps": 170, "total_steps": 216, "loss": 0.3373, "lr": 1.3242680314639995e-06, "epoch": 2.3502304147465436, "percentage": 78.7, "elapsed_time": "0:33:15", "remaining_time": "0:09:00"}
171
+ {"current_steps": 171, "total_steps": 216, "loss": 0.3427, "lr": 1.2698628942837698e-06, "epoch": 2.3640552995391704, "percentage": 79.17, "elapsed_time": "0:33:22", "remaining_time": "0:08:47"}
172
+ {"current_steps": 172, "total_steps": 216, "loss": 0.3257, "lr": 1.2164359209115235e-06, "epoch": 2.377880184331797, "percentage": 79.63, "elapsed_time": "0:33:35", "remaining_time": "0:08:35"}
173
+ {"current_steps": 173, "total_steps": 216, "loss": 0.3772, "lr": 1.164001121645069e-06, "epoch": 2.391705069124424, "percentage": 80.09, "elapsed_time": "0:33:46", "remaining_time": "0:08:23"}
174
+ {"current_steps": 174, "total_steps": 216, "loss": 0.326, "lr": 1.1125722466017547e-06, "epoch": 2.4055299539170507, "percentage": 80.56, "elapsed_time": "0:33:56", "remaining_time": "0:08:11"}
175
+ {"current_steps": 175, "total_steps": 216, "loss": 0.3947, "lr": 1.062162782112729e-06, "epoch": 2.4193548387096775, "percentage": 81.02, "elapsed_time": "0:34:10", "remaining_time": "0:08:00"}
176
+ {"current_steps": 176, "total_steps": 216, "loss": 0.3027, "lr": 1.012785947186397e-06, "epoch": 2.4331797235023043, "percentage": 81.48, "elapsed_time": "0:34:20", "remaining_time": "0:07:48"}
177
+ {"current_steps": 177, "total_steps": 216, "loss": 0.3306, "lr": 9.644546900419533e-07, "epoch": 2.447004608294931, "percentage": 81.94, "elapsed_time": "0:34:26", "remaining_time": "0:07:35"}
178
+ {"current_steps": 178, "total_steps": 216, "loss": 0.3596, "lr": 9.171816847139447e-07, "epoch": 2.460829493087558, "percentage": 82.41, "elapsed_time": "0:34:37", "remaining_time": "0:07:23"}
179
+ {"current_steps": 179, "total_steps": 216, "loss": 0.3684, "lr": 8.709793277287182e-07, "epoch": 2.474654377880184, "percentage": 82.87, "elapsed_time": "0:34:45", "remaining_time": "0:07:11"}
180
+ {"current_steps": 180, "total_steps": 216, "loss": 0.32, "lr": 8.258597348536452e-07, "epoch": 2.488479262672811, "percentage": 83.33, "elapsed_time": "0:34:54", "remaining_time": "0:06:58"}
181
+ {"current_steps": 181, "total_steps": 216, "loss": 0.3273, "lr": 7.818347379199781e-07, "epoch": 2.5023041474654377, "percentage": 83.8, "elapsed_time": "0:35:09", "remaining_time": "0:06:47"}
182
+ {"current_steps": 182, "total_steps": 216, "loss": 0.3313, "lr": 7.389158817201541e-07, "epoch": 2.5161290322580645, "percentage": 84.26, "elapsed_time": "0:35:20", "remaining_time": "0:06:36"}
183
+ {"current_steps": 183, "total_steps": 216, "loss": 0.369, "lr": 6.971144209803738e-07, "epoch": 2.5299539170506913, "percentage": 84.72, "elapsed_time": "0:35:31", "remaining_time": "0:06:24"}
184
+ {"current_steps": 184, "total_steps": 216, "loss": 0.3464, "lr": 6.564413174092443e-07, "epoch": 2.543778801843318, "percentage": 85.19, "elapsed_time": "0:35:38", "remaining_time": "0:06:11"}
185
+ {"current_steps": 185, "total_steps": 216, "loss": 0.3334, "lr": 6.16907236823262e-07, "epoch": 2.557603686635945, "percentage": 85.65, "elapsed_time": "0:35:49", "remaining_time": "0:06:00"}
186
+ {"current_steps": 186, "total_steps": 216, "loss": 0.3336, "lr": 5.785225463498828e-07, "epoch": 2.571428571428571, "percentage": 86.11, "elapsed_time": "0:35:59", "remaining_time": "0:05:48"}
187
+ {"current_steps": 187, "total_steps": 216, "loss": 0.357, "lr": 5.412973117089288e-07, "epoch": 2.5852534562211984, "percentage": 86.57, "elapsed_time": "0:36:10", "remaining_time": "0:05:36"}
188
+ {"current_steps": 188, "total_steps": 216, "loss": 0.3389, "lr": 5.05241294573024e-07, "epoch": 2.5990783410138247, "percentage": 87.04, "elapsed_time": "0:36:18", "remaining_time": "0:05:24"}
189
+ {"current_steps": 189, "total_steps": 216, "loss": 0.3816, "lr": 4.7036395000776556e-07, "epoch": 2.6129032258064515, "percentage": 87.5, "elapsed_time": "0:36:31", "remaining_time": "0:05:13"}
190
+ {"current_steps": 190, "total_steps": 216, "loss": 0.3212, "lr": 4.3667442399229985e-07, "epoch": 2.6267281105990783, "percentage": 87.96, "elapsed_time": "0:36:42", "remaining_time": "0:05:01"}
191
+ {"current_steps": 191, "total_steps": 216, "loss": 0.349, "lr": 4.041815510209396e-07, "epoch": 2.640552995391705, "percentage": 88.43, "elapsed_time": "0:36:54", "remaining_time": "0:04:49"}
192
+ {"current_steps": 192, "total_steps": 216, "loss": 0.3155, "lr": 3.728938517864794e-07, "epoch": 2.654377880184332, "percentage": 88.89, "elapsed_time": "0:37:01", "remaining_time": "0:04:37"}
193
+ {"current_steps": 193, "total_steps": 216, "loss": 0.3608, "lr": 3.4281953094578877e-07, "epoch": 2.6682027649769586, "percentage": 89.35, "elapsed_time": "0:37:09", "remaining_time": "0:04:25"}
194
+ {"current_steps": 194, "total_steps": 216, "loss": 0.366, "lr": 3.1396647496828245e-07, "epoch": 2.6820276497695854, "percentage": 89.81, "elapsed_time": "0:37:23", "remaining_time": "0:04:14"}
195
+ {"current_steps": 195, "total_steps": 216, "loss": 0.3447, "lr": 2.8634225006782867e-07, "epoch": 2.6958525345622117, "percentage": 90.28, "elapsed_time": "0:37:33", "remaining_time": "0:04:02"}
196
+ {"current_steps": 196, "total_steps": 216, "loss": 0.3791, "lr": 2.599541002186479e-07, "epoch": 2.709677419354839, "percentage": 90.74, "elapsed_time": "0:37:44", "remaining_time": "0:03:51"}
197
+ {"current_steps": 197, "total_steps": 216, "loss": 0.303, "lr": 2.3480894525569564e-07, "epoch": 2.7235023041474653, "percentage": 91.2, "elapsed_time": "0:37:55", "remaining_time": "0:03:39"}
198
+ {"current_steps": 198, "total_steps": 216, "loss": 0.3427, "lr": 2.109133790600648e-07, "epoch": 2.737327188940092, "percentage": 91.67, "elapsed_time": "0:38:05", "remaining_time": "0:03:27"}
199
+ {"current_steps": 199, "total_steps": 216, "loss": 0.325, "lr": 1.8827366782984913e-07, "epoch": 2.751152073732719, "percentage": 92.13, "elapsed_time": "0:38:19", "remaining_time": "0:03:16"}
200
+ {"current_steps": 200, "total_steps": 216, "loss": 0.3852, "lr": 1.6689574843694433e-07, "epoch": 2.7649769585253456, "percentage": 92.59, "elapsed_time": "0:38:35", "remaining_time": "0:03:05"}
201
+ {"current_steps": 201, "total_steps": 216, "loss": 0.3513, "lr": 1.4678522687020414e-07, "epoch": 2.7788018433179724, "percentage": 93.06, "elapsed_time": "0:38:47", "remaining_time": "0:02:53"}
202
+ {"current_steps": 202, "total_steps": 216, "loss": 0.331, "lr": 1.2794737676536993e-07, "epoch": 2.792626728110599, "percentage": 93.52, "elapsed_time": "0:39:02", "remaining_time": "0:02:42"}
203
+ {"current_steps": 203, "total_steps": 216, "loss": 0.3411, "lr": 1.1038713802214718e-07, "epoch": 2.806451612903226, "percentage": 93.98, "elapsed_time": "0:39:13", "remaining_time": "0:02:30"}
204
+ {"current_steps": 204, "total_steps": 216, "loss": 0.3244, "lr": 9.410911550880474e-08, "epoch": 2.8202764976958523, "percentage": 94.44, "elapsed_time": "0:39:23", "remaining_time": "0:02:19"}
205
+ {"current_steps": 205, "total_steps": 216, "loss": 0.3417, "lr": 7.911757785462882e-08, "epoch": 2.8341013824884795, "percentage": 94.91, "elapsed_time": "0:39:33", "remaining_time": "0:02:07"}
206
+ {"current_steps": 206, "total_steps": 216, "loss": 0.3391, "lr": 6.54164563305465e-08, "epoch": 2.847926267281106, "percentage": 95.37, "elapsed_time": "0:39:44", "remaining_time": "0:01:55"}
207
+ {"current_steps": 207, "total_steps": 216, "loss": 0.3707, "lr": 5.3009343818219985e-08, "epoch": 2.8617511520737327, "percentage": 95.83, "elapsed_time": "0:40:00", "remaining_time": "0:01:44"}
208
+ {"current_steps": 208, "total_steps": 216, "loss": 0.351, "lr": 4.189949386787462e-08, "epoch": 2.8755760368663594, "percentage": 96.3, "elapsed_time": "0:40:14", "remaining_time": "0:01:32"}
209
+ {"current_steps": 209, "total_steps": 216, "loss": 0.3168, "lr": 3.2089819845111946e-08, "epoch": 2.889400921658986, "percentage": 96.76, "elapsed_time": "0:40:24", "remaining_time": "0:01:21"}
210
+ {"current_steps": 210, "total_steps": 216, "loss": 0.4198, "lr": 2.358289416693027e-08, "epoch": 2.903225806451613, "percentage": 97.22, "elapsed_time": "0:40:36", "remaining_time": "0:01:09"}
211
+ {"current_steps": 211, "total_steps": 216, "loss": 0.3174, "lr": 1.6380947627153143e-08, "epoch": 2.9170506912442398, "percentage": 97.69, "elapsed_time": "0:40:46", "remaining_time": "0:00:57"}
212
+ {"current_steps": 212, "total_steps": 216, "loss": 0.3538, "lr": 1.0485868811441757e-08, "epoch": 2.9308755760368665, "percentage": 98.15, "elapsed_time": "0:40:55", "remaining_time": "0:00:46"}
213
+ {"current_steps": 213, "total_steps": 216, "loss": 0.3474, "lr": 5.899203602046655e-09, "epoch": 2.944700460829493, "percentage": 98.61, "elapsed_time": "0:41:06", "remaining_time": "0:00:34"}
214
+ {"current_steps": 214, "total_steps": 216, "loss": 0.319, "lr": 2.6221547724253337e-09, "epoch": 2.9585253456221197, "percentage": 99.07, "elapsed_time": "0:41:14", "remaining_time": "0:00:23"}
215
+ {"current_steps": 215, "total_steps": 216, "loss": 0.3884, "lr": 6.555816718389896e-10, "epoch": 2.9723502304147464, "percentage": 99.54, "elapsed_time": "0:41:27", "remaining_time": "0:00:11"}
216
+ {"current_steps": 216, "total_steps": 216, "loss": 0.331, "lr": 0.0, "epoch": 2.986175115207373, "percentage": 100.0, "elapsed_time": "0:41:41", "remaining_time": "0:00:00"}
217
+ {"current_steps": 216, "total_steps": 216, "epoch": 2.986175115207373, "percentage": 100.0, "elapsed_time": "0:43:56", "remaining_time": "0:00:00"}