sedrickkeh commited on
Commit
0c36e87
·
verified ·
1 Parent(s): 6c36338

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 sha256:7a6b436cb508baba054ff9bf139e01549c013b0fbe21fe52ebfcee7b37000375
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b937356a11de7765df782058109eb92a08bd80f1facbfdcc5fed0129d2f13d7e
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65154e1b2a59f015516cb07add8fb5ebeb9c0724f13a985544b028f288980c1c
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:320bd4c3cc2080091c18f3ab0b70d39c5d83b3cd67960ed84e4abf3ae1a4ab7d
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:d395b1a92eeca8efe013a6ee03743457331dbf5fa648226c8693dc1859054be9
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e39d139b061470c718265467e436a4cf9282a3a1ae657bd20563dc789a968892
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:823c7c5df2d8ac48018a3a275859584ad1c2f13e9792b10dd4737156ffbda2b8
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a367c3f610e995972c4c30fcb7677595f906f2f3529b0a78dc89e6b92e05a0bc
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -132,3 +132,70 @@
132
  {"current_steps": 132, "total_steps": 335, "loss": 0.3802, "lr": 6.083761361951722e-05, "epoch": 1.9664804469273744, "percentage": 39.4, "elapsed_time": "5:34:53", "remaining_time": "8:35:00"}
133
  {"current_steps": 133, "total_steps": 335, "loss": 0.3773, "lr": 6.048012077309612e-05, "epoch": 1.9813780260707636, "percentage": 39.7, "elapsed_time": "5:37:24", "remaining_time": "8:32:27"}
134
  {"current_steps": 134, "total_steps": 335, "loss": 0.3832, "lr": 6.01203969484827e-05, "epoch": 1.9962756052141528, "percentage": 40.0, "elapsed_time": "5:39:53", "remaining_time": "8:29:50"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
132
  {"current_steps": 132, "total_steps": 335, "loss": 0.3802, "lr": 6.083761361951722e-05, "epoch": 1.9664804469273744, "percentage": 39.4, "elapsed_time": "5:34:53", "remaining_time": "8:35:00"}
133
  {"current_steps": 133, "total_steps": 335, "loss": 0.3773, "lr": 6.048012077309612e-05, "epoch": 1.9813780260707636, "percentage": 39.7, "elapsed_time": "5:37:24", "remaining_time": "8:32:27"}
134
  {"current_steps": 134, "total_steps": 335, "loss": 0.3832, "lr": 6.01203969484827e-05, "epoch": 1.9962756052141528, "percentage": 40.0, "elapsed_time": "5:39:53", "remaining_time": "8:29:50"}
135
+ {"current_steps": 135, "total_steps": 335, "loss": 0.7025, "lr": 5.975848133177442e-05, "epoch": 2.011173184357542, "percentage": 40.3, "elapsed_time": "5:44:02", "remaining_time": "8:29:41"}
136
+ {"current_steps": 136, "total_steps": 335, "loss": 0.3581, "lr": 5.939441334782901e-05, "epoch": 2.026070763500931, "percentage": 40.6, "elapsed_time": "5:46:32", "remaining_time": "8:27:03"}
137
+ {"current_steps": 137, "total_steps": 335, "loss": 0.3662, "lr": 5.9028232655969866e-05, "epoch": 2.0409683426443204, "percentage": 40.9, "elapsed_time": "5:49:02", "remaining_time": "8:24:27"}
138
+ {"current_steps": 138, "total_steps": 335, "loss": 0.3606, "lr": 5.865997914566577e-05, "epoch": 2.0558659217877095, "percentage": 41.19, "elapsed_time": "5:51:33", "remaining_time": "8:21:51"}
139
+ {"current_steps": 139, "total_steps": 335, "loss": 0.3619, "lr": 5.8289692932185546e-05, "epoch": 2.0707635009310987, "percentage": 41.49, "elapsed_time": "5:54:05", "remaining_time": "8:19:17"}
140
+ {"current_steps": 140, "total_steps": 335, "loss": 0.3613, "lr": 5.791741435222821e-05, "epoch": 2.085661080074488, "percentage": 41.79, "elapsed_time": "5:56:37", "remaining_time": "8:16:43"}
141
+ {"current_steps": 141, "total_steps": 335, "loss": 0.3523, "lr": 5.7543183959528886e-05, "epoch": 2.100558659217877, "percentage": 42.09, "elapsed_time": "5:59:07", "remaining_time": "8:14:07"}
142
+ {"current_steps": 142, "total_steps": 335, "loss": 0.3543, "lr": 5.716704252044116e-05, "epoch": 2.1154562383612663, "percentage": 42.39, "elapsed_time": "6:01:38", "remaining_time": "8:11:31"}
143
+ {"current_steps": 143, "total_steps": 335, "loss": 0.3564, "lr": 5.678903100949625e-05, "epoch": 2.1303538175046555, "percentage": 42.69, "elapsed_time": "6:04:09", "remaining_time": "8:08:56"}
144
+ {"current_steps": 144, "total_steps": 335, "loss": 0.3547, "lr": 5.640919060493948e-05, "epoch": 2.1452513966480447, "percentage": 42.99, "elapsed_time": "6:06:40", "remaining_time": "8:06:20"}
145
+ {"current_steps": 145, "total_steps": 335, "loss": 0.3521, "lr": 5.602756268424457e-05, "epoch": 2.160148975791434, "percentage": 43.28, "elapsed_time": "6:09:10", "remaining_time": "8:03:44"}
146
+ {"current_steps": 146, "total_steps": 335, "loss": 0.3525, "lr": 5.564418881960624e-05, "epoch": 2.175046554934823, "percentage": 43.58, "elapsed_time": "6:11:41", "remaining_time": "8:01:09"}
147
+ {"current_steps": 147, "total_steps": 335, "loss": 0.3578, "lr": 5.5259110773411596e-05, "epoch": 2.189944134078212, "percentage": 43.88, "elapsed_time": "6:14:11", "remaining_time": "7:58:33"}
148
+ {"current_steps": 148, "total_steps": 335, "loss": 0.3485, "lr": 5.487237049369075e-05, "epoch": 2.2048417132216014, "percentage": 44.18, "elapsed_time": "6:16:41", "remaining_time": "7:55:57"}
149
+ {"current_steps": 149, "total_steps": 335, "loss": 0.3482, "lr": 5.448401010954733e-05, "epoch": 2.2197392923649906, "percentage": 44.48, "elapsed_time": "6:19:12", "remaining_time": "7:53:21"}
150
+ {"current_steps": 150, "total_steps": 335, "loss": 0.3465, "lr": 5.4094071926569146e-05, "epoch": 2.2346368715083798, "percentage": 44.78, "elapsed_time": "6:21:43", "remaining_time": "7:50:48"}
151
+ {"current_steps": 151, "total_steps": 335, "loss": 0.3574, "lr": 5.370259842221972e-05, "epoch": 2.249534450651769, "percentage": 45.07, "elapsed_time": "6:24:14", "remaining_time": "7:48:13"}
152
+ {"current_steps": 152, "total_steps": 335, "loss": 0.356, "lr": 5.330963224121096e-05, "epoch": 2.264432029795158, "percentage": 45.37, "elapsed_time": "6:26:44", "remaining_time": "7:45:37"}
153
+ {"current_steps": 153, "total_steps": 335, "loss": 0.3536, "lr": 5.291521619085785e-05, "epoch": 2.2793296089385473, "percentage": 45.67, "elapsed_time": "6:29:15", "remaining_time": "7:43:02"}
154
+ {"current_steps": 154, "total_steps": 335, "loss": 0.3494, "lr": 5.251939323641516e-05, "epoch": 2.294227188081937, "percentage": 45.97, "elapsed_time": "6:31:45", "remaining_time": "7:40:27"}
155
+ {"current_steps": 155, "total_steps": 335, "loss": 0.3511, "lr": 5.212220649639715e-05, "epoch": 2.3091247672253257, "percentage": 46.27, "elapsed_time": "6:34:16", "remaining_time": "7:37:52"}
156
+ {"current_steps": 156, "total_steps": 335, "loss": 0.3589, "lr": 5.172369923788046e-05, "epoch": 2.3240223463687153, "percentage": 46.57, "elapsed_time": "6:36:47", "remaining_time": "7:35:17"}
157
+ {"current_steps": 157, "total_steps": 335, "loss": 0.3537, "lr": 5.132391487179088e-05, "epoch": 2.338919925512104, "percentage": 46.87, "elapsed_time": "6:39:18", "remaining_time": "7:32:43"}
158
+ {"current_steps": 158, "total_steps": 335, "loss": 0.3483, "lr": 5.092289694817446e-05, "epoch": 2.3538175046554937, "percentage": 47.16, "elapsed_time": "6:41:49", "remaining_time": "7:30:08"}
159
+ {"current_steps": 159, "total_steps": 335, "loss": 0.3571, "lr": 5.052068915145336e-05, "epoch": 2.368715083798883, "percentage": 47.46, "elapsed_time": "6:44:20", "remaining_time": "7:27:34"}
160
+ {"current_steps": 160, "total_steps": 335, "loss": 0.3446, "lr": 5.011733529566723e-05, "epoch": 2.383612662942272, "percentage": 47.76, "elapsed_time": "6:46:51", "remaining_time": "7:24:59"}
161
+ {"current_steps": 161, "total_steps": 335, "loss": 0.3482, "lr": 4.971287931970033e-05, "epoch": 2.398510242085661, "percentage": 48.06, "elapsed_time": "6:49:22", "remaining_time": "7:22:25"}
162
+ {"current_steps": 162, "total_steps": 335, "loss": 0.3473, "lr": 4.9307365282495075e-05, "epoch": 2.4134078212290504, "percentage": 48.36, "elapsed_time": "6:51:52", "remaining_time": "7:19:50"}
163
+ {"current_steps": 163, "total_steps": 335, "loss": 0.3531, "lr": 4.890083735825258e-05, "epoch": 2.4283054003724396, "percentage": 48.66, "elapsed_time": "6:54:24", "remaining_time": "7:17:17"}
164
+ {"current_steps": 164, "total_steps": 335, "loss": 0.3516, "lr": 4.849333983162056e-05, "epoch": 2.4432029795158288, "percentage": 48.96, "elapsed_time": "6:56:55", "remaining_time": "7:14:43"}
165
+ {"current_steps": 165, "total_steps": 335, "loss": 0.356, "lr": 4.808491709286921e-05, "epoch": 2.458100558659218, "percentage": 49.25, "elapsed_time": "6:59:26", "remaining_time": "7:12:09"}
166
+ {"current_steps": 166, "total_steps": 335, "loss": 0.3491, "lr": 4.76756136330557e-05, "epoch": 2.472998137802607, "percentage": 49.55, "elapsed_time": "7:01:58", "remaining_time": "7:09:35"}
167
+ {"current_steps": 167, "total_steps": 335, "loss": 0.3435, "lr": 4.726547403917746e-05, "epoch": 2.4878957169459963, "percentage": 49.85, "elapsed_time": "7:04:29", "remaining_time": "7:07:02"}
168
+ {"current_steps": 168, "total_steps": 335, "loss": 0.3506, "lr": 4.685454298931527e-05, "epoch": 2.5027932960893855, "percentage": 50.15, "elapsed_time": "7:07:01", "remaining_time": "7:04:28"}
169
+ {"current_steps": 169, "total_steps": 335, "loss": 0.3547, "lr": 4.6442865247766203e-05, "epoch": 2.5176908752327747, "percentage": 50.45, "elapsed_time": "7:09:33", "remaining_time": "7:01:56"}
170
+ {"current_steps": 170, "total_steps": 335, "loss": 0.3486, "lr": 4.603048566016735e-05, "epoch": 2.532588454376164, "percentage": 50.75, "elapsed_time": "7:12:05", "remaining_time": "6:59:23"}
171
+ {"current_steps": 171, "total_steps": 335, "loss": 0.3483, "lr": 4.5617449148610584e-05, "epoch": 2.547486033519553, "percentage": 51.04, "elapsed_time": "7:14:39", "remaining_time": "6:56:51"}
172
+ {"current_steps": 172, "total_steps": 335, "loss": 0.3477, "lr": 4.520380070674902e-05, "epoch": 2.5623836126629422, "percentage": 51.34, "elapsed_time": "7:17:10", "remaining_time": "6:54:18"}
173
+ {"current_steps": 173, "total_steps": 335, "loss": 0.3571, "lr": 4.478958539489569e-05, "epoch": 2.5772811918063314, "percentage": 51.64, "elapsed_time": "7:19:42", "remaining_time": "6:51:45"}
174
+ {"current_steps": 174, "total_steps": 335, "loss": 0.3522, "lr": 4.437484833511499e-05, "epoch": 2.5921787709497206, "percentage": 51.94, "elapsed_time": "7:22:12", "remaining_time": "6:49:10"}
175
+ {"current_steps": 175, "total_steps": 335, "loss": 0.3413, "lr": 4.395963470630723e-05, "epoch": 2.60707635009311, "percentage": 52.24, "elapsed_time": "7:24:43", "remaining_time": "6:46:36"}
176
+ {"current_steps": 176, "total_steps": 335, "loss": 0.3477, "lr": 4.3543989739287326e-05, "epoch": 2.621973929236499, "percentage": 52.54, "elapsed_time": "7:27:13", "remaining_time": "6:44:01"}
177
+ {"current_steps": 177, "total_steps": 335, "loss": 0.3483, "lr": 4.312795871185742e-05, "epoch": 2.636871508379888, "percentage": 52.84, "elapsed_time": "7:29:43", "remaining_time": "6:41:27"}
178
+ {"current_steps": 178, "total_steps": 335, "loss": 0.3452, "lr": 4.2711586943874774e-05, "epoch": 2.6517690875232773, "percentage": 53.13, "elapsed_time": "7:32:13", "remaining_time": "6:38:52"}
179
+ {"current_steps": 179, "total_steps": 335, "loss": 0.3488, "lr": 4.2294919792314794e-05, "epoch": 2.6666666666666665, "percentage": 53.43, "elapsed_time": "7:34:45", "remaining_time": "6:36:19"}
180
+ {"current_steps": 180, "total_steps": 335, "loss": 0.3524, "lr": 4.1878002646330144e-05, "epoch": 2.6815642458100557, "percentage": 53.73, "elapsed_time": "7:37:16", "remaining_time": "6:33:45"}
181
+ {"current_steps": 181, "total_steps": 335, "loss": 0.3458, "lr": 4.1460880922306367e-05, "epoch": 2.6964618249534453, "percentage": 54.03, "elapsed_time": "7:39:47", "remaining_time": "6:31:12"}
182
+ {"current_steps": 182, "total_steps": 335, "loss": 0.3479, "lr": 4.1043600058914436e-05, "epoch": 2.711359404096834, "percentage": 54.33, "elapsed_time": "7:42:18", "remaining_time": "6:28:38"}
183
+ {"current_steps": 183, "total_steps": 335, "loss": 0.3503, "lr": 4.0626205512161034e-05, "epoch": 2.7262569832402237, "percentage": 54.63, "elapsed_time": "7:44:48", "remaining_time": "6:26:04"}
184
+ {"current_steps": 184, "total_steps": 335, "loss": 0.346, "lr": 4.020874275043679e-05, "epoch": 2.7411545623836124, "percentage": 54.93, "elapsed_time": "7:47:19", "remaining_time": "6:23:30"}
185
+ {"current_steps": 185, "total_steps": 335, "loss": 0.3506, "lr": 3.979125724956324e-05, "epoch": 2.756052141527002, "percentage": 55.22, "elapsed_time": "7:49:49", "remaining_time": "6:20:56"}
186
+ {"current_steps": 186, "total_steps": 335, "loss": 0.3502, "lr": 3.937379448783898e-05, "epoch": 2.770949720670391, "percentage": 55.52, "elapsed_time": "7:52:20", "remaining_time": "6:18:22"}
187
+ {"current_steps": 187, "total_steps": 335, "loss": 0.3541, "lr": 3.895639994108558e-05, "epoch": 2.7858472998137804, "percentage": 55.82, "elapsed_time": "7:54:50", "remaining_time": "6:15:48"}
188
+ {"current_steps": 188, "total_steps": 335, "loss": 0.3497, "lr": 3.853911907769365e-05, "epoch": 2.8007448789571696, "percentage": 56.12, "elapsed_time": "7:57:21", "remaining_time": "6:13:15"}
189
+ {"current_steps": 189, "total_steps": 335, "loss": 0.3473, "lr": 3.812199735366986e-05, "epoch": 2.815642458100559, "percentage": 56.42, "elapsed_time": "7:59:52", "remaining_time": "6:10:41"}
190
+ {"current_steps": 190, "total_steps": 335, "loss": 0.3489, "lr": 3.770508020768522e-05, "epoch": 2.830540037243948, "percentage": 56.72, "elapsed_time": "8:02:23", "remaining_time": "6:08:08"}
191
+ {"current_steps": 191, "total_steps": 335, "loss": 0.3464, "lr": 3.728841305612524e-05, "epoch": 2.845437616387337, "percentage": 57.01, "elapsed_time": "8:04:55", "remaining_time": "6:05:35"}
192
+ {"current_steps": 192, "total_steps": 335, "loss": 0.3428, "lr": 3.687204128814259e-05, "epoch": 2.8603351955307263, "percentage": 57.31, "elapsed_time": "8:07:25", "remaining_time": "6:03:02"}
193
+ {"current_steps": 193, "total_steps": 335, "loss": 0.3505, "lr": 3.645601026071269e-05, "epoch": 2.8752327746741155, "percentage": 57.61, "elapsed_time": "8:09:56", "remaining_time": "6:00:28"}
194
+ {"current_steps": 194, "total_steps": 335, "loss": 0.347, "lr": 3.604036529369277e-05, "epoch": 2.8901303538175047, "percentage": 57.91, "elapsed_time": "8:12:28", "remaining_time": "5:57:55"}
195
+ {"current_steps": 195, "total_steps": 335, "loss": 0.3461, "lr": 3.5625151664885036e-05, "epoch": 2.905027932960894, "percentage": 58.21, "elapsed_time": "8:15:01", "remaining_time": "5:55:24"}
196
+ {"current_steps": 196, "total_steps": 335, "loss": 0.3428, "lr": 3.5210414605104314e-05, "epoch": 2.919925512104283, "percentage": 58.51, "elapsed_time": "8:17:31", "remaining_time": "5:52:50"}
197
+ {"current_steps": 197, "total_steps": 335, "loss": 0.3479, "lr": 3.4796199293250987e-05, "epoch": 2.9348230912476723, "percentage": 58.81, "elapsed_time": "8:20:03", "remaining_time": "5:50:17"}
198
+ {"current_steps": 198, "total_steps": 335, "loss": 0.3464, "lr": 3.438255085138943e-05, "epoch": 2.9497206703910615, "percentage": 59.1, "elapsed_time": "8:22:34", "remaining_time": "5:47:44"}
199
+ {"current_steps": 199, "total_steps": 335, "loss": 0.3458, "lr": 3.396951433983266e-05, "epoch": 2.9646182495344506, "percentage": 59.4, "elapsed_time": "8:25:05", "remaining_time": "5:45:11"}
200
+ {"current_steps": 200, "total_steps": 335, "loss": 0.3463, "lr": 3.355713475223382e-05, "epoch": 2.97951582867784, "percentage": 59.7, "elapsed_time": "8:27:35", "remaining_time": "5:42:37"}
201
+ {"current_steps": 201, "total_steps": 335, "loss": 0.3491, "lr": 3.314545701068475e-05, "epoch": 2.994413407821229, "percentage": 60.0, "elapsed_time": "8:30:05", "remaining_time": "5:40:03"}