Hugging Face's logo

mlfoundations-dev
/
hp_ablations_grid_mistral_bsz512_lr2e-6_scheduler-cosine-warmup0.15-minlr5e-7

Text Generation
Transformers
Safetensors
mistral
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
sedrickkeh commited on
Commit
2e308d2
·
verified ·
1 Parent(s): 9bcc950

Training in progress, epoch 2

Browse files
Files changed (4) hide show
  1. model-00001-of-00003.safetensors +1 -1
  2. model-00002-of-00003.safetensors +1 -1
  3. model-00003-of-00003.safetensors +1 -1
  4. trainer_log.jsonl +67 -0
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0547d7f1891fc9b15e06a3adc9386f18c65126667804faba29f64c0b456df5af
3
  size 4943162336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e06c2f3d5502c91414b412d897a8a001c908a3169efc560880c0b8627849e4d3
3
  size 4943162336
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:60095d10b334e8ec56c55664ee63df0f7dccbba2d6d3e4fa295d4e905aa45c56
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:871b84e935225625a59e7786c07c81c5d33c9dd5399cbadd88c8f0ee7650aa25
3
  size 4999819336
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef125931df36772b576785d700f6e2e2fac6d3e1dec1720d6525f5ee0af37f9e
3
  size 4540516344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4475910810f6d35bbef6bf058aa53d1e86b19c756794289ea43e3b252258be09
3
  size 4540516344
trainer_log.jsonl CHANGED
@@ -134,3 +134,70 @@
134
  {"current_steps": 1330, "total_steps": 2013, "loss": 0.4233, "lr": 1.0164044604295092e-06, "epoch": 1.9804651162790696, "percentage": 66.07, "elapsed_time": "20:49:05", "remaining_time": "10:41:27"}
135
  {"current_steps": 1340, "total_steps": 2013, "loss": 0.4273, "lr": 1.0033586848823286e-06, "epoch": 1.9953488372093022, "percentage": 66.57, "elapsed_time": "20:58:24", "remaining_time": "10:32:01"}
136
  {"current_steps": 1342, "total_steps": 2013, "eval_loss": 0.05757646635174751, "epoch": 1.9983255813953489, "percentage": 66.67, "elapsed_time": "21:12:09", "remaining_time": "10:36:04"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
134
  {"current_steps": 1330, "total_steps": 2013, "loss": 0.4233, "lr": 1.0164044604295092e-06, "epoch": 1.9804651162790696, "percentage": 66.07, "elapsed_time": "20:49:05", "remaining_time": "10:41:27"}
135
  {"current_steps": 1340, "total_steps": 2013, "loss": 0.4273, "lr": 1.0033586848823286e-06, "epoch": 1.9953488372093022, "percentage": 66.57, "elapsed_time": "20:58:24", "remaining_time": "10:32:01"}
136
  {"current_steps": 1342, "total_steps": 2013, "eval_loss": 0.05757646635174751, "epoch": 1.9983255813953489, "percentage": 66.67, "elapsed_time": "21:12:09", "remaining_time": "10:36:04"}
137
+ {"current_steps": 1350, "total_steps": 2013, "loss": 0.3933, "lr": 9.903960576309687e-07, "epoch": 2.0111627906976746, "percentage": 67.06, "elapsed_time": "21:20:17", "remaining_time": "10:28:45"}
138
+ {"current_steps": 1360, "total_steps": 2013, "loss": 0.3784, "lr": 9.77520948666583e-07, "epoch": 2.026046511627907, "percentage": 67.56, "elapsed_time": "21:29:35", "remaining_time": "10:19:11"}
139
+ {"current_steps": 1370, "total_steps": 2013, "loss": 0.3811, "lr": 9.64737698475958e-07, "epoch": 2.0409302325581393, "percentage": 68.06, "elapsed_time": "21:38:54", "remaining_time": "10:09:37"}
140
+ {"current_steps": 1380, "total_steps": 2013, "loss": 0.3819, "lr": 9.520506165782327e-07, "epoch": 2.055813953488372, "percentage": 68.55, "elapsed_time": "21:48:12", "remaining_time": "10:00:04"}
141
+ {"current_steps": 1390, "total_steps": 2013, "loss": 0.3774, "lr": 9.394639800720695e-07, "epoch": 2.0706976744186045, "percentage": 69.05, "elapsed_time": "21:57:32", "remaining_time": "9:50:31"}
142
+ {"current_steps": 1400, "total_steps": 2013, "loss": 0.3822, "lr": 9.269820321937446e-07, "epoch": 2.085581395348837, "percentage": 69.55, "elapsed_time": "22:06:51", "remaining_time": "9:40:58"}
143
+ {"current_steps": 1410, "total_steps": 2013, "loss": 0.3783, "lr": 9.146089808866602e-07, "epoch": 2.1004651162790697, "percentage": 70.04, "elapsed_time": "22:16:09", "remaining_time": "9:31:25"}
144
+ {"current_steps": 1420, "total_steps": 2013, "loss": 0.3741, "lr": 9.023489973827518e-07, "epoch": 2.1153488372093023, "percentage": 70.54, "elapsed_time": "22:25:29", "remaining_time": "9:21:53"}
145
+ {"current_steps": 1430, "total_steps": 2013, "loss": 0.3802, "lr": 8.902062147962738e-07, "epoch": 2.130232558139535, "percentage": 71.04, "elapsed_time": "22:34:48", "remaining_time": "9:12:20"}
146
+ {"current_steps": 1440, "total_steps": 2013, "loss": 0.3759, "lr": 8.781847267304324e-07, "epoch": 2.1451162790697675, "percentage": 71.54, "elapsed_time": "22:44:07", "remaining_time": "9:02:48"}
147
+ {"current_steps": 1450, "total_steps": 2013, "loss": 0.3772, "lr": 8.662885858973442e-07, "epoch": 2.16, "percentage": 72.03, "elapsed_time": "22:53:26", "remaining_time": "8:53:16"}
148
+ {"current_steps": 1460, "total_steps": 2013, "loss": 0.3808, "lr": 8.545218027517718e-07, "epoch": 2.1748837209302327, "percentage": 72.53, "elapsed_time": "23:02:45", "remaining_time": "8:43:44"}
149
+ {"current_steps": 1470, "total_steps": 2013, "loss": 0.3748, "lr": 8.428883441391134e-07, "epoch": 2.1897674418604653, "percentage": 73.03, "elapsed_time": "23:12:03", "remaining_time": "8:34:12"}
150
+ {"current_steps": 1480, "total_steps": 2013, "loss": 0.3782, "lr": 8.313921319580899e-07, "epoch": 2.2046511627906975, "percentage": 73.52, "elapsed_time": "23:21:22", "remaining_time": "8:24:40"}
151
+ {"current_steps": 1490, "total_steps": 2013, "loss": 0.3803, "lr": 8.200370418385838e-07, "epoch": 2.21953488372093, "percentage": 74.02, "elapsed_time": "23:30:42", "remaining_time": "8:15:10"}
152
+ {"current_steps": 1500, "total_steps": 2013, "loss": 0.3811, "lr": 8.088269018350793e-07, "epoch": 2.2344186046511627, "percentage": 74.52, "elapsed_time": "23:40:02", "remaining_time": "8:05:39"}
153
+ {"current_steps": 1510, "total_steps": 2013, "loss": 0.3806, "lr": 7.977654911361391e-07, "epoch": 2.2493023255813953, "percentage": 75.01, "elapsed_time": "23:49:21", "remaining_time": "7:56:08"}
154
+ {"current_steps": 1520, "total_steps": 2013, "loss": 0.3796, "lr": 7.868565387903561e-07, "epoch": 2.264186046511628, "percentage": 75.51, "elapsed_time": "23:58:41", "remaining_time": "7:46:37"}
155
+ {"current_steps": 1530, "total_steps": 2013, "loss": 0.3747, "lr": 7.761037224492066e-07, "epoch": 2.2790697674418605, "percentage": 76.01, "elapsed_time": "1 day, 0:08:01", "remaining_time": "7:37:07"}
156
+ {"current_steps": 1540, "total_steps": 2013, "loss": 0.3777, "lr": 7.655106671272331e-07, "epoch": 2.293953488372093, "percentage": 76.5, "elapsed_time": "1 day, 0:17:19", "remaining_time": "7:27:36"}
157
+ {"current_steps": 1550, "total_steps": 2013, "loss": 0.3766, "lr": 7.5508094397997e-07, "epoch": 2.3088372093023257, "percentage": 77.0, "elapsed_time": "1 day, 0:26:39", "remaining_time": "7:18:06"}
158
+ {"current_steps": 1560, "total_steps": 2013, "loss": 0.3787, "lr": 7.448180691000282e-07, "epoch": 2.3237209302325583, "percentage": 77.5, "elapsed_time": "1 day, 0:35:59", "remaining_time": "7:08:36"}
159
+ {"current_steps": 1570, "total_steps": 2013, "loss": 0.3751, "lr": 7.34725502331741e-07, "epoch": 2.3386046511627905, "percentage": 77.99, "elapsed_time": "1 day, 0:45:18", "remaining_time": "6:59:06"}
160
+ {"current_steps": 1580, "total_steps": 2013, "loss": 0.3739, "lr": 7.248066461047738e-07, "epoch": 2.353488372093023, "percentage": 78.49, "elapsed_time": "1 day, 0:54:37", "remaining_time": "6:49:36"}
161
+ {"current_steps": 1590, "total_steps": 2013, "loss": 0.3785, "lr": 7.150648442870886e-07, "epoch": 2.3683720930232557, "percentage": 78.99, "elapsed_time": "1 day, 1:03:55", "remaining_time": "6:40:05"}
162
+ {"current_steps": 1600, "total_steps": 2013, "loss": 0.376, "lr": 7.055033810576521e-07, "epoch": 2.3832558139534883, "percentage": 79.48, "elapsed_time": "1 day, 1:13:14", "remaining_time": "6:30:36"}
163
+ {"current_steps": 1610, "total_steps": 2013, "loss": 0.3756, "lr": 6.961254797992642e-07, "epoch": 2.398139534883721, "percentage": 79.98, "elapsed_time": "1 day, 1:22:33", "remaining_time": "6:21:06"}
164
+ {"current_steps": 1620, "total_steps": 2013, "loss": 0.3785, "lr": 6.869343020118862e-07, "epoch": 2.4130232558139535, "percentage": 80.48, "elapsed_time": "1 day, 1:31:52", "remaining_time": "6:11:37"}
165
+ {"current_steps": 1630, "total_steps": 2013, "loss": 0.3738, "lr": 6.779329462468263e-07, "epoch": 2.427906976744186, "percentage": 80.97, "elapsed_time": "1 day, 1:41:10", "remaining_time": "6:02:07"}
166
+ {"current_steps": 1640, "total_steps": 2013, "loss": 0.3763, "lr": 6.691244470621486e-07, "epoch": 2.4427906976744187, "percentage": 81.47, "elapsed_time": "1 day, 1:50:30", "remaining_time": "5:52:38"}
167
+ {"current_steps": 1650, "total_steps": 2013, "loss": 0.3766, "lr": 6.605117739996584e-07, "epoch": 2.4576744186046513, "percentage": 81.97, "elapsed_time": "1 day, 1:59:49", "remaining_time": "5:43:09"}
168
+ {"current_steps": 1660, "total_steps": 2013, "loss": 0.3759, "lr": 6.520978305838008e-07, "epoch": 2.472558139534884, "percentage": 82.46, "elapsed_time": "1 day, 2:09:07", "remaining_time": "5:33:40"}
169
+ {"current_steps": 1670, "total_steps": 2013, "loss": 0.3748, "lr": 6.438854533428178e-07, "epoch": 2.4874418604651165, "percentage": 82.96, "elapsed_time": "1 day, 2:18:26", "remaining_time": "5:24:11"}
170
+ {"current_steps": 1680, "total_steps": 2013, "loss": 0.3781, "lr": 6.358774108524931e-07, "epoch": 2.5023255813953487, "percentage": 83.46, "elapsed_time": "1 day, 2:27:45", "remaining_time": "5:14:42"}
171
+ {"current_steps": 1690, "total_steps": 2013, "loss": 0.3774, "lr": 6.280764028028025e-07, "epoch": 2.5172093023255813, "percentage": 83.95, "elapsed_time": "1 day, 2:37:04", "remaining_time": "5:05:14"}
172
+ {"current_steps": 1700, "total_steps": 2013, "loss": 0.3772, "lr": 6.204850590877871e-07, "epoch": 2.532093023255814, "percentage": 84.45, "elapsed_time": "1 day, 2:46:23", "remaining_time": "4:55:45"}
173
+ {"current_steps": 1710, "total_steps": 2013, "loss": 0.3771, "lr": 6.131059389189585e-07, "epoch": 2.5469767441860465, "percentage": 84.95, "elapsed_time": "1 day, 2:55:41", "remaining_time": "4:46:17"}
174
+ {"current_steps": 1720, "total_steps": 2013, "loss": 0.3768, "lr": 6.059415299625312e-07, "epoch": 2.561860465116279, "percentage": 85.44, "elapsed_time": "1 day, 3:05:00", "remaining_time": "4:36:49"}
175
+ {"current_steps": 1730, "total_steps": 2013, "loss": 0.3829, "lr": 5.989942475007746e-07, "epoch": 2.5767441860465117, "percentage": 85.94, "elapsed_time": "1 day, 3:14:19", "remaining_time": "4:27:20"}
176
+ {"current_steps": 1740, "total_steps": 2013, "loss": 0.3791, "lr": 5.922664336177671e-07, "epoch": 2.5916279069767443, "percentage": 86.44, "elapsed_time": "1 day, 3:23:38", "remaining_time": "4:17:52"}
177
+ {"current_steps": 1750, "total_steps": 2013, "loss": 0.3763, "lr": 5.857603564098281e-07, "epoch": 2.606511627906977, "percentage": 86.93, "elapsed_time": "1 day, 3:32:56", "remaining_time": "4:08:24"}
178
+ {"current_steps": 1760, "total_steps": 2013, "loss": 0.3755, "lr": 5.794782092208914e-07, "epoch": 2.6213953488372095, "percentage": 87.43, "elapsed_time": "1 day, 3:42:15", "remaining_time": "3:58:56"}
179
+ {"current_steps": 1770, "total_steps": 2013, "loss": 0.3755, "lr": 5.734221099030799e-07, "epoch": 2.6362790697674416, "percentage": 87.93, "elapsed_time": "1 day, 3:51:34", "remaining_time": "3:49:29"}
180
+ {"current_steps": 1780, "total_steps": 2013, "loss": 0.3791, "lr": 5.675941001027307e-07, "epoch": 2.6511627906976747, "percentage": 88.43, "elapsed_time": "1 day, 4:00:54", "remaining_time": "3:40:01"}
181
+ {"current_steps": 1790, "total_steps": 2013, "loss": 0.3766, "lr": 5.619961445721106e-07, "epoch": 2.666046511627907, "percentage": 88.92, "elapsed_time": "1 day, 4:10:12", "remaining_time": "3:30:34"}
182
+ {"current_steps": 1800, "total_steps": 2013, "loss": 0.3749, "lr": 5.566301305070539e-07, "epoch": 2.6809302325581394, "percentage": 89.42, "elapsed_time": "1 day, 4:19:30", "remaining_time": "3:21:06"}
183
+ {"current_steps": 1810, "total_steps": 2013, "loss": 0.3756, "lr": 5.514978669107462e-07, "epoch": 2.695813953488372, "percentage": 89.92, "elapsed_time": "1 day, 4:28:50", "remaining_time": "3:11:39"}
184
+ {"current_steps": 1820, "total_steps": 2013, "loss": 0.3765, "lr": 5.466010839838704e-07, "epoch": 2.7106976744186047, "percentage": 90.41, "elapsed_time": "1 day, 4:38:09", "remaining_time": "3:02:12"}
185
+ {"current_steps": 1830, "total_steps": 2013, "loss": 0.3794, "lr": 5.419414325413161e-07, "epoch": 2.7255813953488373, "percentage": 90.91, "elapsed_time": "1 day, 4:47:28", "remaining_time": "2:52:44"}
186
+ {"current_steps": 1840, "total_steps": 2013, "loss": 0.3801, "lr": 5.375204834556529e-07, "epoch": 2.74046511627907, "percentage": 91.41, "elapsed_time": "1 day, 4:56:48", "remaining_time": "2:43:17"}
187
+ {"current_steps": 1850, "total_steps": 2013, "loss": 0.377, "lr": 5.333397271275555e-07, "epoch": 2.7553488372093025, "percentage": 91.9, "elapsed_time": "1 day, 5:06:07", "remaining_time": "2:33:50"}
188
+ {"current_steps": 1860, "total_steps": 2013, "loss": 0.3763, "lr": 5.294005729833554e-07, "epoch": 2.7702325581395346, "percentage": 92.4, "elapsed_time": "1 day, 5:15:27", "remaining_time": "2:24:24"}
189
+ {"current_steps": 1870, "total_steps": 2013, "loss": 0.3752, "lr": 5.257043489998916e-07, "epoch": 2.7851162790697677, "percentage": 92.9, "elapsed_time": "1 day, 5:24:45", "remaining_time": "2:14:57"}
190
+ {"current_steps": 1880, "total_steps": 2013, "loss": 0.376, "lr": 5.222523012568204e-07, "epoch": 2.8, "percentage": 93.39, "elapsed_time": "1 day, 5:34:04", "remaining_time": "2:05:30"}
191
+ {"current_steps": 1890, "total_steps": 2013, "loss": 0.3768, "lr": 5.190455935165343e-07, "epoch": 2.8148837209302324, "percentage": 93.89, "elapsed_time": "1 day, 5:43:23", "remaining_time": "1:56:03"}
192
+ {"current_steps": 1900, "total_steps": 2013, "loss": 0.3774, "lr": 5.160853068318311e-07, "epoch": 2.829767441860465, "percentage": 94.39, "elapsed_time": "1 day, 5:52:42", "remaining_time": "1:46:37"}
193
+ {"current_steps": 1910, "total_steps": 2013, "loss": 0.3749, "lr": 5.133724391814676e-07, "epoch": 2.8446511627906976, "percentage": 94.88, "elapsed_time": "1 day, 6:02:01", "remaining_time": "1:37:10"}
194
+ {"current_steps": 1920, "total_steps": 2013, "loss": 0.3757, "lr": 5.109079051337177e-07, "epoch": 2.8595348837209302, "percentage": 95.38, "elapsed_time": "1 day, 6:11:21", "remaining_time": "1:27:44"}
195
+ {"current_steps": 1930, "total_steps": 2013, "loss": 0.3737, "lr": 5.086925355380522e-07, "epoch": 2.874418604651163, "percentage": 95.88, "elapsed_time": "1 day, 6:20:38", "remaining_time": "1:18:17"}
196
+ {"current_steps": 1940, "total_steps": 2013, "loss": 0.3742, "lr": 5.067270772450396e-07, "epoch": 2.8893023255813954, "percentage": 96.37, "elapsed_time": "1 day, 6:29:56", "remaining_time": "1:08:51"}
197
+ {"current_steps": 1950, "total_steps": 2013, "loss": 0.3749, "lr": 5.050121928545672e-07, "epoch": 2.904186046511628, "percentage": 96.87, "elapsed_time": "1 day, 6:39:15", "remaining_time": "0:59:25"}
198
+ {"current_steps": 1960, "total_steps": 2013, "loss": 0.3708, "lr": 5.035484604924633e-07, "epoch": 2.9190697674418606, "percentage": 97.37, "elapsed_time": "1 day, 6:48:33", "remaining_time": "0:49:59"}
199
+ {"current_steps": 1970, "total_steps": 2013, "loss": 0.379, "lr": 5.023363736155983e-07, "epoch": 2.933953488372093, "percentage": 97.86, "elapsed_time": "1 day, 6:57:50", "remaining_time": "0:40:33"}
200
+ {"current_steps": 1980, "total_steps": 2013, "loss": 0.3752, "lr": 5.013763408455293e-07, "epoch": 2.948837209302326, "percentage": 98.36, "elapsed_time": "1 day, 7:07:09", "remaining_time": "0:31:07"}
201
+ {"current_steps": 1990, "total_steps": 2013, "loss": 0.3727, "lr": 5.00668685830744e-07, "epoch": 2.963720930232558, "percentage": 98.86, "elapsed_time": "1 day, 7:16:28", "remaining_time": "0:21:41"}
202
+ {"current_steps": 2000, "total_steps": 2013, "loss": 0.3743, "lr": 5.002136471375532e-07, "epoch": 2.9786046511627906, "percentage": 99.35, "elapsed_time": "1 day, 7:25:46", "remaining_time": "0:12:15"}
203
+ {"current_steps": 2010, "total_steps": 2013, "loss": 0.3733, "lr": 5.00011378169663e-07, "epoch": 2.993488372093023, "percentage": 99.85, "elapsed_time": "1 day, 7:35:03", "remaining_time": "0:02:49"}