ryanmarten commited on
Commit
9cb37ee
·
verified ·
1 Parent(s): d5ef3eb

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:ad1cdf7e9dc78d77105d4a044605ada46a001bb8a5c8ce6f7559768ac14dc5b0
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:353908f767f8bc376c556d9be3e0eb6f0bfed147d1aec7355d27030bf571d1e7
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:a391ae7acf5756a185d555f7231f34689a51ea6aea483f392df911b6d5b4ce9c
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abaa66e0a6ecb6a69cffbd9efafd11b65298548c049ed5885375cf3f27b3b276
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:797876af006a2e0bdb12218fabdee91e9855d790680335d82936625e1bd63f11
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:647a9efba8e3d89687d9633185c6c37ae5ee1725f1073ca749e6a1bdc6d25c19
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:a1a76c9b2c5717f2a40be49322e1e071e3cfa6cd9029bd3a5bec89a32dca7f50
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e990bb35ef009dcf87cdef6d3970619de8aacb5b40c21b6819041cd0ab109f8
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -152,3 +152,80 @@
152
  {"current_steps": 152, "total_steps": 380, "loss": 0.5557, "lr": 6.000000000000001e-05, "epoch": 1.9772542648253453, "percentage": 40.0, "elapsed_time": "4:20:56", "remaining_time": "6:31:25"}
153
  {"current_steps": 153, "total_steps": 380, "loss": 0.5581, "lr": 5.968095025075114e-05, "epoch": 1.990251827782291, "percentage": 40.26, "elapsed_time": "4:22:38", "remaining_time": "6:29:40"}
154
  {"current_steps": 154, "total_steps": 380, "loss": 0.5411, "lr": 5.936023980395997e-05, "epoch": 2.0048740861088548, "percentage": 40.53, "elapsed_time": "4:26:06", "remaining_time": "6:30:31"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
152
  {"current_steps": 152, "total_steps": 380, "loss": 0.5557, "lr": 6.000000000000001e-05, "epoch": 1.9772542648253453, "percentage": 40.0, "elapsed_time": "4:20:56", "remaining_time": "6:31:25"}
153
  {"current_steps": 153, "total_steps": 380, "loss": 0.5581, "lr": 5.968095025075114e-05, "epoch": 1.990251827782291, "percentage": 40.26, "elapsed_time": "4:22:38", "remaining_time": "6:29:40"}
154
  {"current_steps": 154, "total_steps": 380, "loss": 0.5411, "lr": 5.936023980395997e-05, "epoch": 2.0048740861088548, "percentage": 40.53, "elapsed_time": "4:26:06", "remaining_time": "6:30:31"}
155
+ {"current_steps": 155, "total_steps": 380, "loss": 0.5115, "lr": 5.903789572148295e-05, "epoch": 2.0178716490658, "percentage": 40.79, "elapsed_time": "4:27:47", "remaining_time": "6:28:43"}
156
+ {"current_steps": 156, "total_steps": 380, "loss": 0.5036, "lr": 5.871394520302432e-05, "epoch": 2.0308692120227456, "percentage": 41.05, "elapsed_time": "4:29:28", "remaining_time": "6:26:56"}
157
+ {"current_steps": 157, "total_steps": 380, "loss": 0.5023, "lr": 5.838841558384091e-05, "epoch": 2.0438667749796915, "percentage": 41.32, "elapsed_time": "4:31:11", "remaining_time": "6:25:12"}
158
+ {"current_steps": 158, "total_steps": 380, "loss": 0.5115, "lr": 5.806133433243558e-05, "epoch": 2.056864337936637, "percentage": 41.58, "elapsed_time": "4:32:54", "remaining_time": "6:23:27"}
159
+ {"current_steps": 159, "total_steps": 380, "loss": 0.5059, "lr": 5.7732729048239444e-05, "epoch": 2.0698619008935824, "percentage": 41.84, "elapsed_time": "4:34:35", "remaining_time": "6:21:39"}
160
+ {"current_steps": 160, "total_steps": 380, "loss": 0.5094, "lr": 5.740262745928293e-05, "epoch": 2.0828594638505282, "percentage": 42.11, "elapsed_time": "4:36:17", "remaining_time": "6:19:54"}
161
+ {"current_steps": 161, "total_steps": 380, "loss": 0.5099, "lr": 5.707105741985615e-05, "epoch": 2.0958570268074737, "percentage": 42.37, "elapsed_time": "4:38:01", "remaining_time": "6:18:10"}
162
+ {"current_steps": 162, "total_steps": 380, "loss": 0.5115, "lr": 5.673804690815845e-05, "epoch": 2.108854589764419, "percentage": 42.63, "elapsed_time": "4:39:44", "remaining_time": "6:16:26"}
163
+ {"current_steps": 163, "total_steps": 380, "loss": 0.5031, "lr": 5.6403624023937614e-05, "epoch": 2.121852152721365, "percentage": 42.89, "elapsed_time": "4:41:25", "remaining_time": "6:14:39"}
164
+ {"current_steps": 164, "total_steps": 380, "loss": 0.5021, "lr": 5.606781698611879e-05, "epoch": 2.1348497156783104, "percentage": 43.16, "elapsed_time": "4:43:08", "remaining_time": "6:12:54"}
165
+ {"current_steps": 165, "total_steps": 380, "loss": 0.5053, "lr": 5.573065413042333e-05, "epoch": 2.147847278635256, "percentage": 43.42, "elapsed_time": "4:44:52", "remaining_time": "6:11:12"}
166
+ {"current_steps": 166, "total_steps": 380, "loss": 0.507, "lr": 5.5392163906977835e-05, "epoch": 2.1608448415922012, "percentage": 43.68, "elapsed_time": "4:46:37", "remaining_time": "6:09:30"}
167
+ {"current_steps": 167, "total_steps": 380, "loss": 0.5042, "lr": 5.505237487791343e-05, "epoch": 2.173842404549147, "percentage": 43.95, "elapsed_time": "4:48:20", "remaining_time": "6:07:45"}
168
+ {"current_steps": 168, "total_steps": 380, "loss": 0.5006, "lr": 5.471131571495574e-05, "epoch": 2.1868399675060926, "percentage": 44.21, "elapsed_time": "4:50:04", "remaining_time": "6:06:02"}
169
+ {"current_steps": 169, "total_steps": 380, "loss": 0.5102, "lr": 5.4369015197005506e-05, "epoch": 2.199837530463038, "percentage": 44.47, "elapsed_time": "4:51:49", "remaining_time": "6:04:21"}
170
+ {"current_steps": 170, "total_steps": 380, "loss": 0.5061, "lr": 5.4025502207710184e-05, "epoch": 2.212835093419984, "percentage": 44.74, "elapsed_time": "4:53:31", "remaining_time": "6:02:35"}
171
+ {"current_steps": 171, "total_steps": 380, "loss": 0.5016, "lr": 5.368080573302676e-05, "epoch": 2.2258326563769293, "percentage": 45.0, "elapsed_time": "4:55:13", "remaining_time": "6:00:49"}
172
+ {"current_steps": 172, "total_steps": 380, "loss": 0.5014, "lr": 5.333495485877583e-05, "epoch": 2.2388302193338747, "percentage": 45.26, "elapsed_time": "4:56:55", "remaining_time": "5:59:04"}
173
+ {"current_steps": 173, "total_steps": 380, "loss": 0.501, "lr": 5.298797876818735e-05, "epoch": 2.2518277822908206, "percentage": 45.53, "elapsed_time": "4:58:38", "remaining_time": "5:57:20"}
174
+ {"current_steps": 174, "total_steps": 380, "loss": 0.5022, "lr": 5.263990673943811e-05, "epoch": 2.264825345247766, "percentage": 45.79, "elapsed_time": "5:00:19", "remaining_time": "5:55:32"}
175
+ {"current_steps": 175, "total_steps": 380, "loss": 0.5024, "lr": 5.229076814318122e-05, "epoch": 2.2778229082047114, "percentage": 46.05, "elapsed_time": "5:01:59", "remaining_time": "5:53:45"}
176
+ {"current_steps": 176, "total_steps": 380, "loss": 0.4956, "lr": 5.194059244006779e-05, "epoch": 2.2908204711616573, "percentage": 46.32, "elapsed_time": "5:03:40", "remaining_time": "5:51:59"}
177
+ {"current_steps": 177, "total_steps": 380, "loss": 0.5048, "lr": 5.158940917826099e-05, "epoch": 2.3038180341186028, "percentage": 46.58, "elapsed_time": "5:05:23", "remaining_time": "5:50:15"}
178
+ {"current_steps": 178, "total_steps": 380, "loss": 0.4971, "lr": 5.123724799094279e-05, "epoch": 2.316815597075548, "percentage": 46.84, "elapsed_time": "5:07:03", "remaining_time": "5:48:27"}
179
+ {"current_steps": 179, "total_steps": 380, "loss": 0.4953, "lr": 5.088413859381341e-05, "epoch": 2.329813160032494, "percentage": 47.11, "elapsed_time": "5:08:44", "remaining_time": "5:46:41"}
180
+ {"current_steps": 180, "total_steps": 380, "loss": 0.4988, "lr": 5.053011078258397e-05, "epoch": 2.3428107229894395, "percentage": 47.37, "elapsed_time": "5:10:26", "remaining_time": "5:44:55"}
181
+ {"current_steps": 181, "total_steps": 380, "loss": 0.5062, "lr": 5.017519443046226e-05, "epoch": 2.355808285946385, "percentage": 47.63, "elapsed_time": "5:12:09", "remaining_time": "5:43:12"}
182
+ {"current_steps": 182, "total_steps": 380, "loss": 0.4947, "lr": 4.981941948563197e-05, "epoch": 2.368805848903331, "percentage": 47.89, "elapsed_time": "5:13:51", "remaining_time": "5:41:26"}
183
+ {"current_steps": 183, "total_steps": 380, "loss": 0.4959, "lr": 4.94628159687257e-05, "epoch": 2.381803411860276, "percentage": 48.16, "elapsed_time": "5:15:31", "remaining_time": "5:39:39"}
184
+ {"current_steps": 184, "total_steps": 380, "loss": 0.5004, "lr": 4.9105413970291747e-05, "epoch": 2.3948009748172217, "percentage": 48.42, "elapsed_time": "5:17:12", "remaining_time": "5:37:53"}
185
+ {"current_steps": 185, "total_steps": 380, "loss": 0.5059, "lr": 4.874724364825504e-05, "epoch": 2.4077985377741675, "percentage": 48.68, "elapsed_time": "5:18:53", "remaining_time": "5:36:07"}
186
+ {"current_steps": 186, "total_steps": 380, "loss": 0.5047, "lr": 4.8388335225372416e-05, "epoch": 2.420796100731113, "percentage": 48.95, "elapsed_time": "5:20:33", "remaining_time": "5:34:20"}
187
+ {"current_steps": 187, "total_steps": 380, "loss": 0.5019, "lr": 4.802871898668237e-05, "epoch": 2.4337936636880584, "percentage": 49.21, "elapsed_time": "5:22:14", "remaining_time": "5:32:34"}
188
+ {"current_steps": 188, "total_steps": 380, "loss": 0.5055, "lr": 4.7668425276949546e-05, "epoch": 2.4467912266450043, "percentage": 49.47, "elapsed_time": "5:23:55", "remaining_time": "5:30:49"}
189
+ {"current_steps": 189, "total_steps": 380, "loss": 0.4955, "lr": 4.730748449810429e-05, "epoch": 2.4597887896019497, "percentage": 49.74, "elapsed_time": "5:25:36", "remaining_time": "5:29:03"}
190
+ {"current_steps": 190, "total_steps": 380, "loss": 0.4954, "lr": 4.694592710667723e-05, "epoch": 2.472786352558895, "percentage": 50.0, "elapsed_time": "5:27:16", "remaining_time": "5:27:16"}
191
+ {"current_steps": 191, "total_steps": 380, "loss": 0.4991, "lr": 4.658378361122936e-05, "epoch": 2.4857839155158405, "percentage": 50.26, "elapsed_time": "5:28:57", "remaining_time": "5:25:31"}
192
+ {"current_steps": 192, "total_steps": 380, "loss": 0.5029, "lr": 4.622108456977773e-05, "epoch": 2.4987814784727864, "percentage": 50.53, "elapsed_time": "5:30:40", "remaining_time": "5:23:47"}
193
+ {"current_steps": 193, "total_steps": 380, "loss": 0.4995, "lr": 4.585786058721687e-05, "epoch": 2.511779041429732, "percentage": 50.79, "elapsed_time": "5:32:24", "remaining_time": "5:22:04"}
194
+ {"current_steps": 194, "total_steps": 380, "loss": 0.5026, "lr": 4.549414231273633e-05, "epoch": 2.5247766043866777, "percentage": 51.05, "elapsed_time": "5:34:05", "remaining_time": "5:20:18"}
195
+ {"current_steps": 195, "total_steps": 380, "loss": 0.5016, "lr": 4.512996043723453e-05, "epoch": 2.537774167343623, "percentage": 51.32, "elapsed_time": "5:35:48", "remaining_time": "5:18:34"}
196
+ {"current_steps": 196, "total_steps": 380, "loss": 0.5015, "lr": 4.476534569072895e-05, "epoch": 2.5507717303005686, "percentage": 51.58, "elapsed_time": "5:37:32", "remaining_time": "5:16:52"}
197
+ {"current_steps": 197, "total_steps": 380, "loss": 0.4987, "lr": 4.440032883976318e-05, "epoch": 2.563769293257514, "percentage": 51.84, "elapsed_time": "5:39:15", "remaining_time": "5:15:08"}
198
+ {"current_steps": 198, "total_steps": 380, "loss": 0.497, "lr": 4.403494068481074e-05, "epoch": 2.57676685621446, "percentage": 52.11, "elapsed_time": "5:40:56", "remaining_time": "5:13:23"}
199
+ {"current_steps": 199, "total_steps": 380, "loss": 0.5039, "lr": 4.3669212057676145e-05, "epoch": 2.5897644191714053, "percentage": 52.37, "elapsed_time": "5:42:37", "remaining_time": "5:11:38"}
200
+ {"current_steps": 200, "total_steps": 380, "loss": 0.494, "lr": 4.33031738188933e-05, "epoch": 2.602761982128351, "percentage": 52.63, "elapsed_time": "5:44:19", "remaining_time": "5:09:53"}
201
+ {"current_steps": 201, "total_steps": 380, "loss": 0.4983, "lr": 4.293685685512142e-05, "epoch": 2.6157595450852966, "percentage": 52.89, "elapsed_time": "5:46:01", "remaining_time": "5:08:08"}
202
+ {"current_steps": 202, "total_steps": 380, "loss": 0.4973, "lr": 4.257029207653881e-05, "epoch": 2.628757108042242, "percentage": 53.16, "elapsed_time": "5:47:41", "remaining_time": "5:06:22"}
203
+ {"current_steps": 203, "total_steps": 380, "loss": 0.4965, "lr": 4.220351041423462e-05, "epoch": 2.6417546709991875, "percentage": 53.42, "elapsed_time": "5:49:22", "remaining_time": "5:04:37"}
204
+ {"current_steps": 204, "total_steps": 380, "loss": 0.5064, "lr": 4.183654281759888e-05, "epoch": 2.6547522339561334, "percentage": 53.68, "elapsed_time": "5:51:06", "remaining_time": "5:02:54"}
205
+ {"current_steps": 205, "total_steps": 380, "loss": 0.5006, "lr": 4.1469420251710905e-05, "epoch": 2.667749796913079, "percentage": 53.95, "elapsed_time": "5:52:48", "remaining_time": "5:01:10"}
206
+ {"current_steps": 206, "total_steps": 380, "loss": 0.505, "lr": 4.110217369472649e-05, "epoch": 2.680747359870024, "percentage": 54.21, "elapsed_time": "5:54:29", "remaining_time": "4:59:25"}
207
+ {"current_steps": 207, "total_steps": 380, "loss": 0.4931, "lr": 4.07348341352639e-05, "epoch": 2.69374492282697, "percentage": 54.47, "elapsed_time": "5:56:11", "remaining_time": "4:57:41"}
208
+ {"current_steps": 208, "total_steps": 380, "loss": 0.4932, "lr": 4.0367432569789065e-05, "epoch": 2.7067424857839155, "percentage": 54.74, "elapsed_time": "5:57:54", "remaining_time": "4:55:57"}
209
+ {"current_steps": 209, "total_steps": 380, "loss": 0.4903, "lr": 4e-05, "epoch": 2.719740048740861, "percentage": 55.0, "elapsed_time": "5:59:34", "remaining_time": "4:54:12"}
210
+ {"current_steps": 210, "total_steps": 380, "loss": 0.4938, "lr": 3.963256743021095e-05, "epoch": 2.732737611697807, "percentage": 55.26, "elapsed_time": "6:01:15", "remaining_time": "4:52:27"}
211
+ {"current_steps": 211, "total_steps": 380, "loss": 0.4932, "lr": 3.92651658647361e-05, "epoch": 2.7457351746547523, "percentage": 55.53, "elapsed_time": "6:02:58", "remaining_time": "4:50:43"}
212
+ {"current_steps": 212, "total_steps": 380, "loss": 0.501, "lr": 3.889782630527353e-05, "epoch": 2.7587327376116977, "percentage": 55.79, "elapsed_time": "6:04:42", "remaining_time": "4:49:00"}
213
+ {"current_steps": 213, "total_steps": 380, "loss": 0.5028, "lr": 3.853057974828911e-05, "epoch": 2.7717303005686436, "percentage": 56.05, "elapsed_time": "6:06:23", "remaining_time": "4:47:16"}
214
+ {"current_steps": 214, "total_steps": 380, "loss": 0.4966, "lr": 3.816345718240113e-05, "epoch": 2.784727863525589, "percentage": 56.32, "elapsed_time": "6:08:05", "remaining_time": "4:45:31"}
215
+ {"current_steps": 215, "total_steps": 380, "loss": 0.4971, "lr": 3.779648958576538e-05, "epoch": 2.7977254264825344, "percentage": 56.58, "elapsed_time": "6:09:47", "remaining_time": "4:43:47"}
216
+ {"current_steps": 216, "total_steps": 380, "loss": 0.5, "lr": 3.74297079234612e-05, "epoch": 2.81072298943948, "percentage": 56.84, "elapsed_time": "6:11:30", "remaining_time": "4:42:04"}
217
+ {"current_steps": 217, "total_steps": 380, "loss": 0.5029, "lr": 3.706314314487859e-05, "epoch": 2.8237205523964257, "percentage": 57.11, "elapsed_time": "6:13:11", "remaining_time": "4:40:19"}
218
+ {"current_steps": 218, "total_steps": 380, "loss": 0.4963, "lr": 3.669682618110671e-05, "epoch": 2.836718115353371, "percentage": 57.37, "elapsed_time": "6:14:52", "remaining_time": "4:38:34"}
219
+ {"current_steps": 219, "total_steps": 380, "loss": 0.4975, "lr": 3.6330787942323855e-05, "epoch": 2.849715678310317, "percentage": 57.63, "elapsed_time": "6:16:35", "remaining_time": "4:36:51"}
220
+ {"current_steps": 220, "total_steps": 380, "loss": 0.5001, "lr": 3.5965059315189274e-05, "epoch": 2.8627132412672625, "percentage": 57.89, "elapsed_time": "6:18:19", "remaining_time": "4:35:08"}
221
+ {"current_steps": 221, "total_steps": 380, "loss": 0.5015, "lr": 3.559967116023683e-05, "epoch": 2.875710804224208, "percentage": 58.16, "elapsed_time": "6:20:01", "remaining_time": "4:33:24"}
222
+ {"current_steps": 222, "total_steps": 380, "loss": 0.4978, "lr": 3.523465430927106e-05, "epoch": 2.8887083671811533, "percentage": 58.42, "elapsed_time": "6:21:44", "remaining_time": "4:31:41"}
223
+ {"current_steps": 223, "total_steps": 380, "loss": 0.4974, "lr": 3.4870039562765475e-05, "epoch": 2.901705930138099, "percentage": 58.68, "elapsed_time": "6:23:27", "remaining_time": "4:29:58"}
224
+ {"current_steps": 224, "total_steps": 380, "loss": 0.4921, "lr": 3.4505857687263675e-05, "epoch": 2.9147034930950446, "percentage": 58.95, "elapsed_time": "6:25:12", "remaining_time": "4:28:16"}
225
+ {"current_steps": 225, "total_steps": 380, "loss": 0.5012, "lr": 3.414213941278314e-05, "epoch": 2.9277010560519905, "percentage": 59.21, "elapsed_time": "6:26:54", "remaining_time": "4:26:32"}
226
+ {"current_steps": 226, "total_steps": 380, "loss": 0.4967, "lr": 3.377891543022229e-05, "epoch": 2.940698619008936, "percentage": 59.47, "elapsed_time": "6:28:37", "remaining_time": "4:24:49"}
227
+ {"current_steps": 227, "total_steps": 380, "loss": 0.5026, "lr": 3.341621638877064e-05, "epoch": 2.9536961819658814, "percentage": 59.74, "elapsed_time": "6:30:21", "remaining_time": "4:23:06"}
228
+ {"current_steps": 228, "total_steps": 380, "loss": 0.4944, "lr": 3.305407289332279e-05, "epoch": 2.966693744922827, "percentage": 60.0, "elapsed_time": "6:32:04", "remaining_time": "4:21:23"}
229
+ {"current_steps": 229, "total_steps": 380, "loss": 0.4954, "lr": 3.269251550189573e-05, "epoch": 2.9796913078797727, "percentage": 60.26, "elapsed_time": "6:33:45", "remaining_time": "4:19:38"}
230
+ {"current_steps": 230, "total_steps": 380, "loss": 0.5042, "lr": 3.2331574723050474e-05, "epoch": 2.992688870836718, "percentage": 60.53, "elapsed_time": "6:35:25", "remaining_time": "4:17:53"}
231
+ {"current_steps": 231, "total_steps": 380, "loss": 0.4791, "lr": 3.197128101331764e-05, "epoch": 3.007311129163282, "percentage": 60.79, "elapsed_time": "6:38:56", "remaining_time": "4:17:19"}