sedrickkeh commited on
Commit
d24cc26
·
verified ·
1 Parent(s): f36cb2c

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 sha256:305fb7cdd5cd6972716e748371d7b24c5d4fe0bc1f56ae33757c35250d6f523d
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f276426e234f109273a38a7bbc3a4c7b084aac63b281cea852d6711d82a2a2b3
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b9ebbb34052296046a3b49311bb1c4941423b209bfec2d10f9a82e4a852264e
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef2ac7487c3992578135896887e63879d5dc7a87d978c4d36ee74324c09adca0
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dbcdd9febc81b421a60165e0e873bd43ae07b1f7e9d82456c2ab198018d824c3
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:217057e0fa3bffeaa7b41469e1593bd0ea6f79d8189a36cfca0d14e7f1e5734d
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aad7527e4ee1e5477f241618b65846165b23caaf1a68566da209deb1a67262f5
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe526776320e76c869455d8b6e95f881f1a212caff2e5f388bf2df035545e484
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -199,3 +199,104 @@
199
  {"current_steps": 1980, "total_steps": 3984, "loss": 0.6886, "lr": 5e-06, "epoch": 1.9872036130974784, "percentage": 49.7, "elapsed_time": "17:44:50", "remaining_time": "17:57:44"}
200
  {"current_steps": 1990, "total_steps": 3984, "loss": 0.6923, "lr": 5e-06, "epoch": 1.997239994981809, "percentage": 49.95, "elapsed_time": "17:50:07", "remaining_time": "17:52:16"}
201
  {"current_steps": 1992, "total_steps": 3984, "eval_loss": 0.7167317867279053, "epoch": 1.999247271358675, "percentage": 50.0, "elapsed_time": "18:02:52", "remaining_time": "18:02:52"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
199
  {"current_steps": 1980, "total_steps": 3984, "loss": 0.6886, "lr": 5e-06, "epoch": 1.9872036130974784, "percentage": 49.7, "elapsed_time": "17:44:50", "remaining_time": "17:57:44"}
200
  {"current_steps": 1990, "total_steps": 3984, "loss": 0.6923, "lr": 5e-06, "epoch": 1.997239994981809, "percentage": 49.95, "elapsed_time": "17:50:07", "remaining_time": "17:52:16"}
201
  {"current_steps": 1992, "total_steps": 3984, "eval_loss": 0.7167317867279053, "epoch": 1.999247271358675, "percentage": 50.0, "elapsed_time": "18:02:52", "remaining_time": "18:02:52"}
202
+ {"current_steps": 2000, "total_steps": 3984, "loss": 0.7021, "lr": 5e-06, "epoch": 2.0072763768661397, "percentage": 50.2, "elapsed_time": "18:08:11", "remaining_time": "17:59:29"}
203
+ {"current_steps": 2010, "total_steps": 3984, "loss": 0.6464, "lr": 5e-06, "epoch": 2.0173127587504704, "percentage": 50.45, "elapsed_time": "18:13:30", "remaining_time": "17:53:55"}
204
+ {"current_steps": 2020, "total_steps": 3984, "loss": 0.6468, "lr": 5e-06, "epoch": 2.027349140634801, "percentage": 50.7, "elapsed_time": "18:18:48", "remaining_time": "17:48:21"}
205
+ {"current_steps": 2030, "total_steps": 3984, "loss": 0.6466, "lr": 5e-06, "epoch": 2.037385522519132, "percentage": 50.95, "elapsed_time": "18:24:08", "remaining_time": "17:42:48"}
206
+ {"current_steps": 2040, "total_steps": 3984, "loss": 0.645, "lr": 5e-06, "epoch": 2.0474219044034627, "percentage": 51.2, "elapsed_time": "18:29:28", "remaining_time": "17:37:15"}
207
+ {"current_steps": 2050, "total_steps": 3984, "loss": 0.6484, "lr": 5e-06, "epoch": 2.057458286287793, "percentage": 51.46, "elapsed_time": "18:34:47", "remaining_time": "17:31:42"}
208
+ {"current_steps": 2060, "total_steps": 3984, "loss": 0.6479, "lr": 5e-06, "epoch": 2.067494668172124, "percentage": 51.71, "elapsed_time": "18:40:08", "remaining_time": "17:26:10"}
209
+ {"current_steps": 2070, "total_steps": 3984, "loss": 0.646, "lr": 5e-06, "epoch": 2.0775310500564546, "percentage": 51.96, "elapsed_time": "18:45:26", "remaining_time": "17:20:37"}
210
+ {"current_steps": 2080, "total_steps": 3984, "loss": 0.6492, "lr": 5e-06, "epoch": 2.0875674319407853, "percentage": 52.21, "elapsed_time": "18:50:44", "remaining_time": "17:15:03"}
211
+ {"current_steps": 2090, "total_steps": 3984, "loss": 0.6538, "lr": 5e-06, "epoch": 2.097603813825116, "percentage": 52.46, "elapsed_time": "18:56:05", "remaining_time": "17:09:32"}
212
+ {"current_steps": 2100, "total_steps": 3984, "loss": 0.6468, "lr": 5e-06, "epoch": 2.107640195709447, "percentage": 52.71, "elapsed_time": "19:01:25", "remaining_time": "17:04:01"}
213
+ {"current_steps": 2110, "total_steps": 3984, "loss": 0.6468, "lr": 5e-06, "epoch": 2.1176765775937776, "percentage": 52.96, "elapsed_time": "19:06:46", "remaining_time": "16:58:30"}
214
+ {"current_steps": 2120, "total_steps": 3984, "loss": 0.645, "lr": 5e-06, "epoch": 2.1277129594781083, "percentage": 53.21, "elapsed_time": "19:12:04", "remaining_time": "16:52:57"}
215
+ {"current_steps": 2130, "total_steps": 3984, "loss": 0.6495, "lr": 5e-06, "epoch": 2.1377493413624387, "percentage": 53.46, "elapsed_time": "19:17:23", "remaining_time": "16:47:25"}
216
+ {"current_steps": 2140, "total_steps": 3984, "loss": 0.6494, "lr": 5e-06, "epoch": 2.1477857232467694, "percentage": 53.71, "elapsed_time": "19:22:41", "remaining_time": "16:41:51"}
217
+ {"current_steps": 2150, "total_steps": 3984, "loss": 0.6502, "lr": 5e-06, "epoch": 2.1578221051311, "percentage": 53.97, "elapsed_time": "19:28:01", "remaining_time": "16:36:21"}
218
+ {"current_steps": 2160, "total_steps": 3984, "loss": 0.6469, "lr": 5e-06, "epoch": 2.167858487015431, "percentage": 54.22, "elapsed_time": "19:33:22", "remaining_time": "16:30:51"}
219
+ {"current_steps": 2170, "total_steps": 3984, "loss": 0.6445, "lr": 5e-06, "epoch": 2.1778948688997617, "percentage": 54.47, "elapsed_time": "19:38:43", "remaining_time": "16:25:20"}
220
+ {"current_steps": 2180, "total_steps": 3984, "loss": 0.6506, "lr": 5e-06, "epoch": 2.1879312507840925, "percentage": 54.72, "elapsed_time": "19:44:03", "remaining_time": "16:19:50"}
221
+ {"current_steps": 2190, "total_steps": 3984, "loss": 0.6527, "lr": 5e-06, "epoch": 2.197967632668423, "percentage": 54.97, "elapsed_time": "19:49:21", "remaining_time": "16:14:17"}
222
+ {"current_steps": 2200, "total_steps": 3984, "loss": 0.6493, "lr": 5e-06, "epoch": 2.2080040145527535, "percentage": 55.22, "elapsed_time": "19:54:39", "remaining_time": "16:08:45"}
223
+ {"current_steps": 2210, "total_steps": 3984, "loss": 0.6537, "lr": 5e-06, "epoch": 2.2180403964370843, "percentage": 55.47, "elapsed_time": "19:59:59", "remaining_time": "16:03:14"}
224
+ {"current_steps": 2220, "total_steps": 3984, "loss": 0.6491, "lr": 5e-06, "epoch": 2.228076778321415, "percentage": 55.72, "elapsed_time": "20:05:16", "remaining_time": "15:57:42"}
225
+ {"current_steps": 2230, "total_steps": 3984, "loss": 0.6497, "lr": 5e-06, "epoch": 2.238113160205746, "percentage": 55.97, "elapsed_time": "20:10:34", "remaining_time": "15:52:10"}
226
+ {"current_steps": 2240, "total_steps": 3984, "loss": 0.6479, "lr": 5e-06, "epoch": 2.2481495420900766, "percentage": 56.22, "elapsed_time": "20:15:52", "remaining_time": "15:46:38"}
227
+ {"current_steps": 2250, "total_steps": 3984, "loss": 0.6481, "lr": 5e-06, "epoch": 2.2581859239744073, "percentage": 56.48, "elapsed_time": "20:21:10", "remaining_time": "15:41:07"}
228
+ {"current_steps": 2260, "total_steps": 3984, "loss": 0.6496, "lr": 5e-06, "epoch": 2.268222305858738, "percentage": 56.73, "elapsed_time": "20:26:31", "remaining_time": "15:35:37"}
229
+ {"current_steps": 2270, "total_steps": 3984, "loss": 0.6495, "lr": 5e-06, "epoch": 2.278258687743069, "percentage": 56.98, "elapsed_time": "20:31:52", "remaining_time": "15:30:09"}
230
+ {"current_steps": 2280, "total_steps": 3984, "loss": 0.6488, "lr": 5e-06, "epoch": 2.288295069627399, "percentage": 57.23, "elapsed_time": "20:37:13", "remaining_time": "15:24:39"}
231
+ {"current_steps": 2290, "total_steps": 3984, "loss": 0.6463, "lr": 5e-06, "epoch": 2.29833145151173, "percentage": 57.48, "elapsed_time": "20:42:32", "remaining_time": "15:19:09"}
232
+ {"current_steps": 2300, "total_steps": 3984, "loss": 0.6512, "lr": 5e-06, "epoch": 2.3083678333960607, "percentage": 57.73, "elapsed_time": "20:47:53", "remaining_time": "15:13:40"}
233
+ {"current_steps": 2310, "total_steps": 3984, "loss": 0.6531, "lr": 5e-06, "epoch": 2.3184042152803914, "percentage": 57.98, "elapsed_time": "20:53:11", "remaining_time": "15:08:09"}
234
+ {"current_steps": 2320, "total_steps": 3984, "loss": 0.651, "lr": 5e-06, "epoch": 2.328440597164722, "percentage": 58.23, "elapsed_time": "20:58:32", "remaining_time": "15:02:40"}
235
+ {"current_steps": 2330, "total_steps": 3984, "loss": 0.6496, "lr": 5e-06, "epoch": 2.338476979049053, "percentage": 58.48, "elapsed_time": "21:03:53", "remaining_time": "14:57:11"}
236
+ {"current_steps": 2340, "total_steps": 3984, "loss": 0.6478, "lr": 5e-06, "epoch": 2.3485133609333837, "percentage": 58.73, "elapsed_time": "21:09:13", "remaining_time": "14:51:42"}
237
+ {"current_steps": 2350, "total_steps": 3984, "loss": 0.6474, "lr": 5e-06, "epoch": 2.358549742817714, "percentage": 58.99, "elapsed_time": "21:14:34", "remaining_time": "14:46:14"}
238
+ {"current_steps": 2360, "total_steps": 3984, "loss": 0.6513, "lr": 5e-06, "epoch": 2.3685861247020448, "percentage": 59.24, "elapsed_time": "21:19:54", "remaining_time": "14:40:45"}
239
+ {"current_steps": 2370, "total_steps": 3984, "loss": 0.6549, "lr": 5e-06, "epoch": 2.3786225065863755, "percentage": 59.49, "elapsed_time": "21:25:11", "remaining_time": "14:35:14"}
240
+ {"current_steps": 2380, "total_steps": 3984, "loss": 0.6517, "lr": 5e-06, "epoch": 2.3886588884707063, "percentage": 59.74, "elapsed_time": "21:30:29", "remaining_time": "14:29:43"}
241
+ {"current_steps": 2390, "total_steps": 3984, "loss": 0.6479, "lr": 5e-06, "epoch": 2.398695270355037, "percentage": 59.99, "elapsed_time": "21:35:50", "remaining_time": "14:24:15"}
242
+ {"current_steps": 2400, "total_steps": 3984, "loss": 0.6497, "lr": 5e-06, "epoch": 2.408731652239368, "percentage": 60.24, "elapsed_time": "21:41:10", "remaining_time": "14:18:46"}
243
+ {"current_steps": 2410, "total_steps": 3984, "loss": 0.6523, "lr": 5e-06, "epoch": 2.4187680341236986, "percentage": 60.49, "elapsed_time": "21:46:31", "remaining_time": "14:13:18"}
244
+ {"current_steps": 2420, "total_steps": 3984, "loss": 0.653, "lr": 5e-06, "epoch": 2.4288044160080293, "percentage": 60.74, "elapsed_time": "21:51:52", "remaining_time": "14:07:50"}
245
+ {"current_steps": 2430, "total_steps": 3984, "loss": 0.6482, "lr": 5e-06, "epoch": 2.4388407978923596, "percentage": 60.99, "elapsed_time": "21:57:11", "remaining_time": "14:02:21"}
246
+ {"current_steps": 2440, "total_steps": 3984, "loss": 0.656, "lr": 5e-06, "epoch": 2.4488771797766904, "percentage": 61.24, "elapsed_time": "22:02:27", "remaining_time": "13:56:50"}
247
+ {"current_steps": 2450, "total_steps": 3984, "loss": 0.6501, "lr": 5e-06, "epoch": 2.458913561661021, "percentage": 61.5, "elapsed_time": "22:07:45", "remaining_time": "13:51:20"}
248
+ {"current_steps": 2460, "total_steps": 3984, "loss": 0.6526, "lr": 5e-06, "epoch": 2.468949943545352, "percentage": 61.75, "elapsed_time": "22:13:05", "remaining_time": "13:45:51"}
249
+ {"current_steps": 2470, "total_steps": 3984, "loss": 0.6579, "lr": 5e-06, "epoch": 2.4789863254296827, "percentage": 62.0, "elapsed_time": "22:18:23", "remaining_time": "13:40:22"}
250
+ {"current_steps": 2480, "total_steps": 3984, "loss": 0.6473, "lr": 5e-06, "epoch": 2.4890227073140134, "percentage": 62.25, "elapsed_time": "22:23:40", "remaining_time": "13:34:52"}
251
+ {"current_steps": 2490, "total_steps": 3984, "loss": 0.6511, "lr": 5e-06, "epoch": 2.499059089198344, "percentage": 62.5, "elapsed_time": "22:28:57", "remaining_time": "13:29:22"}
252
+ {"current_steps": 2500, "total_steps": 3984, "loss": 0.6577, "lr": 5e-06, "epoch": 2.5090954710826745, "percentage": 62.75, "elapsed_time": "22:34:12", "remaining_time": "13:23:51"}
253
+ {"current_steps": 2510, "total_steps": 3984, "loss": 0.6536, "lr": 5e-06, "epoch": 2.5191318529670053, "percentage": 63.0, "elapsed_time": "22:39:30", "remaining_time": "13:18:22"}
254
+ {"current_steps": 2520, "total_steps": 3984, "loss": 0.6489, "lr": 5e-06, "epoch": 2.529168234851336, "percentage": 63.25, "elapsed_time": "22:44:47", "remaining_time": "13:12:52"}
255
+ {"current_steps": 2530, "total_steps": 3984, "loss": 0.6495, "lr": 5e-06, "epoch": 2.5392046167356668, "percentage": 63.5, "elapsed_time": "22:50:04", "remaining_time": "13:07:23"}
256
+ {"current_steps": 2540, "total_steps": 3984, "loss": 0.651, "lr": 5e-06, "epoch": 2.5492409986199975, "percentage": 63.76, "elapsed_time": "22:55:25", "remaining_time": "13:01:55"}
257
+ {"current_steps": 2550, "total_steps": 3984, "loss": 0.6541, "lr": 5e-06, "epoch": 2.5592773805043283, "percentage": 64.01, "elapsed_time": "23:00:44", "remaining_time": "12:56:27"}
258
+ {"current_steps": 2560, "total_steps": 3984, "loss": 0.6507, "lr": 5e-06, "epoch": 2.569313762388659, "percentage": 64.26, "elapsed_time": "23:06:04", "remaining_time": "12:51:00"}
259
+ {"current_steps": 2570, "total_steps": 3984, "loss": 0.6499, "lr": 5e-06, "epoch": 2.57935014427299, "percentage": 64.51, "elapsed_time": "23:11:24", "remaining_time": "12:45:32"}
260
+ {"current_steps": 2580, "total_steps": 3984, "loss": 0.6616, "lr": 5e-06, "epoch": 2.58938652615732, "percentage": 64.76, "elapsed_time": "23:16:45", "remaining_time": "12:40:05"}
261
+ {"current_steps": 2590, "total_steps": 3984, "loss": 0.6486, "lr": 5e-06, "epoch": 2.599422908041651, "percentage": 65.01, "elapsed_time": "23:22:05", "remaining_time": "12:34:38"}
262
+ {"current_steps": 2600, "total_steps": 3984, "loss": 0.6544, "lr": 5e-06, "epoch": 2.6094592899259816, "percentage": 65.26, "elapsed_time": "23:27:26", "remaining_time": "12:29:11"}
263
+ {"current_steps": 2610, "total_steps": 3984, "loss": 0.6539, "lr": 5e-06, "epoch": 2.6194956718103124, "percentage": 65.51, "elapsed_time": "23:32:46", "remaining_time": "12:23:44"}
264
+ {"current_steps": 2620, "total_steps": 3984, "loss": 0.6475, "lr": 5e-06, "epoch": 2.629532053694643, "percentage": 65.76, "elapsed_time": "23:38:06", "remaining_time": "12:18:17"}
265
+ {"current_steps": 2630, "total_steps": 3984, "loss": 0.6501, "lr": 5e-06, "epoch": 2.639568435578974, "percentage": 66.01, "elapsed_time": "23:43:26", "remaining_time": "12:12:49"}
266
+ {"current_steps": 2640, "total_steps": 3984, "loss": 0.6533, "lr": 5e-06, "epoch": 2.6496048174633042, "percentage": 66.27, "elapsed_time": "23:48:46", "remaining_time": "12:07:22"}
267
+ {"current_steps": 2650, "total_steps": 3984, "loss": 0.6539, "lr": 5e-06, "epoch": 2.659641199347635, "percentage": 66.52, "elapsed_time": "23:54:07", "remaining_time": "12:01:55"}
268
+ {"current_steps": 2660, "total_steps": 3984, "loss": 0.6485, "lr": 5e-06, "epoch": 2.6696775812319657, "percentage": 66.77, "elapsed_time": "23:59:28", "remaining_time": "11:56:29"}
269
+ {"current_steps": 2670, "total_steps": 3984, "loss": 0.6522, "lr": 5e-06, "epoch": 2.6797139631162965, "percentage": 67.02, "elapsed_time": "1 day, 0:04:47", "remaining_time": "11:51:02"}
270
+ {"current_steps": 2680, "total_steps": 3984, "loss": 0.6513, "lr": 5e-06, "epoch": 2.6897503450006273, "percentage": 67.27, "elapsed_time": "1 day, 0:10:08", "remaining_time": "11:45:35"}
271
+ {"current_steps": 2690, "total_steps": 3984, "loss": 0.6507, "lr": 5e-06, "epoch": 2.699786726884958, "percentage": 67.52, "elapsed_time": "1 day, 0:15:28", "remaining_time": "11:40:08"}
272
+ {"current_steps": 2700, "total_steps": 3984, "loss": 0.6532, "lr": 5e-06, "epoch": 2.709823108769289, "percentage": 67.77, "elapsed_time": "1 day, 0:20:49", "remaining_time": "11:34:42"}
273
+ {"current_steps": 2710, "total_steps": 3984, "loss": 0.652, "lr": 5e-06, "epoch": 2.7198594906536195, "percentage": 68.02, "elapsed_time": "1 day, 0:26:09", "remaining_time": "11:29:15"}
274
+ {"current_steps": 2720, "total_steps": 3984, "loss": 0.6529, "lr": 5e-06, "epoch": 2.7298958725379503, "percentage": 68.27, "elapsed_time": "1 day, 0:31:29", "remaining_time": "11:23:48"}
275
+ {"current_steps": 2730, "total_steps": 3984, "loss": 0.6551, "lr": 5e-06, "epoch": 2.7399322544222806, "percentage": 68.52, "elapsed_time": "1 day, 0:36:49", "remaining_time": "11:18:21"}
276
+ {"current_steps": 2740, "total_steps": 3984, "loss": 0.6559, "lr": 5e-06, "epoch": 2.7499686363066114, "percentage": 68.78, "elapsed_time": "1 day, 0:42:08", "remaining_time": "11:12:54"}
277
+ {"current_steps": 2750, "total_steps": 3984, "loss": 0.6536, "lr": 5e-06, "epoch": 2.760005018190942, "percentage": 69.03, "elapsed_time": "1 day, 0:47:28", "remaining_time": "11:07:28"}
278
+ {"current_steps": 2760, "total_steps": 3984, "loss": 0.6607, "lr": 5e-06, "epoch": 2.770041400075273, "percentage": 69.28, "elapsed_time": "1 day, 0:52:49", "remaining_time": "11:02:02"}
279
+ {"current_steps": 2770, "total_steps": 3984, "loss": 0.6532, "lr": 5e-06, "epoch": 2.7800777819596036, "percentage": 69.53, "elapsed_time": "1 day, 0:58:08", "remaining_time": "10:56:35"}
280
+ {"current_steps": 2780, "total_steps": 3984, "loss": 0.6516, "lr": 5e-06, "epoch": 2.7901141638439344, "percentage": 69.78, "elapsed_time": "1 day, 1:03:28", "remaining_time": "10:51:08"}
281
+ {"current_steps": 2790, "total_steps": 3984, "loss": 0.6552, "lr": 5e-06, "epoch": 2.8001505457282647, "percentage": 70.03, "elapsed_time": "1 day, 1:08:47", "remaining_time": "10:45:42"}
282
+ {"current_steps": 2800, "total_steps": 3984, "loss": 0.6556, "lr": 5e-06, "epoch": 2.8101869276125955, "percentage": 70.28, "elapsed_time": "1 day, 1:14:04", "remaining_time": "10:40:14"}
283
+ {"current_steps": 2810, "total_steps": 3984, "loss": 0.6549, "lr": 5e-06, "epoch": 2.8202233094969262, "percentage": 70.53, "elapsed_time": "1 day, 1:19:23", "remaining_time": "10:34:47"}
284
+ {"current_steps": 2820, "total_steps": 3984, "loss": 0.6507, "lr": 5e-06, "epoch": 2.830259691381257, "percentage": 70.78, "elapsed_time": "1 day, 1:24:42", "remaining_time": "10:29:21"}
285
+ {"current_steps": 2830, "total_steps": 3984, "loss": 0.6526, "lr": 5e-06, "epoch": 2.8402960732655878, "percentage": 71.03, "elapsed_time": "1 day, 1:30:02", "remaining_time": "10:23:54"}
286
+ {"current_steps": 2840, "total_steps": 3984, "loss": 0.6519, "lr": 5e-06, "epoch": 2.8503324551499185, "percentage": 71.29, "elapsed_time": "1 day, 1:35:22", "remaining_time": "10:18:28"}
287
+ {"current_steps": 2850, "total_steps": 3984, "loss": 0.6593, "lr": 5e-06, "epoch": 2.8603688370342493, "percentage": 71.54, "elapsed_time": "1 day, 1:40:42", "remaining_time": "10:13:02"}
288
+ {"current_steps": 2860, "total_steps": 3984, "loss": 0.6526, "lr": 5e-06, "epoch": 2.87040521891858, "percentage": 71.79, "elapsed_time": "1 day, 1:46:02", "remaining_time": "10:07:36"}
289
+ {"current_steps": 2870, "total_steps": 3984, "loss": 0.6521, "lr": 5e-06, "epoch": 2.880441600802911, "percentage": 72.04, "elapsed_time": "1 day, 1:51:20", "remaining_time": "10:02:09"}
290
+ {"current_steps": 2880, "total_steps": 3984, "loss": 0.655, "lr": 5e-06, "epoch": 2.890477982687241, "percentage": 72.29, "elapsed_time": "1 day, 1:56:36", "remaining_time": "9:56:41"}
291
+ {"current_steps": 2890, "total_steps": 3984, "loss": 0.6523, "lr": 5e-06, "epoch": 2.900514364571572, "percentage": 72.54, "elapsed_time": "1 day, 2:01:53", "remaining_time": "9:51:14"}
292
+ {"current_steps": 2900, "total_steps": 3984, "loss": 0.6549, "lr": 5e-06, "epoch": 2.9105507464559026, "percentage": 72.79, "elapsed_time": "1 day, 2:07:13", "remaining_time": "9:45:49"}
293
+ {"current_steps": 2910, "total_steps": 3984, "loss": 0.6516, "lr": 5e-06, "epoch": 2.9205871283402334, "percentage": 73.04, "elapsed_time": "1 day, 2:12:34", "remaining_time": "9:40:23"}
294
+ {"current_steps": 2920, "total_steps": 3984, "loss": 0.6505, "lr": 5e-06, "epoch": 2.930623510224564, "percentage": 73.29, "elapsed_time": "1 day, 2:17:55", "remaining_time": "9:34:58"}
295
+ {"current_steps": 2930, "total_steps": 3984, "loss": 0.6523, "lr": 5e-06, "epoch": 2.940659892108895, "percentage": 73.54, "elapsed_time": "1 day, 2:23:14", "remaining_time": "9:29:32"}
296
+ {"current_steps": 2940, "total_steps": 3984, "loss": 0.6562, "lr": 5e-06, "epoch": 2.950696273993225, "percentage": 73.8, "elapsed_time": "1 day, 2:28:34", "remaining_time": "9:24:06"}
297
+ {"current_steps": 2950, "total_steps": 3984, "loss": 0.6542, "lr": 5e-06, "epoch": 2.960732655877556, "percentage": 74.05, "elapsed_time": "1 day, 2:33:52", "remaining_time": "9:18:39"}
298
+ {"current_steps": 2960, "total_steps": 3984, "loss": 0.6561, "lr": 5e-06, "epoch": 2.9707690377618867, "percentage": 74.3, "elapsed_time": "1 day, 2:39:11", "remaining_time": "9:13:14"}
299
+ {"current_steps": 2970, "total_steps": 3984, "loss": 0.6563, "lr": 5e-06, "epoch": 2.9808054196462175, "percentage": 74.55, "elapsed_time": "1 day, 2:44:32", "remaining_time": "9:07:48"}
300
+ {"current_steps": 2980, "total_steps": 3984, "loss": 0.6521, "lr": 5e-06, "epoch": 2.9908418015305482, "percentage": 74.8, "elapsed_time": "1 day, 2:49:51", "remaining_time": "9:02:23"}
301
+ {"current_steps": 2989, "total_steps": 3984, "eval_loss": 0.7146658897399902, "epoch": 2.999874545226446, "percentage": 75.03, "elapsed_time": "1 day, 3:05:49", "remaining_time": "9:01:12"}
302
+ {"current_steps": 2990, "total_steps": 3984, "loss": 0.6898, "lr": 5e-06, "epoch": 3.000878183414879, "percentage": 75.05, "elapsed_time": "1 day, 3:07:48", "remaining_time": "9:01:09"}