sumuks commited on
Commit
76adb42
·
verified ·
1 Parent(s): 652770b

Training in progress, step 2500

Browse files
Files changed (2) hide show
  1. adapter_model.safetensors +1 -1
  2. trainer_log.jsonl +51 -0
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:543c520542a943774206477e40e5b855dec5eddf08a4786441bc3db1a89f74be
3
  size 645976488
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:738c11ae15cbe09018a302072053a4b73f48ad0fee03df5745c3d09cd5cd70ac
3
  size 645976488
trainer_log.jsonl CHANGED
@@ -201,3 +201,54 @@
201
  {"current_steps": 1980, "total_steps": 3573, "loss": 1.2346, "lr": 2.4645788730188595e-05, "epoch": 1.6624685138539044, "percentage": 55.42, "elapsed_time": "0:43:35", "remaining_time": "0:35:04"}
202
  {"current_steps": 1990, "total_steps": 3573, "loss": 1.2266, "lr": 2.4401542241602936e-05, "epoch": 1.670864819479429, "percentage": 55.7, "elapsed_time": "0:43:47", "remaining_time": "0:34:50"}
203
  {"current_steps": 2000, "total_steps": 3573, "loss": 1.2489, "lr": 2.4157352896648785e-05, "epoch": 1.6792611251049538, "percentage": 55.98, "elapsed_time": "0:43:59", "remaining_time": "0:34:36"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
201
  {"current_steps": 1980, "total_steps": 3573, "loss": 1.2346, "lr": 2.4645788730188595e-05, "epoch": 1.6624685138539044, "percentage": 55.42, "elapsed_time": "0:43:35", "remaining_time": "0:35:04"}
202
  {"current_steps": 1990, "total_steps": 3573, "loss": 1.2266, "lr": 2.4401542241602936e-05, "epoch": 1.670864819479429, "percentage": 55.7, "elapsed_time": "0:43:47", "remaining_time": "0:34:50"}
203
  {"current_steps": 2000, "total_steps": 3573, "loss": 1.2489, "lr": 2.4157352896648785e-05, "epoch": 1.6792611251049538, "percentage": 55.98, "elapsed_time": "0:43:59", "remaining_time": "0:34:36"}
204
+ {"current_steps": 2010, "total_steps": 3573, "loss": 1.2321, "lr": 2.391324401170189e-05, "epoch": 1.6876574307304786, "percentage": 56.26, "elapsed_time": "0:44:34", "remaining_time": "0:34:40"}
205
+ {"current_steps": 2020, "total_steps": 3573, "loss": 1.2133, "lr": 2.3669238895455257e-05, "epoch": 1.6960537363560033, "percentage": 56.54, "elapsed_time": "0:44:47", "remaining_time": "0:34:25"}
206
+ {"current_steps": 2030, "total_steps": 3573, "loss": 1.1832, "lr": 2.3425360846693546e-05, "epoch": 1.704450041981528, "percentage": 56.82, "elapsed_time": "0:44:59", "remaining_time": "0:34:11"}
207
+ {"current_steps": 2040, "total_steps": 3573, "loss": 1.1978, "lr": 2.3181633152068444e-05, "epoch": 1.7128463476070528, "percentage": 57.09, "elapsed_time": "0:45:11", "remaining_time": "0:33:57"}
208
+ {"current_steps": 2050, "total_steps": 3573, "loss": 1.2274, "lr": 2.293807908387507e-05, "epoch": 1.7212426532325775, "percentage": 57.37, "elapsed_time": "0:45:23", "remaining_time": "0:33:43"}
209
+ {"current_steps": 2060, "total_steps": 3573, "loss": 1.2107, "lr": 2.269472189782984e-05, "epoch": 1.7296389588581025, "percentage": 57.65, "elapsed_time": "0:45:35", "remaining_time": "0:33:29"}
210
+ {"current_steps": 2070, "total_steps": 3573, "loss": 1.2453, "lr": 2.2451584830849963e-05, "epoch": 1.7380352644836272, "percentage": 57.93, "elapsed_time": "0:45:48", "remaining_time": "0:33:15"}
211
+ {"current_steps": 2080, "total_steps": 3573, "loss": 1.2112, "lr": 2.2208691098834574e-05, "epoch": 1.746431570109152, "percentage": 58.21, "elapsed_time": "0:46:00", "remaining_time": "0:33:01"}
212
+ {"current_steps": 2090, "total_steps": 3573, "loss": 1.2301, "lr": 2.196606389444802e-05, "epoch": 1.7548278757346767, "percentage": 58.49, "elapsed_time": "0:46:12", "remaining_time": "0:32:47"}
213
+ {"current_steps": 2100, "total_steps": 3573, "loss": 1.2254, "lr": 2.1723726384905332e-05, "epoch": 1.7632241813602016, "percentage": 58.77, "elapsed_time": "0:46:25", "remaining_time": "0:32:33"}
214
+ {"current_steps": 2110, "total_steps": 3573, "loss": 1.2191, "lr": 2.1481701709760054e-05, "epoch": 1.7716204869857264, "percentage": 59.05, "elapsed_time": "0:46:37", "remaining_time": "0:32:19"}
215
+ {"current_steps": 2120, "total_steps": 3573, "loss": 1.1897, "lr": 2.1240012978694786e-05, "epoch": 1.7800167926112511, "percentage": 59.33, "elapsed_time": "0:46:49", "remaining_time": "0:32:05"}
216
+ {"current_steps": 2130, "total_steps": 3573, "loss": 1.1936, "lr": 2.0998683269314613e-05, "epoch": 1.7884130982367759, "percentage": 59.61, "elapsed_time": "0:47:01", "remaining_time": "0:31:51"}
217
+ {"current_steps": 2140, "total_steps": 3573, "loss": 1.2248, "lr": 2.0757735624943448e-05, "epoch": 1.7968094038623006, "percentage": 59.89, "elapsed_time": "0:47:13", "remaining_time": "0:31:37"}
218
+ {"current_steps": 2150, "total_steps": 3573, "loss": 1.2022, "lr": 2.0517193052423823e-05, "epoch": 1.8052057094878253, "percentage": 60.17, "elapsed_time": "0:47:26", "remaining_time": "0:31:23"}
219
+ {"current_steps": 2160, "total_steps": 3573, "loss": 1.1938, "lr": 2.0277078519920044e-05, "epoch": 1.81360201511335, "percentage": 60.45, "elapsed_time": "0:47:38", "remaining_time": "0:31:09"}
220
+ {"current_steps": 2170, "total_steps": 3573, "loss": 1.1825, "lr": 2.0037414954725117e-05, "epoch": 1.8219983207388748, "percentage": 60.73, "elapsed_time": "0:47:50", "remaining_time": "0:30:55"}
221
+ {"current_steps": 2180, "total_steps": 3573, "loss": 1.2092, "lr": 1.979822524107148e-05, "epoch": 1.8303946263643995, "percentage": 61.01, "elapsed_time": "0:48:02", "remaining_time": "0:30:42"}
222
+ {"current_steps": 2190, "total_steps": 3573, "loss": 1.2378, "lr": 1.9559532217945974e-05, "epoch": 1.8387909319899243, "percentage": 61.29, "elapsed_time": "0:48:15", "remaining_time": "0:30:28"}
223
+ {"current_steps": 2200, "total_steps": 3573, "loss": 1.2142, "lr": 1.932135867690901e-05, "epoch": 1.8471872376154492, "percentage": 61.57, "elapsed_time": "0:48:27", "remaining_time": "0:30:14"}
224
+ {"current_steps": 2210, "total_steps": 3573, "loss": 1.2003, "lr": 1.908372735991836e-05, "epoch": 1.855583543240974, "percentage": 61.85, "elapsed_time": "0:48:39", "remaining_time": "0:30:00"}
225
+ {"current_steps": 2220, "total_steps": 3573, "loss": 1.2279, "lr": 1.8846660957157626e-05, "epoch": 1.8639798488664987, "percentage": 62.13, "elapsed_time": "0:48:51", "remaining_time": "0:29:46"}
226
+ {"current_steps": 2230, "total_steps": 3573, "loss": 1.2175, "lr": 1.8610182104869676e-05, "epoch": 1.8723761544920237, "percentage": 62.41, "elapsed_time": "0:49:03", "remaining_time": "0:29:32"}
227
+ {"current_steps": 2240, "total_steps": 3573, "loss": 1.1965, "lr": 1.837431338319523e-05, "epoch": 1.8807724601175484, "percentage": 62.69, "elapsed_time": "0:49:16", "remaining_time": "0:29:19"}
228
+ {"current_steps": 2250, "total_steps": 3573, "loss": 1.2082, "lr": 1.813907731401677e-05, "epoch": 1.8891687657430731, "percentage": 62.97, "elapsed_time": "0:49:28", "remaining_time": "0:29:05"}
229
+ {"current_steps": 2260, "total_steps": 3573, "loss": 1.1969, "lr": 1.790449635880813e-05, "epoch": 1.8975650713685979, "percentage": 63.25, "elapsed_time": "0:49:40", "remaining_time": "0:28:51"}
230
+ {"current_steps": 2270, "total_steps": 3573, "loss": 1.2094, "lr": 1.7670592916489637e-05, "epoch": 1.9059613769941226, "percentage": 63.53, "elapsed_time": "0:49:52", "remaining_time": "0:28:37"}
231
+ {"current_steps": 2280, "total_steps": 3573, "loss": 1.2171, "lr": 1.743738932128945e-05, "epoch": 1.9143576826196473, "percentage": 63.81, "elapsed_time": "0:50:05", "remaining_time": "0:28:24"}
232
+ {"current_steps": 2290, "total_steps": 3573, "loss": 1.1902, "lr": 1.7204907840610968e-05, "epoch": 1.922753988245172, "percentage": 64.09, "elapsed_time": "0:50:17", "remaining_time": "0:28:10"}
233
+ {"current_steps": 2300, "total_steps": 3573, "loss": 1.1915, "lr": 1.6973170672906592e-05, "epoch": 1.9311502938706968, "percentage": 64.37, "elapsed_time": "0:50:29", "remaining_time": "0:27:56"}
234
+ {"current_steps": 2310, "total_steps": 3573, "loss": 1.2018, "lr": 1.6742199945558116e-05, "epoch": 1.9395465994962215, "percentage": 64.65, "elapsed_time": "0:50:41", "remaining_time": "0:27:43"}
235
+ {"current_steps": 2320, "total_steps": 3573, "loss": 1.1742, "lr": 1.651201771276397e-05, "epoch": 1.9479429051217463, "percentage": 64.93, "elapsed_time": "0:50:54", "remaining_time": "0:27:29"}
236
+ {"current_steps": 2330, "total_steps": 3573, "loss": 1.2024, "lr": 1.6282645953433278e-05, "epoch": 1.9563392107472712, "percentage": 65.21, "elapsed_time": "0:51:06", "remaining_time": "0:27:15"}
237
+ {"current_steps": 2340, "total_steps": 3573, "loss": 1.2072, "lr": 1.6054106569087247e-05, "epoch": 1.964735516372796, "percentage": 65.49, "elapsed_time": "0:51:18", "remaining_time": "0:27:02"}
238
+ {"current_steps": 2350, "total_steps": 3573, "loss": 1.1996, "lr": 1.5826421381767943e-05, "epoch": 1.9731318219983207, "percentage": 65.77, "elapsed_time": "0:51:30", "remaining_time": "0:26:48"}
239
+ {"current_steps": 2360, "total_steps": 3573, "loss": 1.1963, "lr": 1.5599612131954562e-05, "epoch": 1.9815281276238457, "percentage": 66.05, "elapsed_time": "0:51:42", "remaining_time": "0:26:34"}
240
+ {"current_steps": 2370, "total_steps": 3573, "loss": 1.1909, "lr": 1.537370047648755e-05, "epoch": 1.9899244332493704, "percentage": 66.33, "elapsed_time": "0:51:55", "remaining_time": "0:26:21"}
241
+ {"current_steps": 2380, "total_steps": 3573, "loss": 1.1934, "lr": 1.5148707986500754e-05, "epoch": 1.9983207388748951, "percentage": 66.61, "elapsed_time": "0:52:07", "remaining_time": "0:26:07"}
242
+ {"current_steps": 2390, "total_steps": 3573, "loss": 1.1015, "lr": 1.4924656145361642e-05, "epoch": 2.00671704450042, "percentage": 66.89, "elapsed_time": "0:52:19", "remaining_time": "0:25:53"}
243
+ {"current_steps": 2400, "total_steps": 3573, "loss": 1.0911, "lr": 1.4701566346619994e-05, "epoch": 2.0151133501259446, "percentage": 67.17, "elapsed_time": "0:52:31", "remaining_time": "0:25:40"}
244
+ {"current_steps": 2400, "total_steps": 3573, "eval_loss": 1.288699746131897, "epoch": 2.0151133501259446, "percentage": 67.17, "elapsed_time": "0:53:09", "remaining_time": "0:25:58"}
245
+ {"current_steps": 2410, "total_steps": 3573, "loss": 1.0922, "lr": 1.447945989196518e-05, "epoch": 2.0235096557514693, "percentage": 67.45, "elapsed_time": "0:53:21", "remaining_time": "0:25:45"}
246
+ {"current_steps": 2420, "total_steps": 3573, "loss": 1.0882, "lr": 1.4258357989192089e-05, "epoch": 2.031905961376994, "percentage": 67.73, "elapsed_time": "0:53:33", "remaining_time": "0:25:31"}
247
+ {"current_steps": 2430, "total_steps": 3573, "loss": 1.0976, "lr": 1.403828175017618e-05, "epoch": 2.040302267002519, "percentage": 68.01, "elapsed_time": "0:53:46", "remaining_time": "0:25:17"}
248
+ {"current_steps": 2440, "total_steps": 3573, "loss": 1.0999, "lr": 1.381925218885759e-05, "epoch": 2.0486985726280436, "percentage": 68.29, "elapsed_time": "0:53:58", "remaining_time": "0:25:03"}
249
+ {"current_steps": 2450, "total_steps": 3573, "loss": 1.0848, "lr": 1.3601290219234642e-05, "epoch": 2.0570948782535683, "percentage": 68.57, "elapsed_time": "0:54:10", "remaining_time": "0:24:49"}
250
+ {"current_steps": 2460, "total_steps": 3573, "loss": 1.1053, "lr": 1.3384416653366796e-05, "epoch": 2.065491183879093, "percentage": 68.85, "elapsed_time": "0:54:22", "remaining_time": "0:24:36"}
251
+ {"current_steps": 2470, "total_steps": 3573, "loss": 1.0565, "lr": 1.3168652199387565e-05, "epoch": 2.0738874895046178, "percentage": 69.13, "elapsed_time": "0:54:34", "remaining_time": "0:24:22"}
252
+ {"current_steps": 2480, "total_steps": 3573, "loss": 1.1135, "lr": 1.2954017459527037e-05, "epoch": 2.082283795130143, "percentage": 69.41, "elapsed_time": "0:54:46", "remaining_time": "0:24:08"}
253
+ {"current_steps": 2490, "total_steps": 3573, "loss": 1.0978, "lr": 1.2740532928144785e-05, "epoch": 2.0906801007556677, "percentage": 69.69, "elapsed_time": "0:54:59", "remaining_time": "0:23:54"}
254
+ {"current_steps": 2500, "total_steps": 3573, "loss": 1.0924, "lr": 1.2528218989772928e-05, "epoch": 2.0990764063811924, "percentage": 69.97, "elapsed_time": "0:55:11", "remaining_time": "0:23:41"}