sedrickkeh commited on
Commit
eea6561
·
verified ·
1 Parent(s): 807a482

Training in progress, epoch 1

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c5a8de57e6c7001583f61815ac8ca770def617bc98da32bf11acd3b6a6110971
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:baa48abddd42aacc3f3ac5b61842accd267c86b30c90ef796ee041b2b5e8c8b8
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:f42e3dca44f5be8703dd999d880932035d644fd0c349183144a288648e921379
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72480a6d5d47d78008a87d5a64ac9e4e3ba2f7c94a5bf116768dc4625e6789dc
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5fa7ce90d1e47af06cc1e547dbcb0e3f201a39460dae1b4837c2063150b66544
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e31305a9ac9c52caacb54f836a6d416c29ccbfc29a6a2c10608516a4f6aa9c7
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1273883dc4c9d0a9d54b9c7b6aea2fb95ed2a098b1454ddc36141815c27b78f8
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1530da3a1ad50d7ef0a26cf3639a3a5adcf1af78ddd46cd08ef0b77274144b0
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -27,3 +27,31 @@
27
  {"current_steps": 270, "total_steps": 831, "loss": 0.7392, "lr": 5e-06, "epoch": 0.9720972097209721, "percentage": 32.49, "elapsed_time": "4:17:48", "remaining_time": "8:55:40"}
28
  {"current_steps": 277, "total_steps": 831, "eval_loss": 0.7396969199180603, "epoch": 0.9972997299729973, "percentage": 33.33, "elapsed_time": "4:30:03", "remaining_time": "9:00:06"}
29
  {"current_steps": 280, "total_steps": 831, "loss": 0.7435, "lr": 5e-06, "epoch": 1.008100810081008, "percentage": 33.69, "elapsed_time": "4:33:26", "remaining_time": "8:58:05"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
27
  {"current_steps": 270, "total_steps": 831, "loss": 0.7392, "lr": 5e-06, "epoch": 0.9720972097209721, "percentage": 32.49, "elapsed_time": "4:17:48", "remaining_time": "8:55:40"}
28
  {"current_steps": 277, "total_steps": 831, "eval_loss": 0.7396969199180603, "epoch": 0.9972997299729973, "percentage": 33.33, "elapsed_time": "4:30:03", "remaining_time": "9:00:06"}
29
  {"current_steps": 280, "total_steps": 831, "loss": 0.7435, "lr": 5e-06, "epoch": 1.008100810081008, "percentage": 33.69, "elapsed_time": "4:33:26", "remaining_time": "8:58:05"}
30
+ {"current_steps": 290, "total_steps": 831, "loss": 0.6915, "lr": 5e-06, "epoch": 1.0441044104410442, "percentage": 34.9, "elapsed_time": "4:42:59", "remaining_time": "8:47:54"}
31
+ {"current_steps": 300, "total_steps": 831, "loss": 0.6946, "lr": 5e-06, "epoch": 1.08010801080108, "percentage": 36.1, "elapsed_time": "4:52:34", "remaining_time": "8:37:50"}
32
+ {"current_steps": 310, "total_steps": 831, "loss": 0.6902, "lr": 5e-06, "epoch": 1.116111611161116, "percentage": 37.3, "elapsed_time": "5:02:08", "remaining_time": "8:27:46"}
33
+ {"current_steps": 320, "total_steps": 831, "loss": 0.6898, "lr": 5e-06, "epoch": 1.1521152115211521, "percentage": 38.51, "elapsed_time": "5:11:41", "remaining_time": "8:17:43"}
34
+ {"current_steps": 330, "total_steps": 831, "loss": 0.6853, "lr": 5e-06, "epoch": 1.188118811881188, "percentage": 39.71, "elapsed_time": "5:21:14", "remaining_time": "8:07:42"}
35
+ {"current_steps": 340, "total_steps": 831, "loss": 0.6863, "lr": 5e-06, "epoch": 1.2241224122412242, "percentage": 40.91, "elapsed_time": "5:30:47", "remaining_time": "7:57:42"}
36
+ {"current_steps": 350, "total_steps": 831, "loss": 0.689, "lr": 5e-06, "epoch": 1.2601260126012601, "percentage": 42.12, "elapsed_time": "5:40:20", "remaining_time": "7:47:43"}
37
+ {"current_steps": 360, "total_steps": 831, "loss": 0.6872, "lr": 5e-06, "epoch": 1.296129612961296, "percentage": 43.32, "elapsed_time": "5:49:55", "remaining_time": "7:37:48"}
38
+ {"current_steps": 370, "total_steps": 831, "loss": 0.6815, "lr": 5e-06, "epoch": 1.3321332133213322, "percentage": 44.52, "elapsed_time": "5:59:27", "remaining_time": "7:27:52"}
39
+ {"current_steps": 380, "total_steps": 831, "loss": 0.6871, "lr": 5e-06, "epoch": 1.368136813681368, "percentage": 45.73, "elapsed_time": "6:08:59", "remaining_time": "7:17:56"}
40
+ {"current_steps": 390, "total_steps": 831, "loss": 0.6809, "lr": 5e-06, "epoch": 1.4041404140414042, "percentage": 46.93, "elapsed_time": "6:18:33", "remaining_time": "7:08:03"}
41
+ {"current_steps": 400, "total_steps": 831, "loss": 0.6885, "lr": 5e-06, "epoch": 1.4401440144014401, "percentage": 48.13, "elapsed_time": "6:28:04", "remaining_time": "6:58:09"}
42
+ {"current_steps": 410, "total_steps": 831, "loss": 0.6851, "lr": 5e-06, "epoch": 1.476147614761476, "percentage": 49.34, "elapsed_time": "6:37:37", "remaining_time": "6:48:17"}
43
+ {"current_steps": 420, "total_steps": 831, "loss": 0.6872, "lr": 5e-06, "epoch": 1.5121512151215122, "percentage": 50.54, "elapsed_time": "6:47:10", "remaining_time": "6:38:26"}
44
+ {"current_steps": 430, "total_steps": 831, "loss": 0.6872, "lr": 5e-06, "epoch": 1.5481548154815483, "percentage": 51.74, "elapsed_time": "6:56:43", "remaining_time": "6:28:37"}
45
+ {"current_steps": 440, "total_steps": 831, "loss": 0.6816, "lr": 5e-06, "epoch": 1.5841584158415842, "percentage": 52.95, "elapsed_time": "7:06:16", "remaining_time": "6:18:48"}
46
+ {"current_steps": 450, "total_steps": 831, "loss": 0.6852, "lr": 5e-06, "epoch": 1.6201620162016201, "percentage": 54.15, "elapsed_time": "7:15:48", "remaining_time": "6:08:59"}
47
+ {"current_steps": 460, "total_steps": 831, "loss": 0.6837, "lr": 5e-06, "epoch": 1.656165616561656, "percentage": 55.35, "elapsed_time": "7:25:22", "remaining_time": "5:59:12"}
48
+ {"current_steps": 470, "total_steps": 831, "loss": 0.6828, "lr": 5e-06, "epoch": 1.6921692169216922, "percentage": 56.56, "elapsed_time": "7:34:54", "remaining_time": "5:49:24"}
49
+ {"current_steps": 480, "total_steps": 831, "loss": 0.6892, "lr": 5e-06, "epoch": 1.7281728172817283, "percentage": 57.76, "elapsed_time": "7:44:28", "remaining_time": "5:39:38"}
50
+ {"current_steps": 490, "total_steps": 831, "loss": 0.6895, "lr": 5e-06, "epoch": 1.7641764176417642, "percentage": 58.97, "elapsed_time": "7:54:02", "remaining_time": "5:29:53"}
51
+ {"current_steps": 500, "total_steps": 831, "loss": 0.6888, "lr": 5e-06, "epoch": 1.8001800180018002, "percentage": 60.17, "elapsed_time": "8:03:36", "remaining_time": "5:20:08"}
52
+ {"current_steps": 510, "total_steps": 831, "loss": 0.6822, "lr": 5e-06, "epoch": 1.836183618361836, "percentage": 61.37, "elapsed_time": "8:13:10", "remaining_time": "5:10:24"}
53
+ {"current_steps": 520, "total_steps": 831, "loss": 0.6856, "lr": 5e-06, "epoch": 1.8721872187218722, "percentage": 62.58, "elapsed_time": "8:22:45", "remaining_time": "5:00:41"}
54
+ {"current_steps": 530, "total_steps": 831, "loss": 0.6858, "lr": 5e-06, "epoch": 1.9081908190819084, "percentage": 63.78, "elapsed_time": "8:32:19", "remaining_time": "4:50:57"}
55
+ {"current_steps": 540, "total_steps": 831, "loss": 0.6854, "lr": 5e-06, "epoch": 1.9441944194419443, "percentage": 64.98, "elapsed_time": "8:41:54", "remaining_time": "4:41:14"}
56
+ {"current_steps": 550, "total_steps": 831, "loss": 0.6894, "lr": 5e-06, "epoch": 1.9801980198019802, "percentage": 66.19, "elapsed_time": "8:51:27", "remaining_time": "4:31:31"}
57
+ {"current_steps": 555, "total_steps": 831, "eval_loss": 0.7263253331184387, "epoch": 1.9981998199819984, "percentage": 66.79, "elapsed_time": "9:01:30", "remaining_time": "4:29:17"}