sedrickkeh commited on
Commit
1551094
·
verified ·
1 Parent(s): 6c31573

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 sha256:31fdc8bff159f37f86a9b4241b32bc7d225a39f5c2bca5b3c36681436e5d4d7d
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03ba242fd7258d179908cb837de7159d61af27142b62a4a05c4987a6894c217a
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:c3527fd46b0b15e6bb271eca46fc1c39a77edaff28620280c0a528d693ed4105
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d52096cd72ce5be8176a1724e7138fc2af3cc651f3638e3d07962785474310f1
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3f143f16ab8d75465e257438f0a0f5df6232783dc6f551b39c704196a0fceef6
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93c70946ed285befde3a4884005b7b301b3555faf54c6e8de84d2be60aa5e47b
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4d1c63d6b83312ca02deb8b56fbb79bee76e460a787833ea455c7c3976d65226
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d4bb903071ea6ed91770ee0a8958bbc029d3c6391949d28f607b60acae4ae95
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -29,3 +29,34 @@
29
  {"current_steps": 290, "total_steps": 909, "loss": 0.7576, "lr": 5e-06, "epoch": 0.9567010309278351, "percentage": 31.9, "elapsed_time": "4:38:38", "remaining_time": "9:54:44"}
30
  {"current_steps": 300, "total_steps": 909, "loss": 0.7548, "lr": 5e-06, "epoch": 0.9896907216494846, "percentage": 33.0, "elapsed_time": "4:48:14", "remaining_time": "9:45:07"}
31
  {"current_steps": 303, "total_steps": 909, "eval_loss": 0.7519278526306152, "epoch": 0.9995876288659794, "percentage": 33.33, "elapsed_time": "4:56:36", "remaining_time": "9:53:13"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
29
  {"current_steps": 290, "total_steps": 909, "loss": 0.7576, "lr": 5e-06, "epoch": 0.9567010309278351, "percentage": 31.9, "elapsed_time": "4:38:38", "remaining_time": "9:54:44"}
30
  {"current_steps": 300, "total_steps": 909, "loss": 0.7548, "lr": 5e-06, "epoch": 0.9896907216494846, "percentage": 33.0, "elapsed_time": "4:48:14", "remaining_time": "9:45:07"}
31
  {"current_steps": 303, "total_steps": 909, "eval_loss": 0.7519278526306152, "epoch": 0.9995876288659794, "percentage": 33.33, "elapsed_time": "4:56:36", "remaining_time": "9:53:13"}
32
+ {"current_steps": 310, "total_steps": 909, "loss": 0.7934, "lr": 5e-06, "epoch": 1.022680412371134, "percentage": 34.1, "elapsed_time": "5:04:22", "remaining_time": "9:48:06"}
33
+ {"current_steps": 320, "total_steps": 909, "loss": 0.7044, "lr": 5e-06, "epoch": 1.0556701030927835, "percentage": 35.2, "elapsed_time": "5:13:57", "remaining_time": "9:37:51"}
34
+ {"current_steps": 330, "total_steps": 909, "loss": 0.7115, "lr": 5e-06, "epoch": 1.088659793814433, "percentage": 36.3, "elapsed_time": "5:23:34", "remaining_time": "9:27:43"}
35
+ {"current_steps": 340, "total_steps": 909, "loss": 0.7094, "lr": 5e-06, "epoch": 1.1216494845360825, "percentage": 37.4, "elapsed_time": "5:33:09", "remaining_time": "9:17:32"}
36
+ {"current_steps": 350, "total_steps": 909, "loss": 0.7079, "lr": 5e-06, "epoch": 1.1546391752577319, "percentage": 38.5, "elapsed_time": "5:42:46", "remaining_time": "9:07:27"}
37
+ {"current_steps": 360, "total_steps": 909, "loss": 0.7073, "lr": 5e-06, "epoch": 1.1876288659793814, "percentage": 39.6, "elapsed_time": "5:52:23", "remaining_time": "8:57:24"}
38
+ {"current_steps": 370, "total_steps": 909, "loss": 0.7096, "lr": 5e-06, "epoch": 1.220618556701031, "percentage": 40.7, "elapsed_time": "6:02:01", "remaining_time": "8:47:22"}
39
+ {"current_steps": 380, "total_steps": 909, "loss": 0.7066, "lr": 5e-06, "epoch": 1.2536082474226804, "percentage": 41.8, "elapsed_time": "6:11:38", "remaining_time": "8:37:22"}
40
+ {"current_steps": 390, "total_steps": 909, "loss": 0.7076, "lr": 5e-06, "epoch": 1.2865979381443298, "percentage": 42.9, "elapsed_time": "6:21:14", "remaining_time": "8:27:20"}
41
+ {"current_steps": 400, "total_steps": 909, "loss": 0.7062, "lr": 5e-06, "epoch": 1.3195876288659794, "percentage": 44.0, "elapsed_time": "6:30:51", "remaining_time": "8:17:21"}
42
+ {"current_steps": 410, "total_steps": 909, "loss": 0.7117, "lr": 5e-06, "epoch": 1.352577319587629, "percentage": 45.1, "elapsed_time": "6:40:26", "remaining_time": "8:07:21"}
43
+ {"current_steps": 420, "total_steps": 909, "loss": 0.7094, "lr": 5e-06, "epoch": 1.3855670103092783, "percentage": 46.2, "elapsed_time": "6:50:02", "remaining_time": "7:57:24"}
44
+ {"current_steps": 430, "total_steps": 909, "loss": 0.7054, "lr": 5e-06, "epoch": 1.418556701030928, "percentage": 47.3, "elapsed_time": "6:59:37", "remaining_time": "7:47:26"}
45
+ {"current_steps": 440, "total_steps": 909, "loss": 0.7075, "lr": 5e-06, "epoch": 1.4515463917525773, "percentage": 48.4, "elapsed_time": "7:09:15", "remaining_time": "7:37:33"}
46
+ {"current_steps": 450, "total_steps": 909, "loss": 0.7099, "lr": 5e-06, "epoch": 1.4845360824742269, "percentage": 49.5, "elapsed_time": "7:18:53", "remaining_time": "7:27:39"}
47
+ {"current_steps": 460, "total_steps": 909, "loss": 0.7018, "lr": 5e-06, "epoch": 1.5175257731958762, "percentage": 50.61, "elapsed_time": "7:28:29", "remaining_time": "7:17:46"}
48
+ {"current_steps": 470, "total_steps": 909, "loss": 0.7051, "lr": 5e-06, "epoch": 1.5505154639175258, "percentage": 51.71, "elapsed_time": "7:38:05", "remaining_time": "7:07:52"}
49
+ {"current_steps": 480, "total_steps": 909, "loss": 0.7106, "lr": 5e-06, "epoch": 1.5835051546391754, "percentage": 52.81, "elapsed_time": "7:47:42", "remaining_time": "6:58:00"}
50
+ {"current_steps": 490, "total_steps": 909, "loss": 0.7043, "lr": 5e-06, "epoch": 1.6164948453608248, "percentage": 53.91, "elapsed_time": "7:57:20", "remaining_time": "6:48:10"}
51
+ {"current_steps": 500, "total_steps": 909, "loss": 0.7086, "lr": 5e-06, "epoch": 1.6494845360824741, "percentage": 55.01, "elapsed_time": "8:06:58", "remaining_time": "6:38:20"}
52
+ {"current_steps": 510, "total_steps": 909, "loss": 0.7026, "lr": 5e-06, "epoch": 1.6824742268041237, "percentage": 56.11, "elapsed_time": "8:16:35", "remaining_time": "6:28:30"}
53
+ {"current_steps": 520, "total_steps": 909, "loss": 0.7037, "lr": 5e-06, "epoch": 1.7154639175257733, "percentage": 57.21, "elapsed_time": "8:26:13", "remaining_time": "6:18:41"}
54
+ {"current_steps": 530, "total_steps": 909, "loss": 0.7066, "lr": 5e-06, "epoch": 1.7484536082474227, "percentage": 58.31, "elapsed_time": "8:35:49", "remaining_time": "6:08:51"}
55
+ {"current_steps": 540, "total_steps": 909, "loss": 0.707, "lr": 5e-06, "epoch": 1.781443298969072, "percentage": 59.41, "elapsed_time": "8:45:27", "remaining_time": "5:59:03"}
56
+ {"current_steps": 550, "total_steps": 909, "loss": 0.6996, "lr": 5e-06, "epoch": 1.8144329896907216, "percentage": 60.51, "elapsed_time": "8:55:03", "remaining_time": "5:49:14"}
57
+ {"current_steps": 560, "total_steps": 909, "loss": 0.7036, "lr": 5e-06, "epoch": 1.8474226804123712, "percentage": 61.61, "elapsed_time": "9:04:41", "remaining_time": "5:39:27"}
58
+ {"current_steps": 570, "total_steps": 909, "loss": 0.7066, "lr": 5e-06, "epoch": 1.8804123711340206, "percentage": 62.71, "elapsed_time": "9:14:19", "remaining_time": "5:29:40"}
59
+ {"current_steps": 580, "total_steps": 909, "loss": 0.705, "lr": 5e-06, "epoch": 1.91340206185567, "percentage": 63.81, "elapsed_time": "9:23:57", "remaining_time": "5:19:53"}
60
+ {"current_steps": 590, "total_steps": 909, "loss": 0.7051, "lr": 5e-06, "epoch": 1.9463917525773196, "percentage": 64.91, "elapsed_time": "9:33:36", "remaining_time": "5:10:07"}
61
+ {"current_steps": 600, "total_steps": 909, "loss": 0.7026, "lr": 5e-06, "epoch": 1.9793814432989691, "percentage": 66.01, "elapsed_time": "9:43:14", "remaining_time": "5:00:21"}
62
+ {"current_steps": 606, "total_steps": 909, "eval_loss": 0.7376570701599121, "epoch": 1.9991752577319588, "percentage": 66.67, "elapsed_time": "9:54:34", "remaining_time": "4:57:17"}