hlillemark commited on
Commit
7e03cc3
·
verified ·
1 Parent(s): 6900048

Training in progress, step 807

Browse files
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c448fa7e070a29f6fe1491909f4d5f51f4a506a523f63e26e71b269ef57d0403
3
  size 207244392
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8eae33852a972f9c21e471190373c66c73c768ce2e1fd2fab76abe313976b84
3
  size 207244392
runs/Mar26_23-17-19_g42-h100-instance-064/events.out.tfevents.1743056315.g42-h100-instance-064.3225165.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b33c8c923e1804d0bacfecd017d21bb431e1ba83548a0d89d1c5039369a5f1bd
3
- size 16697
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34f58049df38cd9dcf33b09b0c34c6630bf06f64c7e03a82435517ae33713fd7
3
+ size 23923
trainer_log.jsonl CHANGED
@@ -50,3 +50,36 @@
50
  {"current_steps": 480, "total_steps": 807, "loss": 0.2157, "lr": 4.2242393123203986e-05, "epoch": 1.7799442896935933, "percentage": 59.48, "elapsed_time": "5:36:15", "remaining_time": "3:49:04"}
51
  {"current_steps": 490, "total_steps": 807, "loss": 0.2121, "lr": 4.011289112726085e-05, "epoch": 1.8170844939647168, "percentage": 60.72, "elapsed_time": "5:43:11", "remaining_time": "3:42:01"}
52
  {"current_steps": 500, "total_steps": 807, "loss": 0.2053, "lr": 3.8001900053309184e-05, "epoch": 1.8542246982358404, "percentage": 61.96, "elapsed_time": "5:50:08", "remaining_time": "3:34:59"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
50
  {"current_steps": 480, "total_steps": 807, "loss": 0.2157, "lr": 4.2242393123203986e-05, "epoch": 1.7799442896935933, "percentage": 59.48, "elapsed_time": "5:36:15", "remaining_time": "3:49:04"}
51
  {"current_steps": 490, "total_steps": 807, "loss": 0.2121, "lr": 4.011289112726085e-05, "epoch": 1.8170844939647168, "percentage": 60.72, "elapsed_time": "5:43:11", "remaining_time": "3:42:01"}
52
  {"current_steps": 500, "total_steps": 807, "loss": 0.2053, "lr": 3.8001900053309184e-05, "epoch": 1.8542246982358404, "percentage": 61.96, "elapsed_time": "5:50:08", "remaining_time": "3:34:59"}
53
+ {"current_steps": 510, "total_steps": 807, "loss": 0.239, "lr": 3.591337215792852e-05, "epoch": 1.8913649025069637, "percentage": 63.2, "elapsed_time": "5:58:29", "remaining_time": "3:28:46"}
54
+ {"current_steps": 520, "total_steps": 807, "loss": 0.2329, "lr": 3.3851217641506656e-05, "epoch": 1.9285051067780872, "percentage": 64.44, "elapsed_time": "6:05:26", "remaining_time": "3:21:41"}
55
+ {"current_steps": 530, "total_steps": 807, "loss": 0.2129, "lr": 3.1819297327453045e-05, "epoch": 1.9656453110492107, "percentage": 65.68, "elapsed_time": "6:12:26", "remaining_time": "3:14:39"}
56
+ {"current_steps": 540, "total_steps": 807, "loss": 0.2212, "lr": 2.9821415433857174e-05, "epoch": 2.0, "percentage": 66.91, "elapsed_time": "6:18:54", "remaining_time": "3:07:20"}
57
+ {"current_steps": 550, "total_steps": 807, "loss": 0.1835, "lr": 2.786131245112495e-05, "epoch": 2.0371402042711235, "percentage": 68.15, "elapsed_time": "6:26:00", "remaining_time": "3:00:22"}
58
+ {"current_steps": 560, "total_steps": 807, "loss": 0.187, "lr": 2.5942658138927867e-05, "epoch": 2.074280408542247, "percentage": 69.39, "elapsed_time": "6:33:03", "remaining_time": "2:53:22"}
59
+ {"current_steps": 570, "total_steps": 807, "loss": 0.1727, "lr": 2.406904465557614e-05, "epoch": 2.1114206128133706, "percentage": 70.63, "elapsed_time": "6:40:03", "remaining_time": "2:46:20"}
60
+ {"current_steps": 580, "total_steps": 807, "loss": 0.1718, "lr": 2.224397983267951e-05, "epoch": 2.148560817084494, "percentage": 71.87, "elapsed_time": "6:47:03", "remaining_time": "2:39:18"}
61
+ {"current_steps": 590, "total_steps": 807, "loss": 0.1611, "lr": 2.0470880607686603e-05, "epoch": 2.1857010213556176, "percentage": 73.11, "elapsed_time": "6:53:56", "remaining_time": "2:32:14"}
62
+ {"current_steps": 600, "total_steps": 807, "loss": 0.1724, "lr": 1.8753066626599086e-05, "epoch": 2.222841225626741, "percentage": 74.35, "elapsed_time": "7:00:57", "remaining_time": "2:25:13"}
63
+ {"current_steps": 600, "total_steps": 807, "eval_loss": 0.31889092922210693, "epoch": 2.222841225626741, "percentage": 74.35, "elapsed_time": "7:02:06", "remaining_time": "2:25:37"}
64
+ {"current_steps": 610, "total_steps": 807, "loss": 0.1786, "lr": 1.7093754028837345e-05, "epoch": 2.2599814298978647, "percentage": 75.59, "elapsed_time": "7:08:59", "remaining_time": "2:18:32"}
65
+ {"current_steps": 620, "total_steps": 807, "loss": 0.1577, "lr": 1.549604942589441e-05, "epoch": 2.2971216341689877, "percentage": 76.83, "elapsed_time": "7:15:53", "remaining_time": "2:11:28"}
66
+ {"current_steps": 630, "total_steps": 807, "loss": 0.1631, "lr": 1.3962944085050832e-05, "epoch": 2.3342618384401113, "percentage": 78.07, "elapsed_time": "7:22:49", "remaining_time": "2:04:24"}
67
+ {"current_steps": 640, "total_steps": 807, "loss": 0.1714, "lr": 1.2497308329040475e-05, "epoch": 2.371402042711235, "percentage": 79.31, "elapsed_time": "7:29:52", "remaining_time": "1:57:23"}
68
+ {"current_steps": 650, "total_steps": 807, "loss": 0.1637, "lr": 1.1101886162151764e-05, "epoch": 2.4085422469823583, "percentage": 80.55, "elapsed_time": "7:36:51", "remaining_time": "1:50:20"}
69
+ {"current_steps": 660, "total_steps": 807, "loss": 0.1728, "lr": 9.779290132826224e-06, "epoch": 2.445682451253482, "percentage": 81.78, "elapsed_time": "7:43:52", "remaining_time": "1:43:19"}
70
+ {"current_steps": 670, "total_steps": 807, "loss": 0.1655, "lr": 8.531996442372048e-06, "epoch": 2.4828226555246053, "percentage": 83.02, "elapsed_time": "7:50:44", "remaining_time": "1:36:15"}
71
+ {"current_steps": 680, "total_steps": 807, "loss": 0.1538, "lr": 7.3623403089507825e-06, "epoch": 2.519962859795729, "percentage": 84.26, "elapsed_time": "7:57:39", "remaining_time": "1:29:12"}
72
+ {"current_steps": 690, "total_steps": 807, "loss": 0.1601, "lr": 6.272511595516401e-06, "epoch": 2.5571030640668524, "percentage": 85.5, "elapsed_time": "8:04:41", "remaining_time": "1:22:11"}
73
+ {"current_steps": 700, "total_steps": 807, "loss": 0.1706, "lr": 5.264550709892685e-06, "epoch": 2.594243268337976, "percentage": 86.74, "elapsed_time": "8:11:39", "remaining_time": "1:15:09"}
74
+ {"current_steps": 710, "total_steps": 807, "loss": 0.1644, "lr": 4.340344784664535e-06, "epoch": 2.6313834726090994, "percentage": 87.98, "elapsed_time": "8:18:38", "remaining_time": "1:08:07"}
75
+ {"current_steps": 720, "total_steps": 807, "loss": 0.1712, "lr": 3.501624144035559e-06, "epoch": 2.668523676880223, "percentage": 89.22, "elapsed_time": "8:25:31", "remaining_time": "1:01:05"}
76
+ {"current_steps": 730, "total_steps": 807, "loss": 0.1685, "lr": 2.7499590642665774e-06, "epoch": 2.7056638811513465, "percentage": 90.46, "elapsed_time": "8:32:31", "remaining_time": "0:54:03"}
77
+ {"current_steps": 740, "total_steps": 807, "loss": 0.1488, "lr": 2.0867568337605616e-06, "epoch": 2.7428040854224696, "percentage": 91.7, "elapsed_time": "8:39:32", "remaining_time": "0:47:02"}
78
+ {"current_steps": 750, "total_steps": 807, "loss": 0.17, "lr": 1.5132591182978106e-06, "epoch": 2.779944289693593, "percentage": 92.94, "elapsed_time": "8:46:35", "remaining_time": "0:40:01"}
79
+ {"current_steps": 760, "total_steps": 807, "loss": 0.156, "lr": 1.0305396363545717e-06, "epoch": 2.8170844939647166, "percentage": 94.18, "elapsed_time": "8:53:35", "remaining_time": "0:32:59"}
80
+ {"current_steps": 770, "total_steps": 807, "loss": 0.1625, "lr": 6.395021488572128e-07, "epoch": 2.85422469823584, "percentage": 95.42, "elapsed_time": "9:00:34", "remaining_time": "0:25:58"}
81
+ {"current_steps": 780, "total_steps": 807, "loss": 0.1714, "lr": 3.408787671357494e-07, "epoch": 2.8913649025069637, "percentage": 96.65, "elapsed_time": "9:07:26", "remaining_time": "0:18:56"}
82
+ {"current_steps": 790, "total_steps": 807, "loss": 0.1688, "lr": 1.352285822445065e-07, "epoch": 2.928505106778087, "percentage": 97.89, "elapsed_time": "9:14:17", "remaining_time": "0:11:55"}
83
+ {"current_steps": 800, "total_steps": 807, "loss": 0.1525, "lr": 2.2936618216201632e-08, "epoch": 2.9656453110492107, "percentage": 99.13, "elapsed_time": "9:21:17", "remaining_time": "0:04:54"}
84
+ {"current_steps": 800, "total_steps": 807, "eval_loss": 0.31994694471359253, "epoch": 2.9656453110492107, "percentage": 99.13, "elapsed_time": "9:22:26", "remaining_time": "0:04:55"}
85
+ {"current_steps": 807, "total_steps": 807, "epoch": 2.9916434540389973, "percentage": 100.0, "elapsed_time": "9:28:39", "remaining_time": "0:00:00"}