sedrickkeh commited on
Commit
d8a36ea
·
verified ·
1 Parent(s): 0826e7d

Training in progress, epoch 2

Browse files
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f415e1cce5c92c5012d5d8c4bcd21a28c4613e33969d2fd9172ba815f0a40ff6
3
  size 4938985352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd4c2e49512375442df452f434d76879eca39e6fcf0a9a7d4486570bff470ab8
3
  size 4938985352
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ad2d973318a90b9bf2e13f657fcb2eb5328f224d845b7f60bd6daf4ccfe1ca0f
3
  size 4947390880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66bde4ba2671f5f95a05bf077bc53cbdc8d70c78aa636176962e540c506a8f6e
3
  size 4947390880
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4dd35ae19db40478182eebf2e660315073019b539e74da340633e537f53e1096
3
  size 3590488816
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca0d083eec417b381f8ffc0be8a90c44478e1bd0b70b66e1201d98e5a5abc034
3
  size 3590488816
trainer_log.jsonl CHANGED
@@ -52,3 +52,29 @@
52
  {"current_steps": 510, "total_steps": 783, "loss": 0.5449, "lr": 5e-06, "epoch": 1.9484240687679084, "percentage": 65.13, "elapsed_time": "7:43:30", "remaining_time": "4:08:06"}
53
  {"current_steps": 520, "total_steps": 783, "loss": 0.5494, "lr": 5e-06, "epoch": 1.9866284622731614, "percentage": 66.41, "elapsed_time": "7:52:29", "remaining_time": "3:58:58"}
54
  {"current_steps": 523, "total_steps": 783, "eval_loss": 0.5642140507698059, "epoch": 1.9980897803247375, "percentage": 66.79, "elapsed_time": "7:59:55", "remaining_time": "3:58:35"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
52
  {"current_steps": 510, "total_steps": 783, "loss": 0.5449, "lr": 5e-06, "epoch": 1.9484240687679084, "percentage": 65.13, "elapsed_time": "7:43:30", "remaining_time": "4:08:06"}
53
  {"current_steps": 520, "total_steps": 783, "loss": 0.5494, "lr": 5e-06, "epoch": 1.9866284622731614, "percentage": 66.41, "elapsed_time": "7:52:29", "remaining_time": "3:58:58"}
54
  {"current_steps": 523, "total_steps": 783, "eval_loss": 0.5642140507698059, "epoch": 1.9980897803247375, "percentage": 66.79, "elapsed_time": "7:59:55", "remaining_time": "3:58:35"}
55
+ {"current_steps": 530, "total_steps": 783, "loss": 0.5442, "lr": 5e-06, "epoch": 2.0248328557784143, "percentage": 67.69, "elapsed_time": "8:06:52", "remaining_time": "3:52:24"}
56
+ {"current_steps": 540, "total_steps": 783, "loss": 0.512, "lr": 5e-06, "epoch": 2.0630372492836675, "percentage": 68.97, "elapsed_time": "8:15:50", "remaining_time": "3:43:07"}
57
+ {"current_steps": 550, "total_steps": 783, "loss": 0.5191, "lr": 5e-06, "epoch": 2.1012416427889207, "percentage": 70.24, "elapsed_time": "8:24:47", "remaining_time": "3:33:50"}
58
+ {"current_steps": 560, "total_steps": 783, "loss": 0.5197, "lr": 5e-06, "epoch": 2.139446036294174, "percentage": 71.52, "elapsed_time": "8:33:45", "remaining_time": "3:24:35"}
59
+ {"current_steps": 570, "total_steps": 783, "loss": 0.5239, "lr": 5e-06, "epoch": 2.177650429799427, "percentage": 72.8, "elapsed_time": "8:42:45", "remaining_time": "3:15:20"}
60
+ {"current_steps": 580, "total_steps": 783, "loss": 0.5222, "lr": 5e-06, "epoch": 2.21585482330468, "percentage": 74.07, "elapsed_time": "8:51:44", "remaining_time": "3:06:06"}
61
+ {"current_steps": 590, "total_steps": 783, "loss": 0.5279, "lr": 5e-06, "epoch": 2.2540592168099334, "percentage": 75.35, "elapsed_time": "9:00:42", "remaining_time": "2:56:52"}
62
+ {"current_steps": 600, "total_steps": 783, "loss": 0.5189, "lr": 5e-06, "epoch": 2.292263610315186, "percentage": 76.63, "elapsed_time": "9:09:40", "remaining_time": "2:47:38"}
63
+ {"current_steps": 610, "total_steps": 783, "loss": 0.5245, "lr": 5e-06, "epoch": 2.3304680038204393, "percentage": 77.91, "elapsed_time": "9:18:39", "remaining_time": "2:38:26"}
64
+ {"current_steps": 620, "total_steps": 783, "loss": 0.5204, "lr": 5e-06, "epoch": 2.3686723973256925, "percentage": 79.18, "elapsed_time": "9:27:38", "remaining_time": "2:29:14"}
65
+ {"current_steps": 630, "total_steps": 783, "loss": 0.5136, "lr": 5e-06, "epoch": 2.4068767908309456, "percentage": 80.46, "elapsed_time": "9:36:35", "remaining_time": "2:20:01"}
66
+ {"current_steps": 640, "total_steps": 783, "loss": 0.5158, "lr": 5e-06, "epoch": 2.445081184336199, "percentage": 81.74, "elapsed_time": "9:45:33", "remaining_time": "2:10:50"}
67
+ {"current_steps": 650, "total_steps": 783, "loss": 0.526, "lr": 5e-06, "epoch": 2.4832855778414515, "percentage": 83.01, "elapsed_time": "9:54:31", "remaining_time": "2:01:39"}
68
+ {"current_steps": 660, "total_steps": 783, "loss": 0.5168, "lr": 5e-06, "epoch": 2.5214899713467047, "percentage": 84.29, "elapsed_time": "10:03:30", "remaining_time": "1:52:28"}
69
+ {"current_steps": 670, "total_steps": 783, "loss": 0.5161, "lr": 5e-06, "epoch": 2.559694364851958, "percentage": 85.57, "elapsed_time": "10:12:29", "remaining_time": "1:43:18"}
70
+ {"current_steps": 680, "total_steps": 783, "loss": 0.5249, "lr": 5e-06, "epoch": 2.597898758357211, "percentage": 86.85, "elapsed_time": "10:21:29", "remaining_time": "1:34:08"}
71
+ {"current_steps": 690, "total_steps": 783, "loss": 0.5151, "lr": 5e-06, "epoch": 2.6361031518624642, "percentage": 88.12, "elapsed_time": "10:30:28", "remaining_time": "1:24:58"}
72
+ {"current_steps": 700, "total_steps": 783, "loss": 0.5183, "lr": 5e-06, "epoch": 2.6743075453677174, "percentage": 89.4, "elapsed_time": "10:39:25", "remaining_time": "1:15:49"}
73
+ {"current_steps": 710, "total_steps": 783, "loss": 0.5063, "lr": 5e-06, "epoch": 2.7125119388729706, "percentage": 90.68, "elapsed_time": "10:48:24", "remaining_time": "1:06:40"}
74
+ {"current_steps": 720, "total_steps": 783, "loss": 0.5112, "lr": 5e-06, "epoch": 2.7507163323782233, "percentage": 91.95, "elapsed_time": "10:57:24", "remaining_time": "0:57:31"}
75
+ {"current_steps": 730, "total_steps": 783, "loss": 0.5163, "lr": 5e-06, "epoch": 2.7889207258834765, "percentage": 93.23, "elapsed_time": "11:06:23", "remaining_time": "0:48:22"}
76
+ {"current_steps": 740, "total_steps": 783, "loss": 0.5207, "lr": 5e-06, "epoch": 2.8271251193887297, "percentage": 94.51, "elapsed_time": "11:15:21", "remaining_time": "0:39:14"}
77
+ {"current_steps": 750, "total_steps": 783, "loss": 0.5102, "lr": 5e-06, "epoch": 2.865329512893983, "percentage": 95.79, "elapsed_time": "11:24:19", "remaining_time": "0:30:06"}
78
+ {"current_steps": 760, "total_steps": 783, "loss": 0.5149, "lr": 5e-06, "epoch": 2.903533906399236, "percentage": 97.06, "elapsed_time": "11:33:18", "remaining_time": "0:20:58"}
79
+ {"current_steps": 770, "total_steps": 783, "loss": 0.5115, "lr": 5e-06, "epoch": 2.9417382999044888, "percentage": 98.34, "elapsed_time": "11:42:17", "remaining_time": "0:11:51"}
80
+ {"current_steps": 780, "total_steps": 783, "loss": 0.5177, "lr": 5e-06, "epoch": 2.9799426934097424, "percentage": 99.62, "elapsed_time": "11:51:16", "remaining_time": "0:02:44"}