sedrickkeh commited on
Commit
d8e4486
·
verified ·
1 Parent(s): 373558a

Training in progress, epoch 2

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d05c4f2f9568ce7150879c361833758927ea18fa5d4a79f1600582747541841
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33c68f9d65404390696855684dce72dcaeb19973c2f318b84219b81c0f687855
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:42f76765cefcb79ae745438ac4f11c4f58274ab962fb1a56a90ee6a5828ed6d5
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:806f85eae417b93b925ff1ee2b480337c7f8ff8bf73a244a1333ba3f7c75c00b
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:c76a7f5c4e8e605647b08d6c5a9cc9f1ca49a619c7a812e97c0eebeebe6902e7
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e67da5bf03f764e3a5573488fe5594a1b258df9ee333b78c79d688f3df36cd0
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:ec9f55e0dcccd3c7d705d4f2e3ce4623cb161f31a05963fdc1b0fc6040226664
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1418314047f8cec7d87b3d017875d9a293eb734e241297c047e48c7870d06186
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -54,3 +54,29 @@
54
  {"current_steps": 530, "total_steps": 804, "loss": 0.6846, "lr": 5e-06, "epoch": 1.9721059972105999, "percentage": 65.92, "elapsed_time": "8:36:09", "remaining_time": "4:26:50"}
55
  {"current_steps": 537, "total_steps": 804, "eval_loss": 0.7252578735351562, "epoch": 1.99814039981404, "percentage": 66.79, "elapsed_time": "8:47:53", "remaining_time": "4:22:28"}
56
  {"current_steps": 540, "total_steps": 804, "loss": 0.6895, "lr": 5e-06, "epoch": 2.01022780102278, "percentage": 67.16, "elapsed_time": "8:51:47", "remaining_time": "4:19:59"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
54
  {"current_steps": 530, "total_steps": 804, "loss": 0.6846, "lr": 5e-06, "epoch": 1.9721059972105999, "percentage": 65.92, "elapsed_time": "8:36:09", "remaining_time": "4:26:50"}
55
  {"current_steps": 537, "total_steps": 804, "eval_loss": 0.7252578735351562, "epoch": 1.99814039981404, "percentage": 66.79, "elapsed_time": "8:47:53", "remaining_time": "4:22:28"}
56
  {"current_steps": 540, "total_steps": 804, "loss": 0.6895, "lr": 5e-06, "epoch": 2.01022780102278, "percentage": 67.16, "elapsed_time": "8:51:47", "remaining_time": "4:19:59"}
57
+ {"current_steps": 550, "total_steps": 804, "loss": 0.633, "lr": 5e-06, "epoch": 2.0474198047419803, "percentage": 68.41, "elapsed_time": "9:01:24", "remaining_time": "4:10:01"}
58
+ {"current_steps": 560, "total_steps": 804, "loss": 0.6306, "lr": 5e-06, "epoch": 2.084611808461181, "percentage": 69.65, "elapsed_time": "9:11:00", "remaining_time": "4:00:05"}
59
+ {"current_steps": 570, "total_steps": 804, "loss": 0.6268, "lr": 5e-06, "epoch": 2.121803812180381, "percentage": 70.9, "elapsed_time": "9:20:37", "remaining_time": "3:50:08"}
60
+ {"current_steps": 580, "total_steps": 804, "loss": 0.6236, "lr": 5e-06, "epoch": 2.1589958158995817, "percentage": 72.14, "elapsed_time": "9:30:14", "remaining_time": "3:40:13"}
61
+ {"current_steps": 590, "total_steps": 804, "loss": 0.6347, "lr": 5e-06, "epoch": 2.196187819618782, "percentage": 73.38, "elapsed_time": "9:39:51", "remaining_time": "3:30:19"}
62
+ {"current_steps": 600, "total_steps": 804, "loss": 0.6303, "lr": 5e-06, "epoch": 2.2333798233379825, "percentage": 74.63, "elapsed_time": "9:49:28", "remaining_time": "3:20:25"}
63
+ {"current_steps": 610, "total_steps": 804, "loss": 0.6397, "lr": 5e-06, "epoch": 2.2705718270571826, "percentage": 75.87, "elapsed_time": "9:59:05", "remaining_time": "3:10:31"}
64
+ {"current_steps": 620, "total_steps": 804, "loss": 0.6314, "lr": 5e-06, "epoch": 2.3077638307763833, "percentage": 77.11, "elapsed_time": "10:08:43", "remaining_time": "3:00:39"}
65
+ {"current_steps": 630, "total_steps": 804, "loss": 0.6333, "lr": 5e-06, "epoch": 2.3449558344955834, "percentage": 78.36, "elapsed_time": "10:18:21", "remaining_time": "2:50:47"}
66
+ {"current_steps": 640, "total_steps": 804, "loss": 0.635, "lr": 5e-06, "epoch": 2.3821478382147836, "percentage": 79.6, "elapsed_time": "10:27:58", "remaining_time": "2:40:55"}
67
+ {"current_steps": 650, "total_steps": 804, "loss": 0.6327, "lr": 5e-06, "epoch": 2.419339841933984, "percentage": 80.85, "elapsed_time": "10:37:35", "remaining_time": "2:31:03"}
68
+ {"current_steps": 660, "total_steps": 804, "loss": 0.6325, "lr": 5e-06, "epoch": 2.4565318456531844, "percentage": 82.09, "elapsed_time": "10:47:13", "remaining_time": "2:21:12"}
69
+ {"current_steps": 670, "total_steps": 804, "loss": 0.6304, "lr": 5e-06, "epoch": 2.493723849372385, "percentage": 83.33, "elapsed_time": "10:56:50", "remaining_time": "2:11:22"}
70
+ {"current_steps": 680, "total_steps": 804, "loss": 0.6291, "lr": 5e-06, "epoch": 2.530915853091585, "percentage": 84.58, "elapsed_time": "11:06:27", "remaining_time": "2:01:31"}
71
+ {"current_steps": 690, "total_steps": 804, "loss": 0.6326, "lr": 5e-06, "epoch": 2.568107856810786, "percentage": 85.82, "elapsed_time": "11:16:05", "remaining_time": "1:51:42"}
72
+ {"current_steps": 700, "total_steps": 804, "loss": 0.6359, "lr": 5e-06, "epoch": 2.605299860529986, "percentage": 87.06, "elapsed_time": "11:25:42", "remaining_time": "1:41:52"}
73
+ {"current_steps": 710, "total_steps": 804, "loss": 0.6323, "lr": 5e-06, "epoch": 2.6424918642491866, "percentage": 88.31, "elapsed_time": "11:35:20", "remaining_time": "1:32:03"}
74
+ {"current_steps": 720, "total_steps": 804, "loss": 0.6361, "lr": 5e-06, "epoch": 2.6796838679683868, "percentage": 89.55, "elapsed_time": "11:44:57", "remaining_time": "1:22:14"}
75
+ {"current_steps": 730, "total_steps": 804, "loss": 0.6354, "lr": 5e-06, "epoch": 2.716875871687587, "percentage": 90.8, "elapsed_time": "11:54:35", "remaining_time": "1:12:26"}
76
+ {"current_steps": 740, "total_steps": 804, "loss": 0.6385, "lr": 5e-06, "epoch": 2.7540678754067875, "percentage": 92.04, "elapsed_time": "12:04:14", "remaining_time": "1:02:38"}
77
+ {"current_steps": 750, "total_steps": 804, "loss": 0.6377, "lr": 5e-06, "epoch": 2.791259879125988, "percentage": 93.28, "elapsed_time": "12:13:52", "remaining_time": "0:52:50"}
78
+ {"current_steps": 760, "total_steps": 804, "loss": 0.6379, "lr": 5e-06, "epoch": 2.8284518828451883, "percentage": 94.53, "elapsed_time": "12:23:29", "remaining_time": "0:43:02"}
79
+ {"current_steps": 770, "total_steps": 804, "loss": 0.635, "lr": 5e-06, "epoch": 2.8656438865643885, "percentage": 95.77, "elapsed_time": "12:33:07", "remaining_time": "0:33:15"}
80
+ {"current_steps": 780, "total_steps": 804, "loss": 0.6373, "lr": 5e-06, "epoch": 2.902835890283589, "percentage": 97.01, "elapsed_time": "12:42:45", "remaining_time": "0:23:28"}
81
+ {"current_steps": 790, "total_steps": 804, "loss": 0.6363, "lr": 5e-06, "epoch": 2.9400278940027893, "percentage": 98.26, "elapsed_time": "12:52:23", "remaining_time": "0:13:41"}
82
+ {"current_steps": 800, "total_steps": 804, "loss": 0.6343, "lr": 5e-06, "epoch": 2.97721989772199, "percentage": 99.5, "elapsed_time": "13:02:00", "remaining_time": "0:03:54"}