sedrickkeh commited on
Commit
46da08f
·
verified ·
1 Parent(s): 1274030

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:cb71e9e206d74cb0560ade3ec6a3320b425a05817a8eeedd0b24925d630f73a2
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e950e3acf2df9cdd3c7ddf9fd8d8dd70935bae0edae2501098a0a9bde1b19e5
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:db74c4b849c8716f8b2fe3ff5e1030724394f3031f5eea883ba24b57e6cb3a38
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bd8f2394cdae5914fddaf278524a64dc385273326da67884e73d333a01d0646
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c75392e382f2ca70345fbfe62315fea52cbc4d38765297c995fddbdf73b9f0f4
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dbd528859e3b01fa2e4e8bbe872308ca440ee785ac5cf6bbf90d60696e8c912
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:48059600fa52647790f5c7a364e91e7902d5c9ba034329ad6fd017b76ca0d942
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11a4950177fdc5ce016fba04c386a442c8d969e78958f1a63613264dd0b4fe09
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -16,3 +16,18 @@
16
  {"current_steps": 16, "total_steps": 45, "loss": 0.9603, "lr": 8.247240241650918e-06, "epoch": 1.032, "percentage": 35.56, "elapsed_time": "0:18:35", "remaining_time": "0:33:42"}
17
  {"current_steps": 17, "total_steps": 45, "loss": 0.7434, "lr": 7.938926261462366e-06, "epoch": 1.096, "percentage": 37.78, "elapsed_time": "0:19:39", "remaining_time": "0:32:22"}
18
  {"current_steps": 18, "total_steps": 45, "loss": 0.5232, "lr": 7.612492823579744e-06, "epoch": 1.16, "percentage": 40.0, "elapsed_time": "0:20:47", "remaining_time": "0:31:11"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
16
  {"current_steps": 16, "total_steps": 45, "loss": 0.9603, "lr": 8.247240241650918e-06, "epoch": 1.032, "percentage": 35.56, "elapsed_time": "0:18:35", "remaining_time": "0:33:42"}
17
  {"current_steps": 17, "total_steps": 45, "loss": 0.7434, "lr": 7.938926261462366e-06, "epoch": 1.096, "percentage": 37.78, "elapsed_time": "0:19:39", "remaining_time": "0:32:22"}
18
  {"current_steps": 18, "total_steps": 45, "loss": 0.5232, "lr": 7.612492823579744e-06, "epoch": 1.16, "percentage": 40.0, "elapsed_time": "0:20:47", "remaining_time": "0:31:11"}
19
+ {"current_steps": 19, "total_steps": 45, "loss": 0.6181, "lr": 7.269952498697734e-06, "epoch": 1.224, "percentage": 42.22, "elapsed_time": "0:22:01", "remaining_time": "0:30:08"}
20
+ {"current_steps": 20, "total_steps": 45, "loss": 0.5387, "lr": 6.913417161825449e-06, "epoch": 1.288, "percentage": 44.44, "elapsed_time": "0:23:03", "remaining_time": "0:28:49"}
21
+ {"current_steps": 21, "total_steps": 45, "loss": 0.6179, "lr": 6.545084971874738e-06, "epoch": 1.3519999999999999, "percentage": 46.67, "elapsed_time": "0:24:13", "remaining_time": "0:27:41"}
22
+ {"current_steps": 22, "total_steps": 45, "loss": 0.5751, "lr": 6.1672268192795285e-06, "epoch": 1.416, "percentage": 48.89, "elapsed_time": "0:25:24", "remaining_time": "0:26:34"}
23
+ {"current_steps": 23, "total_steps": 45, "loss": 0.5951, "lr": 5.782172325201155e-06, "epoch": 1.48, "percentage": 51.11, "elapsed_time": "0:26:30", "remaining_time": "0:25:21"}
24
+ {"current_steps": 24, "total_steps": 45, "loss": 0.5711, "lr": 5.392295478639226e-06, "epoch": 1.544, "percentage": 53.33, "elapsed_time": "0:27:30", "remaining_time": "0:24:04"}
25
+ {"current_steps": 25, "total_steps": 45, "loss": 0.6038, "lr": 5e-06, "epoch": 1.608, "percentage": 55.56, "elapsed_time": "0:28:39", "remaining_time": "0:22:55"}
26
+ {"current_steps": 26, "total_steps": 45, "loss": 0.6156, "lr": 4.6077045213607765e-06, "epoch": 1.6720000000000002, "percentage": 57.78, "elapsed_time": "0:29:37", "remaining_time": "0:21:38"}
27
+ {"current_steps": 27, "total_steps": 45, "loss": 0.5486, "lr": 4.217827674798845e-06, "epoch": 1.736, "percentage": 60.0, "elapsed_time": "0:30:44", "remaining_time": "0:20:29"}
28
+ {"current_steps": 28, "total_steps": 45, "loss": 0.5681, "lr": 3.832773180720475e-06, "epoch": 1.8, "percentage": 62.22, "elapsed_time": "0:31:41", "remaining_time": "0:19:14"}
29
+ {"current_steps": 29, "total_steps": 45, "loss": 0.5366, "lr": 3.4549150281252635e-06, "epoch": 1.8639999999999999, "percentage": 64.44, "elapsed_time": "0:32:39", "remaining_time": "0:18:01"}
30
+ {"current_steps": 30, "total_steps": 45, "loss": 0.6139, "lr": 3.0865828381745515e-06, "epoch": 1.928, "percentage": 66.67, "elapsed_time": "0:33:40", "remaining_time": "0:16:50"}
31
+ {"current_steps": 31, "total_steps": 45, "loss": 0.8237, "lr": 2.7300475013022666e-06, "epoch": 1.992, "percentage": 68.89, "elapsed_time": "0:34:44", "remaining_time": "0:15:41"}
32
+ {"current_steps": 32, "total_steps": 45, "loss": 0.5648, "lr": 2.387507176420256e-06, "epoch": 2.064, "percentage": 71.11, "elapsed_time": "0:36:56", "remaining_time": "0:15:00"}
33
+ {"current_steps": 33, "total_steps": 45, "loss": 0.514, "lr": 2.061073738537635e-06, "epoch": 2.128, "percentage": 73.33, "elapsed_time": "0:37:47", "remaining_time": "0:13:44"}