Hugging Face's logo

mlfoundations-dev
/
stackexchange_quant

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
sedrickkeh commited on
Commit
f391d35
·
verified ·
1 Parent(s): c98480f

Training in progress, epoch 2

Browse files
Files changed (5) hide show
  1. model-00001-of-00004.safetensors +1 -1
  2. model-00002-of-00004.safetensors +1 -1
  3. model-00003-of-00004.safetensors +1 -1
  4. model-00004-of-00004.safetensors +1 -1
  5. trainer_log.jsonl +5 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2db2a001906820854c0f4f2512114d1bbaf2d2b0e045b2376d1756a9247bd95a
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78e25da4ce788f077d6f3ebb3bee11f0a93b190903ad7f19c84773c3408571c3
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7960b489b818c441e6858177ff065b900be3afee69d320fce94dd04929494fbe
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6814bef8d54ac12fbed143f96b468610db3777c84b49a0569beaf9a461ae4cb
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:aee63f9861921732120a6f455cdb0481a55f2bd60ab783c24994a158aa4d54b3
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:136a15737d62951d4e41b2bafcff77c92bac05ba5b3f5433d7d193aa052e4dcc
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:21f9f5f6e81aa15fa63914db9c837615c35e35fa180a7596b4e77b7f8c68035d
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f48a078fe5272ba9ab1b17772f12b5b4c05be40ca1eaa4068e55e789d28be34
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -8,3 +8,8 @@
8
  {"current_steps": 70, "total_steps": 114, "loss": 0.8286, "lr": 5e-06, "epoch": 1.8360655737704918, "percentage": 61.4, "elapsed_time": "0:39:12", "remaining_time": "0:24:38"}
9
  {"current_steps": 76, "total_steps": 114, "eval_loss": 0.8515063524246216, "epoch": 1.9934426229508198, "percentage": 66.67, "elapsed_time": "0:42:58", "remaining_time": "0:21:29"}
10
  {"current_steps": 80, "total_steps": 114, "loss": 0.8792, "lr": 5e-06, "epoch": 2.098360655737705, "percentage": 70.18, "elapsed_time": "0:46:25", "remaining_time": "0:19:43"}
 
 
 
 
 
 
8
  {"current_steps": 70, "total_steps": 114, "loss": 0.8286, "lr": 5e-06, "epoch": 1.8360655737704918, "percentage": 61.4, "elapsed_time": "0:39:12", "remaining_time": "0:24:38"}
9
  {"current_steps": 76, "total_steps": 114, "eval_loss": 0.8515063524246216, "epoch": 1.9934426229508198, "percentage": 66.67, "elapsed_time": "0:42:58", "remaining_time": "0:21:29"}
10
  {"current_steps": 80, "total_steps": 114, "loss": 0.8792, "lr": 5e-06, "epoch": 2.098360655737705, "percentage": 70.18, "elapsed_time": "0:46:25", "remaining_time": "0:19:43"}
11
+ {"current_steps": 90, "total_steps": 114, "loss": 0.7768, "lr": 5e-06, "epoch": 2.360655737704918, "percentage": 78.95, "elapsed_time": "0:51:45", "remaining_time": "0:13:48"}
12
+ {"current_steps": 100, "total_steps": 114, "loss": 0.7699, "lr": 5e-06, "epoch": 2.6229508196721314, "percentage": 87.72, "elapsed_time": "0:57:07", "remaining_time": "0:07:59"}
13
+ {"current_steps": 110, "total_steps": 114, "loss": 0.771, "lr": 5e-06, "epoch": 2.8852459016393444, "percentage": 96.49, "elapsed_time": "1:02:29", "remaining_time": "0:02:16"}
14
+ {"current_steps": 114, "total_steps": 114, "eval_loss": 0.8435602784156799, "epoch": 2.9901639344262296, "percentage": 100.0, "elapsed_time": "1:06:34", "remaining_time": "0:00:00"}
15
+ {"current_steps": 114, "total_steps": 114, "epoch": 2.9901639344262296, "percentage": 100.0, "elapsed_time": "1:07:57", "remaining_time": "0:00:00"}