Hugging Face's logo

mlfoundations-dev
/
stackexchange_chemistry

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
sedrickkeh commited on
Commit
4829bf9
·
verified ·
1 Parent(s): 0c6a0e5

Training in progress, epoch 1

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 +4 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d5f2b64fa4dbad95b5d57c40907971a7cefe2db3c8be57a6dd66c02dcaa630d
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef559fe14872235f288d3a6dbd87f7fe34ef25da105279d10c918e4a9f33a9bc
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b1eccf9e488e4338d9422e12e5a21d8688f840061aa860bca696bdc897495d2
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30005d62ced52e18cbbc5f0bb380aa0c48f1f92c02458b717ed012e53c94d91f
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9733e9eab271990546ec883c998ae4c100cbc7033ef012fd1bca70eb6deb3dc3
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af7b7572c4ccb3645d9ca6955e2e228ef5deb8fcf26d499f62aeb5e9dbc77ec6
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:b000cf42d0ed48fa0572a5eeadda223f7443c5dbde62c9a5c7349e616e5165e0
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e4b4f78b13c5837db1e2ea7ba3fff56a5d540e76fef722a916af455dbed72ad
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -2,3 +2,7 @@
2
  {"current_steps": 20, "total_steps": 90, "loss": 0.9054, "lr": 5e-06, "epoch": 0.6477732793522267, "percentage": 22.22, "elapsed_time": "0:19:11", "remaining_time": "1:07:10"}
3
  {"current_steps": 30, "total_steps": 90, "loss": 0.8668, "lr": 5e-06, "epoch": 0.97165991902834, "percentage": 33.33, "elapsed_time": "0:28:44", "remaining_time": "0:57:29"}
4
  {"current_steps": 30, "total_steps": 90, "eval_loss": 0.8556345701217651, "epoch": 0.97165991902834, "percentage": 33.33, "elapsed_time": "0:29:31", "remaining_time": "0:59:03"}
 
 
 
 
 
2
  {"current_steps": 20, "total_steps": 90, "loss": 0.9054, "lr": 5e-06, "epoch": 0.6477732793522267, "percentage": 22.22, "elapsed_time": "0:19:11", "remaining_time": "1:07:10"}
3
  {"current_steps": 30, "total_steps": 90, "loss": 0.8668, "lr": 5e-06, "epoch": 0.97165991902834, "percentage": 33.33, "elapsed_time": "0:28:44", "remaining_time": "0:57:29"}
4
  {"current_steps": 30, "total_steps": 90, "eval_loss": 0.8556345701217651, "epoch": 0.97165991902834, "percentage": 33.33, "elapsed_time": "0:29:31", "remaining_time": "0:59:03"}
5
+ {"current_steps": 40, "total_steps": 90, "loss": 0.8875, "lr": 5e-06, "epoch": 1.3157894736842106, "percentage": 44.44, "elapsed_time": "0:39:57", "remaining_time": "0:49:56"}
6
+ {"current_steps": 50, "total_steps": 90, "loss": 0.8022, "lr": 5e-06, "epoch": 1.639676113360324, "percentage": 55.56, "elapsed_time": "0:49:30", "remaining_time": "0:39:36"}
7
+ {"current_steps": 60, "total_steps": 90, "loss": 0.7929, "lr": 5e-06, "epoch": 1.9635627530364372, "percentage": 66.67, "elapsed_time": "0:59:03", "remaining_time": "0:29:31"}
8
+ {"current_steps": 60, "total_steps": 90, "eval_loss": 0.8138453960418701, "epoch": 1.9635627530364372, "percentage": 66.67, "elapsed_time": "1:00:02", "remaining_time": "0:30:01"}