Hugging Face's logo

mlfoundations-dev
/
llama3-1_8b_mlfoundations-dev-stackexchange_scicomp

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
EtashGuha commited on
Commit
e50bcdf
·
verified ·
1 Parent(s): 2dbf74d

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 +3 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ebf5887eff71fdb22f0d0df5597546ec7943d72b3dedf0c1c90bc9755171a4e
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12a45bf73f7507c00fb97b49230faa7f05cecf64bb10f8f2b84c8df0f127e810
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c798cc8a320fb3079e535fcf5b1e1ca491e6f2a563d357f20005c549be8c1dd
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ce5c840eccfba1afe02a384ecc57739e49699cc310c1cf739939dc8566d122e
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a229d1561817ae593784ad225b5972e52ad97c6a7db3040aa0676d6fb780432
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbb7961350825f458cc1ab3fbb40f99bc838de984fef1ae4c5665c58cbc95f80
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:64dc37eff34bb3de5be5e2a9131d2bf73cce402c112fd4426759d4654516ad20
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d285feb4655416a684face504d0547402b0dc94c3db8c2b6a0c0c9b83026768
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -1,3 +1,6 @@
1
  {"current_steps": 10, "total_steps": 72, "loss": 1.0638, "lr": 5e-06, "epoch": 0.41025641025641024, "percentage": 13.89, "elapsed_time": "0:26:01", "remaining_time": "2:41:23"}
2
  {"current_steps": 20, "total_steps": 72, "loss": 0.9425, "lr": 5e-06, "epoch": 0.8205128205128205, "percentage": 27.78, "elapsed_time": "0:52:00", "remaining_time": "2:15:14"}
3
  {"current_steps": 24, "total_steps": 72, "eval_loss": 0.915921151638031, "epoch": 0.9846153846153847, "percentage": 33.33, "elapsed_time": "1:04:39", "remaining_time": "2:09:19"}
 
 
 
 
1
  {"current_steps": 10, "total_steps": 72, "loss": 1.0638, "lr": 5e-06, "epoch": 0.41025641025641024, "percentage": 13.89, "elapsed_time": "0:26:01", "remaining_time": "2:41:23"}
2
  {"current_steps": 20, "total_steps": 72, "loss": 0.9425, "lr": 5e-06, "epoch": 0.8205128205128205, "percentage": 27.78, "elapsed_time": "0:52:00", "remaining_time": "2:15:14"}
3
  {"current_steps": 24, "total_steps": 72, "eval_loss": 0.915921151638031, "epoch": 0.9846153846153847, "percentage": 33.33, "elapsed_time": "1:04:39", "remaining_time": "2:09:19"}
4
+ {"current_steps": 30, "total_steps": 72, "loss": 0.8961, "lr": 5e-06, "epoch": 1.2307692307692308, "percentage": 41.67, "elapsed_time": "1:20:37", "remaining_time": "1:52:52"}
5
+ {"current_steps": 40, "total_steps": 72, "loss": 0.8596, "lr": 5e-06, "epoch": 1.641025641025641, "percentage": 55.56, "elapsed_time": "1:46:32", "remaining_time": "1:25:13"}
6
+ {"current_steps": 48, "total_steps": 72, "eval_loss": 0.8778233528137207, "epoch": 1.9692307692307693, "percentage": 66.67, "elapsed_time": "2:10:28", "remaining_time": "1:05:14"}