Hugging Face's logo

mlfoundations-dev
/
stackexchange_graphicdesign

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
sedrickkeh commited on
Commit
0ba3d43
·
verified ·
1 Parent(s): 1d572d1

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 +4 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8015009f2b9f4ace7096bc4ffc879680fc67b43da65fa0323d368ef162ff6c57
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b2e6b82dd51b7fc889d7ffa2ea34569f65fccae37f2f19139744b59808c1110
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45da64cb80c7f7c86314d9dc21f84fd4ab37fd677bcb19cc90cbcae8538a0e9d
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99d80b3fba0a3ef310c775b08e41ba87f3100ce11a108cd68f5625d7049fc0d6
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:12c247917deeb85f4689b9378319716f46f563beb36568acc5342d793136b10f
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40de64f112d990b76f51b6a0fdfc048b768115e749327177e5be14a0d378cd93
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4079837e07bf6ceee3ae879d7dd17a25b3d2063c4f28a659de56247abf01b478
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fff44652da551c55c6e192402fe1609c0ff5a1c2a46c2c65c68aeed40c3d5a39
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -2,3 +2,7 @@
2
  {"current_steps": 20, "total_steps": 87, "loss": 1.0305, "lr": 5e-06, "epoch": 0.6896551724137931, "percentage": 22.99, "elapsed_time": "0:10:45", "remaining_time": "0:36:03"}
3
  {"current_steps": 29, "total_steps": 87, "eval_loss": 0.966795027256012, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:15:57", "remaining_time": "0:31:55"}
4
  {"current_steps": 30, "total_steps": 87, "loss": 0.992, "lr": 5e-06, "epoch": 1.0344827586206897, "percentage": 34.48, "elapsed_time": "0:17:49", "remaining_time": "0:33:52"}
 
 
 
 
 
2
  {"current_steps": 20, "total_steps": 87, "loss": 1.0305, "lr": 5e-06, "epoch": 0.6896551724137931, "percentage": 22.99, "elapsed_time": "0:10:45", "remaining_time": "0:36:03"}
3
  {"current_steps": 29, "total_steps": 87, "eval_loss": 0.966795027256012, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:15:57", "remaining_time": "0:31:55"}
4
  {"current_steps": 30, "total_steps": 87, "loss": 0.992, "lr": 5e-06, "epoch": 1.0344827586206897, "percentage": 34.48, "elapsed_time": "0:17:49", "remaining_time": "0:33:52"}
5
+ {"current_steps": 40, "total_steps": 87, "loss": 0.9331, "lr": 5e-06, "epoch": 1.3793103448275863, "percentage": 45.98, "elapsed_time": "0:23:10", "remaining_time": "0:27:13"}
6
+ {"current_steps": 50, "total_steps": 87, "loss": 0.9029, "lr": 5e-06, "epoch": 1.7241379310344827, "percentage": 57.47, "elapsed_time": "0:28:31", "remaining_time": "0:21:06"}
7
+ {"current_steps": 58, "total_steps": 87, "eval_loss": 0.8883161544799805, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:33:08", "remaining_time": "0:16:34"}
8
+ {"current_steps": 60, "total_steps": 87, "loss": 0.879, "lr": 5e-06, "epoch": 2.0689655172413794, "percentage": 68.97, "elapsed_time": "0:35:35", "remaining_time": "0:16:01"}