Hugging Face's logo

mlfoundations-dev
/
stackexchange_gardening

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
sedrickkeh commited on
Commit
7a7bcff
·
verified ·
1 Parent(s): 2af5a2a

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:ccde6f43b991f567677f3f2d0056f57bfdcd52af45086b10c57d26a84a1e7b64
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a5dc455f031b8640f95756a1d4635f570a1433eabe5894fd74477705e8d9b9c
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:b5d6dda3db36c038b86e21d59a0beff3c780127473b1f288c10492e1b3a37c93
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a01edd24b0ed1a795962f32901adb327b40a7e1e3f66b2860c8385c9de9c7a7
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c6458d8f15f66a0e3e86da0c454b85063a3884e2fe424387fc968e44c2730c6
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f3ed9c880a9b7c9a0173f05386787fd02b74a1278d088424df9ab12e3587f65
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:70000f79b947421367f2bfa8f6d74e862fb63f22b1f70bc7c9e28aaead7027d7
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f0e6bb713a6e66e549fe993e9ed24346427787f32077cfb6ea0c4b07893122b
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -1,3 +1,6 @@
1
  {"current_steps": 10, "total_steps": 63, "loss": 1.0795, "lr": 5e-06, "epoch": 0.47337278106508873, "percentage": 15.87, "elapsed_time": "0:05:24", "remaining_time": "0:28:37"}
2
  {"current_steps": 20, "total_steps": 63, "loss": 0.9536, "lr": 5e-06, "epoch": 0.9467455621301775, "percentage": 31.75, "elapsed_time": "0:10:39", "remaining_time": "0:22:54"}
3
  {"current_steps": 21, "total_steps": 63, "eval_loss": 0.914972722530365, "epoch": 0.9940828402366864, "percentage": 33.33, "elapsed_time": "0:11:28", "remaining_time": "0:22:57"}
 
 
 
 
1
  {"current_steps": 10, "total_steps": 63, "loss": 1.0795, "lr": 5e-06, "epoch": 0.47337278106508873, "percentage": 15.87, "elapsed_time": "0:05:24", "remaining_time": "0:28:37"}
2
  {"current_steps": 20, "total_steps": 63, "loss": 0.9536, "lr": 5e-06, "epoch": 0.9467455621301775, "percentage": 31.75, "elapsed_time": "0:10:39", "remaining_time": "0:22:54"}
3
  {"current_steps": 21, "total_steps": 63, "eval_loss": 0.914972722530365, "epoch": 0.9940828402366864, "percentage": 33.33, "elapsed_time": "0:11:28", "remaining_time": "0:22:57"}
4
+ {"current_steps": 30, "total_steps": 63, "loss": 0.9652, "lr": 5e-06, "epoch": 1.4201183431952662, "percentage": 47.62, "elapsed_time": "0:17:19", "remaining_time": "0:19:03"}
5
+ {"current_steps": 40, "total_steps": 63, "loss": 0.8564, "lr": 5e-06, "epoch": 1.893491124260355, "percentage": 63.49, "elapsed_time": "0:22:36", "remaining_time": "0:13:00"}
6
+ {"current_steps": 42, "total_steps": 63, "eval_loss": 0.8626062870025635, "epoch": 1.9881656804733727, "percentage": 66.67, "elapsed_time": "0:24:01", "remaining_time": "0:12:00"}