Hugging Face's logo

mlfoundations-dev
/
stackexchange_security

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
sedrickkeh commited on
Commit
3622230
·
verified ·
1 Parent(s): ed38a5e

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 +5 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2b844166ca39fc014326c0f433eaabc0bdabd5eb1d1a095a55acc6d9b4f0f61d
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a18a091e7409d5b77ee7d0dbb3ccc3b009d78eb4e229b31ab25e3cbfe9462a2
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:eeb70eb421c94a2e230332fb722c266911d9d21f90ce89d2e5fe49f15d066ed5
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fccf1cfd9058e28f3e5cececa52c7bd216b79ea30a01f7ce5a3b38d9a6d6b557
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3bf05b3257fa6935e1990712cb041de4a25c676a909ca417f97c083c75c1d835
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d471b2107e5e846619bf055b0b49baab4844f6f2d7199fd87b53ebea7d320b5a
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:d2ce6b70ea3efb58647c0e9d472cbe4ae3071f6a9fe20f9a575240ad44d5661d
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24a6214f3de321dda498ef49bae142821cd6f05013f5e92a65f4e5338902ed07
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -2,3 +2,8 @@
2
  {"current_steps": 20, "total_steps": 105, "loss": 1.0785, "lr": 5e-06, "epoch": 0.5653710247349824, "percentage": 19.05, "elapsed_time": "0:10:44", "remaining_time": "0:45:38"}
3
  {"current_steps": 30, "total_steps": 105, "loss": 1.0426, "lr": 5e-06, "epoch": 0.8480565371024735, "percentage": 28.57, "elapsed_time": "0:16:03", "remaining_time": "0:40:08"}
4
  {"current_steps": 35, "total_steps": 105, "eval_loss": 1.022178053855896, "epoch": 0.9893992932862191, "percentage": 33.33, "elapsed_time": "0:19:15", "remaining_time": "0:38:31"}
 
 
 
 
 
 
2
  {"current_steps": 20, "total_steps": 105, "loss": 1.0785, "lr": 5e-06, "epoch": 0.5653710247349824, "percentage": 19.05, "elapsed_time": "0:10:44", "remaining_time": "0:45:38"}
3
  {"current_steps": 30, "total_steps": 105, "loss": 1.0426, "lr": 5e-06, "epoch": 0.8480565371024735, "percentage": 28.57, "elapsed_time": "0:16:03", "remaining_time": "0:40:08"}
4
  {"current_steps": 35, "total_steps": 105, "eval_loss": 1.022178053855896, "epoch": 0.9893992932862191, "percentage": 33.33, "elapsed_time": "0:19:15", "remaining_time": "0:38:31"}
5
+ {"current_steps": 40, "total_steps": 105, "loss": 1.0834, "lr": 5e-06, "epoch": 1.1342756183745584, "percentage": 38.1, "elapsed_time": "0:22:59", "remaining_time": "0:37:21"}
6
+ {"current_steps": 50, "total_steps": 105, "loss": 0.9727, "lr": 5e-06, "epoch": 1.4169611307420495, "percentage": 47.62, "elapsed_time": "0:28:19", "remaining_time": "0:31:09"}
7
+ {"current_steps": 60, "total_steps": 105, "loss": 0.9609, "lr": 5e-06, "epoch": 1.6996466431095407, "percentage": 57.14, "elapsed_time": "0:33:39", "remaining_time": "0:25:14"}
8
+ {"current_steps": 70, "total_steps": 105, "loss": 0.953, "lr": 5e-06, "epoch": 1.9823321554770317, "percentage": 66.67, "elapsed_time": "0:38:59", "remaining_time": "0:19:29"}
9
+ {"current_steps": 70, "total_steps": 105, "eval_loss": 0.9813353419303894, "epoch": 1.9823321554770317, "percentage": 66.67, "elapsed_time": "0:39:38", "remaining_time": "0:19:49"}