Hugging Face's logo

mlfoundations-dev
/
stackexchange_philosophy

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
sedrickkeh commited on
Commit
4b5eb63
·
verified ·
1 Parent(s): 5804482

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 sha256:67561d34d338d45c7656bc76f638f270219ae907ebef471c0eefb3d0deb46fcd
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e41a153efbf7014e9cc426096c717375a4dd829ae1ac8b830edd217831a63d5c
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:e9a6e0279ccc6468a1e19cb2f0b1d312c71f238fd8ba5a5747a262d6a1ecbe8a
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d61e73b4d8ff24e13a5a4a0aced993c9ffb5f5fb8b3a16f8a5a386edb0e35ce
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ae0a1a55248044ce5832672f833e31107707b270bb9be07a2be90e3fdb0a863
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:512cac94484c9cc6fc92680286d357e1f4b50ec028eb94f6fe83c817feb4f60e
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:bab7779fc78b5f589e37159514751f739d987969dd0b312a48ef4306fd2cb663
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4a8b3993d06556d08bd78b73e6a529b87923017c1958169076d86a4ebdc6e56
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -2,3 +2,7 @@
2
  {"current_steps": 20, "total_steps": 99, "loss": 1.1135, "lr": 5e-06, "epoch": 0.6060606060606061, "percentage": 20.2, "elapsed_time": "0:10:48", "remaining_time": "0:42:40"}
3
  {"current_steps": 30, "total_steps": 99, "loss": 1.0698, "lr": 5e-06, "epoch": 0.9090909090909091, "percentage": 30.3, "elapsed_time": "0:16:08", "remaining_time": "0:37:07"}
4
  {"current_steps": 33, "total_steps": 99, "eval_loss": 1.0388543605804443, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:18:06", "remaining_time": "0:36:13"}
 
 
 
 
 
2
  {"current_steps": 20, "total_steps": 99, "loss": 1.1135, "lr": 5e-06, "epoch": 0.6060606060606061, "percentage": 20.2, "elapsed_time": "0:10:48", "remaining_time": "0:42:40"}
3
  {"current_steps": 30, "total_steps": 99, "loss": 1.0698, "lr": 5e-06, "epoch": 0.9090909090909091, "percentage": 30.3, "elapsed_time": "0:16:08", "remaining_time": "0:37:07"}
4
  {"current_steps": 33, "total_steps": 99, "eval_loss": 1.0388543605804443, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:18:06", "remaining_time": "0:36:13"}
5
+ {"current_steps": 40, "total_steps": 99, "loss": 1.0194, "lr": 5e-06, "epoch": 1.2121212121212122, "percentage": 40.4, "elapsed_time": "0:23:12", "remaining_time": "0:34:13"}
6
+ {"current_steps": 50, "total_steps": 99, "loss": 0.992, "lr": 5e-06, "epoch": 1.5151515151515151, "percentage": 50.51, "elapsed_time": "0:28:33", "remaining_time": "0:27:59"}
7
+ {"current_steps": 60, "total_steps": 99, "loss": 0.9788, "lr": 5e-06, "epoch": 1.8181818181818183, "percentage": 60.61, "elapsed_time": "0:33:54", "remaining_time": "0:22:02"}
8
+ {"current_steps": 66, "total_steps": 99, "eval_loss": 0.9927644729614258, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:37:30", "remaining_time": "0:18:45"}