Hugging Face's logo

mlfoundations-dev
/
stackexchange_hermeneutics

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
sedrickkeh commited on
Commit
2081cc6
·
verified ·
1 Parent(s): e03bcae

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 +4 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0578b34b1f59aaeab90a96c6e51a44687a06148a309fbde25255879c5f661801
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b23d3ca3908602b50aa3f2e6437da7f9b9c5f15fcb93761cac1773ec6485110
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:b47cceb204f18bf196dc9b6b680087b53b8a30e193e9857408ba4950cc86fdde
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f2072b661188afb39f1a9aaed6501a64b560b8a78241138711796b26c86bfa3
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5aa37a38b7600918c3879cecf3fc1e13d07fbf0f7b3cfb711d3c7eee370e0950
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1435d48b76817b826795edf405c0fb0d41a885446c6bb8fd369e5bddf41863a
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:dbc890792e9e9066c096ee7cfb0de0f1434f0f11a4215889a3bd4ff8eb0bc064
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fce827aace0cf741f8c40211b94ebe325b401c473fd5259d51d2cbcfa2995fb1
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -2,3 +2,7 @@
2
  {"current_steps": 20, "total_steps": 93, "loss": 1.1085, "lr": 5e-06, "epoch": 0.64, "percentage": 21.51, "elapsed_time": "0:10:40", "remaining_time": "0:38:57"}
3
  {"current_steps": 30, "total_steps": 93, "loss": 1.0621, "lr": 5e-06, "epoch": 0.96, "percentage": 32.26, "elapsed_time": "0:15:57", "remaining_time": "0:33:30"}
4
  {"current_steps": 31, "total_steps": 93, "eval_loss": 1.0408542156219482, "epoch": 0.992, "percentage": 33.33, "elapsed_time": "0:16:59", "remaining_time": "0:33:59"}
 
 
 
 
 
2
  {"current_steps": 20, "total_steps": 93, "loss": 1.1085, "lr": 5e-06, "epoch": 0.64, "percentage": 21.51, "elapsed_time": "0:10:40", "remaining_time": "0:38:57"}
3
  {"current_steps": 30, "total_steps": 93, "loss": 1.0621, "lr": 5e-06, "epoch": 0.96, "percentage": 32.26, "elapsed_time": "0:15:57", "remaining_time": "0:33:30"}
4
  {"current_steps": 31, "total_steps": 93, "eval_loss": 1.0408542156219482, "epoch": 0.992, "percentage": 33.33, "elapsed_time": "0:16:59", "remaining_time": "0:33:59"}
5
+ {"current_steps": 40, "total_steps": 93, "loss": 1.0841, "lr": 5e-06, "epoch": 1.28, "percentage": 43.01, "elapsed_time": "0:22:49", "remaining_time": "0:30:14"}
6
+ {"current_steps": 50, "total_steps": 93, "loss": 0.9873, "lr": 5e-06, "epoch": 1.6, "percentage": 53.76, "elapsed_time": "0:28:05", "remaining_time": "0:24:09"}
7
+ {"current_steps": 60, "total_steps": 93, "loss": 0.9711, "lr": 5e-06, "epoch": 1.92, "percentage": 64.52, "elapsed_time": "0:33:21", "remaining_time": "0:18:20"}
8
+ {"current_steps": 62, "total_steps": 93, "eval_loss": 0.9961642026901245, "epoch": 1.984, "percentage": 66.67, "elapsed_time": "0:35:00", "remaining_time": "0:17:30"}