Hugging Face's logo

mlfoundations-dev
/
llama3-1_8b_4o_annotated_aops

Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
1
gsmyrnis commited on
Commit
680b314
·
verified ·
1 Parent(s): d1d6574

Training in progress, epoch 3

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 sha256:530fbc8499316cb126751dffc718b8351ad21041900a18be8516b023238c9026
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:233d90ff3fc03b1f34b6371af665e12f9af2b1a611854c0a97588886e3ddc9e5
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:d87aa0c84ca34ddca829cf604a89302133ce95a1bf5e8d80abd2ed52e8319e5d
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a7c49b63828ab136e75116e39ad427f224b2fa9c2f3f37683dccc7964a738f9
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:a4bd3660c4392caedb0976def27ff529b5167ad0387ced4c1469cf0dbf152033
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd6bd937733fb3ce0c62dc5d70a97c5ca08907579c9311aca6ca281710a6ab86
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:a8ebd84eea56ebc59c6efa18e4c55ff90a0035c4b863ac77e5fdccb8e263ffe4
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9c7546ca2ffe13afdac1e2b24b34ce3800e43d1f8fe1ad63e2a40b821909a68
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -3,3 +3,7 @@
3
  {"current_steps": 20, "total_steps": 51, "loss": 0.7874, "lr": 5e-06, "epoch": 1.1764705882352942, "percentage": 39.22, "elapsed_time": "0:03:16", "remaining_time": "0:05:04"}
4
  {"current_steps": 30, "total_steps": 51, "loss": 0.7508, "lr": 5e-06, "epoch": 1.7647058823529411, "percentage": 58.82, "elapsed_time": "0:04:15", "remaining_time": "0:02:58"}
5
  {"current_steps": 34, "total_steps": 51, "eval_loss": 0.7634365558624268, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:04:40", "remaining_time": "0:02:20"}
 
 
 
 
 
3
  {"current_steps": 20, "total_steps": 51, "loss": 0.7874, "lr": 5e-06, "epoch": 1.1764705882352942, "percentage": 39.22, "elapsed_time": "0:03:16", "remaining_time": "0:05:04"}
4
  {"current_steps": 30, "total_steps": 51, "loss": 0.7508, "lr": 5e-06, "epoch": 1.7647058823529411, "percentage": 58.82, "elapsed_time": "0:04:15", "remaining_time": "0:02:58"}
5
  {"current_steps": 34, "total_steps": 51, "eval_loss": 0.7634365558624268, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:04:40", "remaining_time": "0:02:20"}
6
+ {"current_steps": 40, "total_steps": 51, "loss": 0.7209, "lr": 5e-06, "epoch": 2.3529411764705883, "percentage": 78.43, "elapsed_time": "0:06:38", "remaining_time": "0:01:49"}
7
+ {"current_steps": 50, "total_steps": 51, "loss": 0.7022, "lr": 5e-06, "epoch": 2.9411764705882355, "percentage": 98.04, "elapsed_time": "0:07:36", "remaining_time": "0:00:09"}
8
+ {"current_steps": 51, "total_steps": 51, "eval_loss": 0.7526352405548096, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:09:13", "remaining_time": "0:00:00"}
9
+ {"current_steps": 51, "total_steps": 51, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:10:36", "remaining_time": "0:00:00"}