Hugging Face's logo

mlfoundations-dev
/
metamath_seeding_stackexchange_codegolf

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
sedrickkeh commited on
Commit
b9cbea2
·
verified ·
1 Parent(s): 95e46e6

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:e448ff4b6255e156e8756d612f5a56b77e9851538f1c7c6dbd36f14f6911c7fd
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce998d31569013797ccaa06a2d3177d918b48769cfd46f5b372f6d8b6a4e155c
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5898e4733937500ec40a99614c031feea114947b8274730dce5532f225842a3c
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:346bf3bd0855793f17544838bf70bceb7a176c9898851099261cb9717f0187b7
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b65f13ff248a98e5832534def0ff31f0a775b954228c373071db1995370f963
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c52e406573dd054a8eb754a42cd69f431ff3a92a67d53e78199b92763673920
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:057f3c47179b46d19fab2e9eacbb90a1cf855de2c83419616de1b7cb381c28c0
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3789d1708d0e94ed215418913d158e888bc8632e32e60d56dd3c99d5085555ff
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -2,3 +2,6 @@
2
  {"current_steps": 20, "total_steps": 81, "loss": 1.2523, "lr": 5e-06, "epoch": 0.7207207207207207, "percentage": 24.69, "elapsed_time": "0:19:07", "remaining_time": "0:58:20"}
3
  {"current_steps": 27, "total_steps": 81, "eval_loss": 1.189139485359192, "epoch": 0.972972972972973, "percentage": 33.33, "elapsed_time": "0:26:32", "remaining_time": "0:53:05"}
4
  {"current_steps": 30, "total_steps": 81, "loss": 1.3046, "lr": 5e-06, "epoch": 1.0990990990990992, "percentage": 37.04, "elapsed_time": "0:30:21", "remaining_time": "0:51:36"}
 
 
 
 
2
  {"current_steps": 20, "total_steps": 81, "loss": 1.2523, "lr": 5e-06, "epoch": 0.7207207207207207, "percentage": 24.69, "elapsed_time": "0:19:07", "remaining_time": "0:58:20"}
3
  {"current_steps": 27, "total_steps": 81, "eval_loss": 1.189139485359192, "epoch": 0.972972972972973, "percentage": 33.33, "elapsed_time": "0:26:32", "remaining_time": "0:53:05"}
4
  {"current_steps": 30, "total_steps": 81, "loss": 1.3046, "lr": 5e-06, "epoch": 1.0990990990990992, "percentage": 37.04, "elapsed_time": "0:30:21", "remaining_time": "0:51:36"}
5
+ {"current_steps": 40, "total_steps": 81, "loss": 1.1666, "lr": 5e-06, "epoch": 1.4594594594594594, "percentage": 49.38, "elapsed_time": "0:39:53", "remaining_time": "0:40:53"}
6
+ {"current_steps": 50, "total_steps": 81, "loss": 1.1629, "lr": 5e-06, "epoch": 1.8198198198198199, "percentage": 61.73, "elapsed_time": "0:49:25", "remaining_time": "0:30:38"}
7
+ {"current_steps": 54, "total_steps": 81, "eval_loss": 1.148915410041809, "epoch": 1.9639639639639639, "percentage": 66.67, "elapsed_time": "0:54:11", "remaining_time": "0:27:05"}