Hugging Face's logo

mlfoundations-dev
/
b2_math_embedding_0.3k

Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
1
ryanmarten commited on
Commit
f02e324
·
verified ·
1 Parent(s): bead1af

Training in progress, epoch 11

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 +7 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3beecb6061212022234242660df2b5b5f673040ac9ed8f46d0c3d75123ffef7a
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adff52076276dd52ed648f63e8f4bd62033cdd9064fe4ca50eadbbd82c9f1787
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bffb1a0bf1f4fed73c470bca244da217cee0e3203c3e58397412cb47cf7b6148
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32d6da13cda1bc2440ca757aefd05e451ffd18338e680d726f4ce6d038e6ef0d
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ec767f66d6f6ac75ca8b6fbb949369e18e6998dbc6093f4363cb1ca5c1854c3
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:921d45512e90c1ed750df46998881198a899372d8acecbd5c567203e0c615f45
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:51deeab1b9ab7c50492c351fbfc093ab77b89cb805299cfd330ff37988615d3d
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4f4bfb1e09820d75dfe1174d108abbe0a21204ff03b613c1fbecafa0a30e44b
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -109,3 +109,10 @@
109
  {"current_steps": 109, "total_steps": 117, "loss": 0.1097, "lr": 1.4254980853566248e-07, "epoch": 11.455696202531646, "percentage": 93.16, "elapsed_time": "1:08:37", "remaining_time": "0:05:02"}
110
  {"current_steps": 110, "total_steps": 117, "loss": 0.1066, "lr": 1.0926199633097156e-07, "epoch": 11.556962025316455, "percentage": 94.02, "elapsed_time": "1:09:06", "remaining_time": "0:04:23"}
111
  {"current_steps": 111, "total_steps": 117, "loss": 0.1218, "lr": 8.035205700685167e-08, "epoch": 11.658227848101266, "percentage": 94.87, "elapsed_time": "1:09:38", "remaining_time": "0:03:45"}
 
 
 
 
 
 
 
 
109
  {"current_steps": 109, "total_steps": 117, "loss": 0.1097, "lr": 1.4254980853566248e-07, "epoch": 11.455696202531646, "percentage": 93.16, "elapsed_time": "1:08:37", "remaining_time": "0:05:02"}
110
  {"current_steps": 110, "total_steps": 117, "loss": 0.1066, "lr": 1.0926199633097156e-07, "epoch": 11.556962025316455, "percentage": 94.02, "elapsed_time": "1:09:06", "remaining_time": "0:04:23"}
111
  {"current_steps": 111, "total_steps": 117, "loss": 0.1218, "lr": 8.035205700685167e-08, "epoch": 11.658227848101266, "percentage": 94.87, "elapsed_time": "1:09:38", "remaining_time": "0:03:45"}
112
+ {"current_steps": 112, "total_steps": 117, "loss": 0.1369, "lr": 5.584586887435739e-08, "epoch": 11.759493670886076, "percentage": 95.73, "elapsed_time": "1:10:19", "remaining_time": "0:03:08"}
113
+ {"current_steps": 113, "total_steps": 117, "loss": 0.1348, "lr": 3.576536829081323e-08, "epoch": 11.860759493670885, "percentage": 96.58, "elapsed_time": "1:10:48", "remaining_time": "0:02:30"}
114
+ {"current_steps": 114, "total_steps": 117, "loss": 0.1254, "lr": 2.012853002380466e-08, "epoch": 11.962025316455696, "percentage": 97.44, "elapsed_time": "1:11:22", "remaining_time": "0:01:52"}
115
+ {"current_steps": 115, "total_steps": 117, "loss": 0.0975, "lr": 8.949351161324227e-09, "epoch": 12.10126582278481, "percentage": 98.29, "elapsed_time": "1:12:52", "remaining_time": "0:01:16"}
116
+ {"current_steps": 116, "total_steps": 117, "loss": 0.1128, "lr": 2.237838582483387e-09, "epoch": 12.20253164556962, "percentage": 99.15, "elapsed_time": "1:13:28", "remaining_time": "0:00:38"}
117
+ {"current_steps": 117, "total_steps": 117, "loss": 0.1488, "lr": 0.0, "epoch": 12.30379746835443, "percentage": 100.0, "elapsed_time": "1:13:59", "remaining_time": "0:00:00"}
118
+ {"current_steps": 117, "total_steps": 117, "epoch": 12.30379746835443, "percentage": 100.0, "elapsed_time": "1:15:41", "remaining_time": "0:00:00"}