Hugging Face's logo

mlfoundations-dev
/
b2_math_random_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
fa4fb7a
·
verified ·
1 Parent(s): 2e11032

Training in progress, epoch 8

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 +8 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc9b589393a4b7eafd83548f9f3e4b5dada1a48ac254128f06ca49f9d6011354
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:436797d8fbde1ceed856f0ce6b06ac05d4d3fc621d5e81668a6e5dc0bc4aae79
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3487d0a1ffd3cc4c75e915dfa07d652bcb3a36a1cbc973cc2d7d6f0549a0834e
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7b8bc8088c4592686cbeeced6264a6d92ac0a74a69d6ab8968717363c7ac7eb
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:42198c91c6149a3b33d6bc527fa66e8fb376b0795ebbbd21fc74f6bf7766aa2f
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a3321ae2b91730f2062880671bd7efe813b0efb490c8b20a07e3883fc6fa799
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f68878084ae8ff5b6103ec62ac54510b2267a8cf8d2ebaceacf23c4dfc94f19
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2129fa232f52b260e7adeb3d395b7e07181e16633f3fc0d7586fe6bf91a5e489
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -83,3 +83,11 @@
83
  {"current_steps": 83, "total_steps": 117, "loss": 0.0994, "lr": 2.371581150947476e-06, "epoch": 8.708860759493671, "percentage": 70.94, "elapsed_time": "0:38:09", "remaining_time": "0:15:37"}
84
  {"current_steps": 84, "total_steps": 117, "loss": 0.0947, "lr": 2.245515092739488e-06, "epoch": 8.810126582278482, "percentage": 71.79, "elapsed_time": "0:38:30", "remaining_time": "0:15:07"}
85
  {"current_steps": 85, "total_steps": 117, "loss": 0.0991, "lr": 2.1219146715716332e-06, "epoch": 8.91139240506329, "percentage": 72.65, "elapsed_time": "0:38:54", "remaining_time": "0:14:38"}
 
 
 
 
 
 
 
 
 
83
  {"current_steps": 83, "total_steps": 117, "loss": 0.0994, "lr": 2.371581150947476e-06, "epoch": 8.708860759493671, "percentage": 70.94, "elapsed_time": "0:38:09", "remaining_time": "0:15:37"}
84
  {"current_steps": 84, "total_steps": 117, "loss": 0.0947, "lr": 2.245515092739488e-06, "epoch": 8.810126582278482, "percentage": 71.79, "elapsed_time": "0:38:30", "remaining_time": "0:15:07"}
85
  {"current_steps": 85, "total_steps": 117, "loss": 0.0991, "lr": 2.1219146715716332e-06, "epoch": 8.91139240506329, "percentage": 72.65, "elapsed_time": "0:38:54", "remaining_time": "0:14:38"}
86
+ {"current_steps": 86, "total_steps": 117, "loss": 0.1179, "lr": 2.0008905265604316e-06, "epoch": 9.050632911392405, "percentage": 73.5, "elapsed_time": "0:40:32", "remaining_time": "0:14:36"}
87
+ {"current_steps": 87, "total_steps": 117, "loss": 0.0762, "lr": 1.8825509907063328e-06, "epoch": 9.151898734177216, "percentage": 74.36, "elapsed_time": "0:40:54", "remaining_time": "0:14:06"}
88
+ {"current_steps": 88, "total_steps": 117, "loss": 0.0745, "lr": 1.7670019939210025e-06, "epoch": 9.253164556962025, "percentage": 75.21, "elapsed_time": "0:41:23", "remaining_time": "0:13:38"}
89
+ {"current_steps": 89, "total_steps": 117, "loss": 0.0754, "lr": 1.6543469682057105e-06, "epoch": 9.354430379746836, "percentage": 76.07, "elapsed_time": "0:41:40", "remaining_time": "0:13:06"}
90
+ {"current_steps": 90, "total_steps": 117, "loss": 0.0825, "lr": 1.544686755065677e-06, "epoch": 9.455696202531646, "percentage": 76.92, "elapsed_time": "0:42:04", "remaining_time": "0:12:37"}
91
+ {"current_steps": 91, "total_steps": 117, "loss": 0.0856, "lr": 1.438119515243277e-06, "epoch": 9.556962025316455, "percentage": 77.78, "elapsed_time": "0:42:28", "remaining_time": "0:12:08"}
92
+ {"current_steps": 92, "total_steps": 117, "loss": 0.0652, "lr": 1.3347406408508695e-06, "epoch": 9.658227848101266, "percentage": 78.63, "elapsed_time": "0:42:50", "remaining_time": "0:11:38"}
93
+ {"current_steps": 93, "total_steps": 117, "loss": 0.0816, "lr": 1.234642669981946e-06, "epoch": 9.759493670886076, "percentage": 79.49, "elapsed_time": "0:43:09", "remaining_time": "0:11:08"}