Hugging Face's logo

mlfoundations-dev
/
316_globalbatchsize64_lr1e5_epochs11

Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
1
sedrickkeh commited on
Commit
46ca499
·
verified ·
1 Parent(s): d387ecc

Training in progress, epoch 9

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 +5 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a86beb759421d128be735c3a91f6acad22815b827fd8fb78a1eab7428c24e872
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b320828fbfb9c78b0968b860f1cfcf81a6bceef023358ef576de161501e8781
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3932850f949b5e7b21c7911c5f643455147cb7384487a67924417990b56f91c1
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fee7a3f3c6ab4909f1bcb3ef6c245b05f0d8f673ec4690e8d347bb1dd86588b3
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d00230598305bf48968eb004f4ad28951f07310c65e0a03f9bd41646f172360
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3989a12bce14a947200e595ecbf1139904b28250a4f58c9bfdd69cdf5199e3eb
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:d1650eeb37c95dfaf45eab9b5c66e69acc4532dce708213074f43ea65cb54c8c
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b51b04d62f82a8fa3a8912d3fa31302f26b3d752d15c2cce9ca4f8f36d758462
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -40,3 +40,8 @@
40
  {"current_steps": 40, "total_steps": 55, "loss": 0.3728, "lr": 2.139416699389153e-06, "epoch": 8.0, "percentage": 72.73, "elapsed_time": "0:53:24", "remaining_time": "0:20:01"}
41
  {"current_steps": 41, "total_steps": 55, "loss": 0.3232, "lr": 1.8825509907063328e-06, "epoch": 8.2, "percentage": 74.55, "elapsed_time": "0:55:23", "remaining_time": "0:18:54"}
42
  {"current_steps": 42, "total_steps": 55, "loss": 0.3751, "lr": 1.6384955486934157e-06, "epoch": 8.4, "percentage": 76.36, "elapsed_time": "0:56:42", "remaining_time": "0:17:33"}
 
 
 
 
 
 
40
  {"current_steps": 40, "total_steps": 55, "loss": 0.3728, "lr": 2.139416699389153e-06, "epoch": 8.0, "percentage": 72.73, "elapsed_time": "0:53:24", "remaining_time": "0:20:01"}
41
  {"current_steps": 41, "total_steps": 55, "loss": 0.3232, "lr": 1.8825509907063328e-06, "epoch": 8.2, "percentage": 74.55, "elapsed_time": "0:55:23", "remaining_time": "0:18:54"}
42
  {"current_steps": 42, "total_steps": 55, "loss": 0.3751, "lr": 1.6384955486934157e-06, "epoch": 8.4, "percentage": 76.36, "elapsed_time": "0:56:42", "remaining_time": "0:17:33"}
43
+ {"current_steps": 43, "total_steps": 55, "loss": 0.3527, "lr": 1.4082532495113627e-06, "epoch": 8.6, "percentage": 78.18, "elapsed_time": "0:57:51", "remaining_time": "0:16:08"}
44
+ {"current_steps": 44, "total_steps": 55, "loss": 0.3582, "lr": 1.1927702081543279e-06, "epoch": 8.8, "percentage": 80.0, "elapsed_time": "0:58:56", "remaining_time": "0:14:44"}
45
+ {"current_steps": 45, "total_steps": 55, "loss": 0.3585, "lr": 9.929318906602176e-07, "epoch": 9.0, "percentage": 81.82, "elapsed_time": "1:00:08", "remaining_time": "0:13:21"}
46
+ {"current_steps": 46, "total_steps": 55, "loss": 0.3448, "lr": 8.095594755407971e-07, "epoch": 9.2, "percentage": 83.64, "elapsed_time": "1:02:13", "remaining_time": "0:12:10"}
47
+ {"current_steps": 47, "total_steps": 55, "loss": 0.3245, "lr": 6.43406479383053e-07, "epoch": 9.4, "percentage": 85.45, "elapsed_time": "1:03:13", "remaining_time": "0:10:45"}