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
364a84a
·
verified ·
1 Parent(s): 46ca499

Training in progress, epoch 10

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 sha256:4b320828fbfb9c78b0968b860f1cfcf81a6bceef023358ef576de161501e8781
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:399da691e7fd1358b22e830beace274cdee99694713126a667c55a3a149a542a
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:fee7a3f3c6ab4909f1bcb3ef6c245b05f0d8f673ec4690e8d347bb1dd86588b3
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afe2e2895b1f886d4c2217c23f0dc651be5e19f256f663e89ea7848a579e5d1f
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3989a12bce14a947200e595ecbf1139904b28250a4f58c9bfdd69cdf5199e3eb
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb87935c4e29b77d81c196be89788796f56b755090917b93de8c05ac0a5624c1
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:b51b04d62f82a8fa3a8912d3fa31302f26b3d752d15c2cce9ca4f8f36d758462
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4bd55aa9a11c03d8ff23b95b4dabc7d989aa5a90d58ccee1052781745b54f2b
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -45,3 +45,8 @@
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"}
 
 
 
 
 
 
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"}
48
+ {"current_steps": 48, "total_steps": 55, "loss": 0.3354, "lr": 4.951556604879049e-07, "epoch": 9.6, "percentage": 87.27, "elapsed_time": "1:04:28", "remaining_time": "0:09:24"}
49
+ {"current_steps": 49, "total_steps": 55, "loss": 0.3437, "lr": 3.6541621326989183e-07, "epoch": 9.8, "percentage": 89.09, "elapsed_time": "1:05:43", "remaining_time": "0:08:02"}
50
+ {"current_steps": 50, "total_steps": 55, "loss": 0.3435, "lr": 2.547212649466568e-07, "epoch": 10.0, "percentage": 90.91, "elapsed_time": "1:07:05", "remaining_time": "0:06:42"}
51
+ {"current_steps": 51, "total_steps": 55, "loss": 0.3301, "lr": 1.6352568480485277e-07, "epoch": 10.2, "percentage": 92.73, "elapsed_time": "1:09:20", "remaining_time": "0:05:26"}
52
+ {"current_steps": 52, "total_steps": 55, "loss": 0.3517, "lr": 9.22042150446728e-08, "epoch": 10.4, "percentage": 94.55, "elapsed_time": "1:10:27", "remaining_time": "0:04:03"}