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
3721af6
·
verified ·
1 Parent(s): 364a84a

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 +4 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:399da691e7fd1358b22e830beace274cdee99694713126a667c55a3a149a542a
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42a593935c90996bdd499a0c5978702b08fcefae9ce78133f823cb0ad1ef7eeb
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:afe2e2895b1f886d4c2217c23f0dc651be5e19f256f663e89ea7848a579e5d1f
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:282cbe0d69c22421627947df4c0a0482672d052db194e3fafdb8b06459571219
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:fb87935c4e29b77d81c196be89788796f56b755090917b93de8c05ac0a5624c1
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:451dc50b03d6d8b2bcb845797c9c5c76c39bd2f1a2dc55b8f734086100607ba1
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:c4bd55aa9a11c03d8ff23b95b4dabc7d989aa5a90d58ccee1052781745b54f2b
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1bdf523f997765a83240feb728544aa74faa9d1fce940c74c18875949106ca0
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -50,3 +50,7 @@
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"}
 
 
 
 
 
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"}
53
+ {"current_steps": 53, "total_steps": 55, "loss": 0.3478, "lr": 4.104993088376974e-08, "epoch": 10.6, "percentage": 96.36, "elapsed_time": "1:11:39", "remaining_time": "0:02:42"}
54
+ {"current_steps": 54, "total_steps": 55, "loss": 0.3138, "lr": 1.0273036248318325e-08, "epoch": 10.8, "percentage": 98.18, "elapsed_time": "1:12:37", "remaining_time": "0:01:20"}
55
+ {"current_steps": 55, "total_steps": 55, "loss": 0.3197, "lr": 0.0, "epoch": 11.0, "percentage": 100.0, "elapsed_time": "1:13:42", "remaining_time": "0:00:00"}
56
+ {"current_steps": 55, "total_steps": 55, "epoch": 11.0, "percentage": 100.0, "elapsed_time": "1:16:13", "remaining_time": "0:00:00"}