Hugging Face's logo

mlfoundations-dev
/
316_globalbatchsize32_lr4e5_epochs15

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
15b8233
·
verified ·
1 Parent(s): 617e2b4

Training in progress, epoch 4

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 +10 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b161373ef5a44bcc6e0cdd088b6105e941089fa4f1ab7e86d4fe4365ce5b51e1
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a61b9c1d0b14a0cb9681b9f326086e9b8fc864a058ab7c3bdbf3c41dacb5f29a
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37b593f087584e6189b26da462075bc37a91be7d431044129cd2a83e6e3fb2bf
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a7f3f59c87d0bb6e291e1cc9f2ccca0a5065c97a6544de13575219b4e25c213
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b385f7dc6279ccfe020d1c9f1e537295607bbdfd15a9b2ea7c0dafe9e4b430b
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd6a53802e7794a6d0bd80436c031c0bf70eb3966bd4f145841f05ac98d0fb18
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a4167ab79b9ef9e92d684350619f1c8952b1c5b27128456c7574b3eaf2691da
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1badee4f89be1881cd20709aaba49d483177471061027d1d039c9ae2d66d368d
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -32,3 +32,13 @@
32
  {"current_steps": 32, "total_steps": 150, "loss": 0.2472, "lr": 3.845524888710885e-05, "epoch": 3.2, "percentage": 21.33, "elapsed_time": "0:21:36", "remaining_time": "1:19:40"}
33
  {"current_steps": 33, "total_steps": 150, "loss": 0.2934, "lr": 3.827090915285202e-05, "epoch": 3.3, "percentage": 22.0, "elapsed_time": "0:22:11", "remaining_time": "1:18:40"}
34
  {"current_steps": 34, "total_steps": 150, "loss": 0.3205, "lr": 3.807667539897041e-05, "epoch": 3.4, "percentage": 22.67, "elapsed_time": "0:22:53", "remaining_time": "1:18:04"}
 
 
 
 
 
 
 
 
 
 
 
32
  {"current_steps": 32, "total_steps": 150, "loss": 0.2472, "lr": 3.845524888710885e-05, "epoch": 3.2, "percentage": 21.33, "elapsed_time": "0:21:36", "remaining_time": "1:19:40"}
33
  {"current_steps": 33, "total_steps": 150, "loss": 0.2934, "lr": 3.827090915285202e-05, "epoch": 3.3, "percentage": 22.0, "elapsed_time": "0:22:11", "remaining_time": "1:18:40"}
34
  {"current_steps": 34, "total_steps": 150, "loss": 0.3205, "lr": 3.807667539897041e-05, "epoch": 3.4, "percentage": 22.67, "elapsed_time": "0:22:53", "remaining_time": "1:18:04"}
35
+ {"current_steps": 35, "total_steps": 150, "loss": 0.2891, "lr": 3.787265280646825e-05, "epoch": 3.5, "percentage": 23.33, "elapsed_time": "0:23:36", "remaining_time": "1:17:35"}
36
+ {"current_steps": 36, "total_steps": 150, "loss": 0.278, "lr": 3.7658951857178544e-05, "epoch": 3.6, "percentage": 24.0, "elapsed_time": "0:24:15", "remaining_time": "1:16:49"}
37
+ {"current_steps": 37, "total_steps": 150, "loss": 0.2636, "lr": 3.743568827393525e-05, "epoch": 3.7, "percentage": 24.67, "elapsed_time": "0:24:35", "remaining_time": "1:15:06"}
38
+ {"current_steps": 38, "total_steps": 150, "loss": 0.2839, "lr": 3.720298295790732e-05, "epoch": 3.8, "percentage": 25.33, "elapsed_time": "0:25:01", "remaining_time": "1:13:46"}
39
+ {"current_steps": 39, "total_steps": 150, "loss": 0.2312, "lr": 3.696096192312852e-05, "epoch": 3.9, "percentage": 26.0, "elapsed_time": "0:25:27", "remaining_time": "1:12:27"}
40
+ {"current_steps": 40, "total_steps": 150, "loss": 0.2242, "lr": 3.6709756228258735e-05, "epoch": 4.0, "percentage": 26.67, "elapsed_time": "0:26:02", "remaining_time": "1:11:36"}
41
+ {"current_steps": 41, "total_steps": 150, "loss": 0.1684, "lr": 3.644950190561325e-05, "epoch": 4.1, "percentage": 27.33, "elapsed_time": "0:27:39", "remaining_time": "1:13:32"}
42
+ {"current_steps": 42, "total_steps": 150, "loss": 0.1844, "lr": 3.6180339887498953e-05, "epoch": 4.2, "percentage": 28.0, "elapsed_time": "0:28:15", "remaining_time": "1:12:39"}
43
+ {"current_steps": 43, "total_steps": 150, "loss": 0.1592, "lr": 3.590241592989696e-05, "epoch": 4.3, "percentage": 28.67, "elapsed_time": "0:28:51", "remaining_time": "1:11:49"}
44
+ {"current_steps": 44, "total_steps": 150, "loss": 0.1432, "lr": 3.561588053353319e-05, "epoch": 4.4, "percentage": 29.33, "elapsed_time": "0:29:29", "remaining_time": "1:11:02"}