Hugging Face's logo

mlfoundations-dev
/
316_globalbatchsize64_lr1e5_epochs5

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
df3f12a
·
verified ·
1 Parent(s): eb8e064

Training in progress, epoch 5

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:f8bad1e88066e430e82d2a4d57b4480f07eefb85ae89aed4e479e898a516071f
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca029c7d8115d85e06cc9f3d4d72629dfb705420a7e46410244b284ace1c0f8d
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5fcc07459b7621181961c5cf1cb0fbb1102f532089133b7b0a98c70601a3b414
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96c952da2e86ab475b08ad96f1f2046fed78e4bdbaa5f651a6b96ee5cb5d3190
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:e169ae1128b3378bcccfa175ca5f73143171336ffd6cb24382dea2647c8897ae
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80db1d95f18042a2070c06a2e423c1a61ee38d9aa2b6632bd43a6e211285586b
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8c846cede97c1820b8b03ce63d1d78de4e27207395b44ed95df0f8d90dfd99b1
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:577c8bdfff5248ce01d8d5ba5e597b9ba3e0675319f25264fa2fc6e9f468d183
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -20,3 +20,7 @@
20
  {"current_steps": 20, "total_steps": 25, "loss": 0.5287, "lr": 1.2212521282287093e-06, "epoch": 4.0, "percentage": 80.0, "elapsed_time": "0:25:57", "remaining_time": "0:06:29"}
21
  {"current_steps": 21, "total_steps": 25, "loss": 0.5862, "lr": 7.937323358440935e-07, "epoch": 4.2, "percentage": 84.0, "elapsed_time": "0:28:11", "remaining_time": "0:05:22"}
22
  {"current_steps": 22, "total_steps": 25, "loss": 0.5381, "lr": 4.5184002322740784e-07, "epoch": 4.4, "percentage": 88.0, "elapsed_time": "0:29:25", "remaining_time": "0:04:00"}
 
 
 
 
 
20
  {"current_steps": 20, "total_steps": 25, "loss": 0.5287, "lr": 1.2212521282287093e-06, "epoch": 4.0, "percentage": 80.0, "elapsed_time": "0:25:57", "remaining_time": "0:06:29"}
21
  {"current_steps": 21, "total_steps": 25, "loss": 0.5862, "lr": 7.937323358440935e-07, "epoch": 4.2, "percentage": 84.0, "elapsed_time": "0:28:11", "remaining_time": "0:05:22"}
22
  {"current_steps": 22, "total_steps": 25, "loss": 0.5381, "lr": 4.5184002322740784e-07, "epoch": 4.4, "percentage": 88.0, "elapsed_time": "0:29:25", "remaining_time": "0:04:00"}
23
+ {"current_steps": 23, "total_steps": 25, "loss": 0.5601, "lr": 2.0253513192751374e-07, "epoch": 4.6, "percentage": 92.0, "elapsed_time": "0:30:35", "remaining_time": "0:02:39"}
24
+ {"current_steps": 24, "total_steps": 25, "loss": 0.5729, "lr": 5.089279059533658e-08, "epoch": 4.8, "percentage": 96.0, "elapsed_time": "0:31:50", "remaining_time": "0:01:19"}
25
+ {"current_steps": 25, "total_steps": 25, "loss": 0.5641, "lr": 0.0, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "0:32:56", "remaining_time": "0:00:00"}
26
+ {"current_steps": 25, "total_steps": 25, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "0:35:14", "remaining_time": "0:00:00"}