Hugging Face's logo

mlfoundations-dev
/
ds_no_offload_liger_packing_dataloader32

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
f44d26d
·
verified ·
1 Parent(s): f8f396f

Training in progress, epoch 3

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 +3 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c2158a80f5a66d483862a6d1aa79f03bf1fdba857fa8dc4b0e9588a8d3a6f5ca
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:131acf9a419de0bb906d1be5a04ec2beea71677366301cf3decbf0f1703cba6f
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:c5a779cad919e2cbbe5b8a5875ee5c9c15fa7ab5623b3a690f52c65455fb2e11
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4ff75c3c64eaee8bbdfa899bc25fe0b54187f82a04714fc6e3123684b78495d
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:ebeb67de6498a0b4a4d7f8037223334114f61c4c33ff9a47ff49556bbe422ff8
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c080751db712983e7a9650f8569bf5f343f5f28319a621391b2e365dbce591e4
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:76e6c43fba96a2bae1bc29a4b0a6ac17789ddb963c6cdf261b137e1de86237bb
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a77f7f6af6a94f5a6018f1f252841d59d595467f3e70e7306f62bd5f0b88c53
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -14,3 +14,6 @@
14
  {"current_steps": 14, "total_steps": 18, "loss": 0.8942, "lr": 1.4644660940672628e-06, "epoch": 2.3333333333333335, "percentage": 77.78, "elapsed_time": "0:13:23", "remaining_time": "0:03:49"}
15
  {"current_steps": 15, "total_steps": 18, "loss": 0.9139, "lr": 8.426519384872733e-07, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "0:14:00", "remaining_time": "0:02:48"}
16
  {"current_steps": 16, "total_steps": 18, "loss": 0.9051, "lr": 3.8060233744356634e-07, "epoch": 2.6666666666666665, "percentage": 88.89, "elapsed_time": "0:14:36", "remaining_time": "0:01:49"}
 
 
 
 
14
  {"current_steps": 14, "total_steps": 18, "loss": 0.8942, "lr": 1.4644660940672628e-06, "epoch": 2.3333333333333335, "percentage": 77.78, "elapsed_time": "0:13:23", "remaining_time": "0:03:49"}
15
  {"current_steps": 15, "total_steps": 18, "loss": 0.9139, "lr": 8.426519384872733e-07, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "0:14:00", "remaining_time": "0:02:48"}
16
  {"current_steps": 16, "total_steps": 18, "loss": 0.9051, "lr": 3.8060233744356634e-07, "epoch": 2.6666666666666665, "percentage": 88.89, "elapsed_time": "0:14:36", "remaining_time": "0:01:49"}
17
+ {"current_steps": 17, "total_steps": 18, "loss": 0.9043, "lr": 9.607359798384785e-08, "epoch": 2.8333333333333335, "percentage": 94.44, "elapsed_time": "0:15:13", "remaining_time": "0:00:53"}
18
+ {"current_steps": 18, "total_steps": 18, "loss": 0.8928, "lr": 0.0, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:15:49", "remaining_time": "0:00:00"}
19
+ {"current_steps": 18, "total_steps": 18, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:17:35", "remaining_time": "0:00:00"}