Hugging Face's logo

mlfoundations-dev
/
ds_no_offload_liger_packing_dataloader16

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
2fc0802
·
verified ·
1 Parent(s): 8af3f6c

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 sha256:786ba58f3696dce669080ab5192fc9f4aa1d056338c656348f9a0d630c76db42
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b1e539664465b33b57e64b9c3b8bc6ded8a6f920eb9e3abe593a9379fd859e7
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f92da04fabddea1af3c1d6b48c987b916ec75765d9d9748ca0c26a1cb6b2cf1
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3eb94fe5ef85199330cff62c8b78c1aa8c636a7a39072227259018bdf53b536
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:f5828d6c46f148f8ca81fb98c06220233c1f4bae0cd059881664660f93e920ee
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2afb5db565ea4b2a9f0e73308ca3fb7bfd1124967e43ead1f8f28df2190dcc87
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:c13d4c0ed661b7fea71e91ef99856e8bc5b32115505b64f90028cb60b00d31c2
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4a122632c297606209021f908b828331500f3b4529d98b9cb8ca33639ee297e
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": "0:12:51", "remaining_time": "0:03:40"}
15
  {"current_steps": 15, "total_steps": 18, "loss": 0.9139, "lr": 8.426519384872733e-07, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "0:13:26", "remaining_time": "0:02:41"}
16
  {"current_steps": 16, "total_steps": 18, "loss": 0.905, "lr": 3.8060233744356634e-07, "epoch": 2.6666666666666665, "percentage": 88.89, "elapsed_time": "0:14:02", "remaining_time": "0:01:45"}
 
 
 
 
14
  {"current_steps": 14, "total_steps": 18, "loss": 0.8942, "lr": 1.4644660940672628e-06, "epoch": 2.3333333333333335, "percentage": 77.78, "elapsed_time": "0:12:51", "remaining_time": "0:03:40"}
15
  {"current_steps": 15, "total_steps": 18, "loss": 0.9139, "lr": 8.426519384872733e-07, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "0:13:26", "remaining_time": "0:02:41"}
16
  {"current_steps": 16, "total_steps": 18, "loss": 0.905, "lr": 3.8060233744356634e-07, "epoch": 2.6666666666666665, "percentage": 88.89, "elapsed_time": "0:14:02", "remaining_time": "0:01:45"}
17
+ {"current_steps": 17, "total_steps": 18, "loss": 0.9043, "lr": 9.607359798384785e-08, "epoch": 2.8333333333333335, "percentage": 94.44, "elapsed_time": "0:14:38", "remaining_time": "0:00:51"}
18
+ {"current_steps": 18, "total_steps": 18, "loss": 0.8928, "lr": 0.0, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:15:13", "remaining_time": "0:00:00"}
19
+ {"current_steps": 18, "total_steps": 18, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:16:46", "remaining_time": "0:00:00"}