Hugging Face's logo

mlfoundations-dev
/
ds_no_offload_liger_packing_torchcompile

Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
sedrickkeh commited on
Commit
740504c
·
verified ·
1 Parent(s): 69a12d5

Training in progress, epoch 3

Browse files
Files changed (2) hide show
  1. adapter_model.safetensors +1 -1
  2. trainer_log.jsonl +7 -0
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cacf6d28608990e0f6a02204bcefc7a62ac1597eb167425695753c4ee4afa9be
3
  size 323014560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b79195fd7581b4fb97fe744d7482fda52db18891078d7fca3b6d2989248f7cd2
3
  size 323014560
trainer_log.jsonl CHANGED
@@ -10,3 +10,10 @@
10
  {"current_steps": 10, "total_steps": 18, "loss": 1.1716, "lr": 5e-06, "epoch": 1.6666666666666665, "percentage": 55.56, "elapsed_time": "0:11:05", "remaining_time": "0:08:52"}
11
  {"current_steps": 11, "total_steps": 18, "loss": 1.1606, "lr": 4.02454838991936e-06, "epoch": 1.8333333333333335, "percentage": 61.11, "elapsed_time": "0:12:09", "remaining_time": "0:07:43"}
12
  {"current_steps": 12, "total_steps": 18, "loss": 1.1714, "lr": 3.0865828381745515e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:13:02", "remaining_time": "0:06:31"}
 
 
 
 
 
 
 
 
10
  {"current_steps": 10, "total_steps": 18, "loss": 1.1716, "lr": 5e-06, "epoch": 1.6666666666666665, "percentage": 55.56, "elapsed_time": "0:11:05", "remaining_time": "0:08:52"}
11
  {"current_steps": 11, "total_steps": 18, "loss": 1.1606, "lr": 4.02454838991936e-06, "epoch": 1.8333333333333335, "percentage": 61.11, "elapsed_time": "0:12:09", "remaining_time": "0:07:43"}
12
  {"current_steps": 12, "total_steps": 18, "loss": 1.1714, "lr": 3.0865828381745515e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:13:02", "remaining_time": "0:06:31"}
13
+ {"current_steps": 13, "total_steps": 18, "loss": 1.1518, "lr": 2.2221488349019903e-06, "epoch": 2.1666666666666665, "percentage": 72.22, "elapsed_time": "0:14:29", "remaining_time": "0:05:34"}
14
+ {"current_steps": 14, "total_steps": 18, "loss": 1.1449, "lr": 1.4644660940672628e-06, "epoch": 2.3333333333333335, "percentage": 77.78, "elapsed_time": "0:15:33", "remaining_time": "0:04:26"}
15
+ {"current_steps": 15, "total_steps": 18, "loss": 1.167, "lr": 8.426519384872733e-07, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "0:16:36", "remaining_time": "0:03:19"}
16
+ {"current_steps": 16, "total_steps": 18, "loss": 1.1749, "lr": 3.8060233744356634e-07, "epoch": 2.6666666666666665, "percentage": 88.89, "elapsed_time": "0:17:39", "remaining_time": "0:02:12"}
17
+ {"current_steps": 17, "total_steps": 18, "loss": 1.1597, "lr": 9.607359798384785e-08, "epoch": 2.8333333333333335, "percentage": 94.44, "elapsed_time": "0:18:43", "remaining_time": "0:01:06"}
18
+ {"current_steps": 18, "total_steps": 18, "loss": 1.1474, "lr": 0.0, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:19:36", "remaining_time": "0:00:00"}
19
+ {"current_steps": 18, "total_steps": 18, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:20:03", "remaining_time": "0:00:00"}