Hugging Face's logo

mlfoundations-dev
/
1k_globalbatchsize96_lr1e5_epochs13

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
e27066a
·
verified ·
1 Parent(s): c6521ec

Training in progress, epoch 12

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 sha256:85acbc9cf83ae371dbac185ab927dc2c0fb87ec4711f4d56ebfcddd1346c2a9f
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b689339786019d3023bf1b8003460b9d75033aedee8532af0015fec5f0d3afd5
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b2daf2d99097616b68102a2e950dd305f4d6d0b74e88906e33716c55be1eb6b
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d086c6ef96709e1cae3c503d40f62215caf24f259a023f3687d746248a509448
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:43887f949f28796b05ddf3d10bcf615ca68656698e9e13cf50caf4f0f1a2ee05
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bfd55f65b517673b47eb2b450bb1ac9f678dbbdfbb213fbb22b4b9b3e3cc462
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:fb990bd1b00a85af12e9532a1dc8d3c9a6be608405d29db01674659d668064c4
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a99de806f41bb9a19c7cd14d829e2ce3c1f9353c788c2d175e442d01d4735d84
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -125,3 +125,7 @@
125
  {"current_steps": 125, "total_steps": 130, "loss": 0.3536, "lr": 4.499410377045765e-08, "epoch": 12.0, "percentage": 96.15, "elapsed_time": "2:02:26", "remaining_time": "0:04:53"}
126
  {"current_steps": 126, "total_steps": 130, "loss": 0.2289, "lr": 2.8811805762860578e-08, "epoch": 12.096, "percentage": 96.92, "elapsed_time": "2:04:26", "remaining_time": "0:03:57"}
127
  {"current_steps": 127, "total_steps": 130, "loss": 0.213, "lr": 1.6213459328950355e-08, "epoch": 12.192, "percentage": 97.69, "elapsed_time": "2:05:19", "remaining_time": "0:02:57"}
 
 
 
 
 
125
  {"current_steps": 125, "total_steps": 130, "loss": 0.3536, "lr": 4.499410377045765e-08, "epoch": 12.0, "percentage": 96.15, "elapsed_time": "2:02:26", "remaining_time": "0:04:53"}
126
  {"current_steps": 126, "total_steps": 130, "loss": 0.2289, "lr": 2.8811805762860578e-08, "epoch": 12.096, "percentage": 96.92, "elapsed_time": "2:04:26", "remaining_time": "0:03:57"}
127
  {"current_steps": 127, "total_steps": 130, "loss": 0.213, "lr": 1.6213459328950355e-08, "epoch": 12.192, "percentage": 97.69, "elapsed_time": "2:05:19", "remaining_time": "0:02:57"}
128
+ {"current_steps": 128, "total_steps": 130, "loss": 0.215, "lr": 7.2081471792911914e-09, "epoch": 12.288, "percentage": 98.46, "elapsed_time": "2:06:13", "remaining_time": "0:01:58"}
129
+ {"current_steps": 129, "total_steps": 130, "loss": 0.2196, "lr": 1.8023616455731253e-09, "epoch": 12.384, "percentage": 99.23, "elapsed_time": "2:07:08", "remaining_time": "0:00:59"}
130
+ {"current_steps": 130, "total_steps": 130, "loss": 0.2433, "lr": 0.0, "epoch": 12.48, "percentage": 100.0, "elapsed_time": "2:07:52", "remaining_time": "0:00:00"}
131
+ {"current_steps": 130, "total_steps": 130, "epoch": 12.48, "percentage": 100.0, "elapsed_time": "2:10:08", "remaining_time": "0:00:00"}