Hugging Face's logo

mlfoundations-dev
/
stackexchange_devops

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
sedrickkeh commited on
Commit
fde354d
·
verified ·
1 Parent(s): 5a1c32e

Training in progress, epoch 2

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:ee9f3eb53047afe3eb037b7f3af6a84f448f192cae7c5b2c3f95d0d98ab048a5
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d978edb77fc5b8eedc2ee6e0691bca2ec2c217031d980e6710232041e5e376dd
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf63ca333adaa870de874d2e80328c953e2a732f1b242648b043a60e05aef9b0
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a413638e95b809c4b0bfc50ba28ab331125c75098cd912b123604e883c44ad0b
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:00aa7e557e908075afd5ee4a7cb7a4bfd0fd996156d94b7bf1a06e79c1a8a61f
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49209cb3ad0a9b1b6f1203b47a61e0c116e6152c3aea86eda0a999c39ff670ba
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:186633b8caa20bfe13e0f258c097ddf169656f1fe23f4d585494fd0923be537c
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48fc9b80022aeaca5f669bc033dfedf78c94df141de1351810a8c8039423a80f
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -2,3 +2,6 @@
2
  {"current_steps": 11, "total_steps": 33, "eval_loss": 0.9338513612747192, "epoch": 0.9887640449438202, "percentage": 33.33, "elapsed_time": "0:10:56", "remaining_time": "0:21:52"}
3
  {"current_steps": 20, "total_steps": 33, "loss": 0.9997, "lr": 5e-06, "epoch": 1.797752808988764, "percentage": 60.61, "elapsed_time": "0:20:34", "remaining_time": "0:13:22"}
4
  {"current_steps": 22, "total_steps": 33, "eval_loss": 0.8875383138656616, "epoch": 1.9775280898876404, "percentage": 66.67, "elapsed_time": "0:22:53", "remaining_time": "0:11:26"}
 
 
 
 
2
  {"current_steps": 11, "total_steps": 33, "eval_loss": 0.9338513612747192, "epoch": 0.9887640449438202, "percentage": 33.33, "elapsed_time": "0:10:56", "remaining_time": "0:21:52"}
3
  {"current_steps": 20, "total_steps": 33, "loss": 0.9997, "lr": 5e-06, "epoch": 1.797752808988764, "percentage": 60.61, "elapsed_time": "0:20:34", "remaining_time": "0:13:22"}
4
  {"current_steps": 22, "total_steps": 33, "eval_loss": 0.8875383138656616, "epoch": 1.9775280898876404, "percentage": 66.67, "elapsed_time": "0:22:53", "remaining_time": "0:11:26"}
5
+ {"current_steps": 30, "total_steps": 33, "loss": 0.9271, "lr": 5e-06, "epoch": 2.696629213483146, "percentage": 90.91, "elapsed_time": "0:31:33", "remaining_time": "0:03:09"}
6
+ {"current_steps": 33, "total_steps": 33, "eval_loss": 0.8657615780830383, "epoch": 2.966292134831461, "percentage": 100.0, "elapsed_time": "0:35:52", "remaining_time": "0:00:00"}
7
+ {"current_steps": 33, "total_steps": 33, "epoch": 2.966292134831461, "percentage": 100.0, "elapsed_time": "0:37:07", "remaining_time": "0:00:00"}