Hugging Face's logo

mlfoundations-dev
/
316_globalbatchsize64_lr2e5_epochs5

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
e576a53
·
verified ·
1 Parent(s): 5d0262f

Training in progress, epoch 5

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:d85bac53f9938b813b101f2b6cab1550796cbe6b9af440db9b14db85b52ca6bc
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f81c3c4a2c07cd882a4dc6a5b6632218e6758965524b3c8bd4cb558f09e89b8f
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:d0779ee2996e0845c7cd284d3ca72b8861988da94cfe772b209dcc787ce3a57f
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96c99f879432996d8805a7340d62cce738dbaf532b33b1d9121fb3db8ca3d731
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:f1cfe054e050d15efc193cebfcc1a9ec6fc1dc282c9ec9db4ecdaba509876aed
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0907e3dcf46a0cd38cd8494bd7d7b98d72b3330e6e7e3a8493eebcfb3914a936
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:063fbc56e27e8ac6fe5afb29b25d88635146e32ff7a8c2a5fdb3010bebf6602e
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47cfb20015caf0b298e811d249a15900d2c63cb279a5cbb16dc1f48e482867d6
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -20,3 +20,7 @@
20
  {"current_steps": 20, "total_steps": 25, "loss": 0.4558, "lr": 2.4425042564574186e-06, "epoch": 4.0, "percentage": 80.0, "elapsed_time": "0:25:58", "remaining_time": "0:06:29"}
21
  {"current_steps": 21, "total_steps": 25, "loss": 0.4984, "lr": 1.587464671688187e-06, "epoch": 4.2, "percentage": 84.0, "elapsed_time": "0:28:13", "remaining_time": "0:05:22"}
22
  {"current_steps": 22, "total_steps": 25, "loss": 0.4525, "lr": 9.036800464548157e-07, "epoch": 4.4, "percentage": 88.0, "elapsed_time": "0:29:27", "remaining_time": "0:04:00"}
 
 
 
 
 
20
  {"current_steps": 20, "total_steps": 25, "loss": 0.4558, "lr": 2.4425042564574186e-06, "epoch": 4.0, "percentage": 80.0, "elapsed_time": "0:25:58", "remaining_time": "0:06:29"}
21
  {"current_steps": 21, "total_steps": 25, "loss": 0.4984, "lr": 1.587464671688187e-06, "epoch": 4.2, "percentage": 84.0, "elapsed_time": "0:28:13", "remaining_time": "0:05:22"}
22
  {"current_steps": 22, "total_steps": 25, "loss": 0.4525, "lr": 9.036800464548157e-07, "epoch": 4.4, "percentage": 88.0, "elapsed_time": "0:29:27", "remaining_time": "0:04:00"}
23
+ {"current_steps": 23, "total_steps": 25, "loss": 0.4713, "lr": 4.0507026385502747e-07, "epoch": 4.6, "percentage": 92.0, "elapsed_time": "0:30:37", "remaining_time": "0:02:39"}
24
+ {"current_steps": 24, "total_steps": 25, "loss": 0.4809, "lr": 1.0178558119067316e-07, "epoch": 4.8, "percentage": 96.0, "elapsed_time": "0:31:52", "remaining_time": "0:01:19"}
25
+ {"current_steps": 25, "total_steps": 25, "loss": 0.4748, "lr": 0.0, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "0:32:59", "remaining_time": "0:00:00"}
26
+ {"current_steps": 25, "total_steps": 25, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "0:35:18", "remaining_time": "0:00:00"}