Hugging Face's logo

mlfoundations-dev
/
316_globalbatchsize64_lr1e5_epochs7

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
36cd4b5
·
verified ·
1 Parent(s): 8764048

Training in progress, epoch 7

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 sha256:0dda05886c487883dcbdf7d56e5e9908a3a7734d2c9cc2731d3b22d378366e60
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc4b5c4a191619b2677f2f808c24c1d5530ceb10b8d23b566070331f8445100f
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:26efe2c8aad8930df81caf2693f11667ba406c6de9d249f539b85da15a3fd360
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17697cb5db86fc6c8604488c49bb4fdea688997197c3c6d34e0dac9b354e4c54
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d50e41070dc2933325334e50d42b90d7cc444316eae5eb2f99a56ac51a47a91
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fde8e10410219ee58da31220111b818db5165a90f7395e279487d8ec08cbc03f
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:d6d760646f9f00cc09aa081c2c89b22a0c0de46c85aac7a0357552054c8292d5
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7455a01345192db2d71aa9efa4329dc1a2eb882364a9ee74a2b6a805f07a16c7
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -30,3 +30,7 @@
30
  {"current_steps": 30, "total_steps": 35, "loss": 0.4784, "lr": 6.282669192770896e-07, "epoch": 6.0, "percentage": 85.71, "elapsed_time": "0:39:36", "remaining_time": "0:06:36"}
31
  {"current_steps": 31, "total_steps": 35, "loss": 0.5251, "lr": 4.05210941898847e-07, "epoch": 6.2, "percentage": 88.57, "elapsed_time": "0:41:45", "remaining_time": "0:05:23"}
32
  {"current_steps": 32, "total_steps": 35, "loss": 0.5024, "lr": 2.2930371799975593e-07, "epoch": 6.4, "percentage": 91.43, "elapsed_time": "0:42:56", "remaining_time": "0:04:01"}
 
 
 
 
 
30
  {"current_steps": 30, "total_steps": 35, "loss": 0.4784, "lr": 6.282669192770896e-07, "epoch": 6.0, "percentage": 85.71, "elapsed_time": "0:39:36", "remaining_time": "0:06:36"}
31
  {"current_steps": 31, "total_steps": 35, "loss": 0.5251, "lr": 4.05210941898847e-07, "epoch": 6.2, "percentage": 88.57, "elapsed_time": "0:41:45", "remaining_time": "0:05:23"}
32
  {"current_steps": 32, "total_steps": 35, "loss": 0.5024, "lr": 2.2930371799975593e-07, "epoch": 6.4, "percentage": 91.43, "elapsed_time": "0:42:56", "remaining_time": "0:04:01"}
33
+ {"current_steps": 33, "total_steps": 35, "loss": 0.4919, "lr": 1.0235029373752758e-07, "epoch": 6.6, "percentage": 94.29, "elapsed_time": "0:44:12", "remaining_time": "0:02:40"}
34
+ {"current_steps": 34, "total_steps": 35, "loss": 0.5287, "lr": 2.5653383040524228e-08, "epoch": 6.8, "percentage": 97.14, "elapsed_time": "0:45:13", "remaining_time": "0:01:19"}
35
+ {"current_steps": 35, "total_steps": 35, "loss": 0.486, "lr": 0.0, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "0:46:21", "remaining_time": "0:00:00"}
36
+ {"current_steps": 35, "total_steps": 35, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "0:48:36", "remaining_time": "0:00:00"}