Hugging Face's logo

mlfoundations-dev
/
b2_code_embedding_1k

Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
1
ryanmarten commited on
Commit
b810e31
·
verified ·
1 Parent(s): 5837291

Training in progress, epoch 6

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 +7 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:25503382cea45f620a71361f641d0b6221bce359e7ef529e9522ab22cdf76bed
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a258e7f05999572f2f64a7ab28747144c8eac59bd39673f3a28335bb964a4f8
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6c5f363b885171c8f6abf919b402ee610d67a13dd62f9a5631ee8b7362a20220
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe923b919badcfffecb85d505b4fe4b8207fbe93d06a643a8b061bdda6e1f709
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:91d019c95c378c334aafa59771b0bc80378361ab06928e93cb67d42916c033e3
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de7c6604f67921e2c0f850d558e915dfd4ad0fc44e5afef0d5cd058236e47ed0
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0015960da2c8715c2f48fc31200e73cad7933f9668c73628ce9fbf2ad05d3856
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b098667d266b71d801a7be7f25ecc3f923f4e7269baf3340722a6c3e02315336
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -62,3 +62,10 @@
62
  {"current_steps": 62, "total_steps": 70, "loss": 0.5251, "lr": 7.852378812959227e-07, "epoch": 5.952, "percentage": 88.57, "elapsed_time": "2:04:31", "remaining_time": "0:16:04"}
63
  {"current_steps": 63, "total_steps": 70, "loss": 0.5123, "lr": 6.030737921409169e-07, "epoch": 6.048, "percentage": 90.0, "elapsed_time": "2:07:11", "remaining_time": "0:14:07"}
64
  {"current_steps": 64, "total_steps": 70, "loss": 0.5244, "lr": 4.4427194213859216e-07, "epoch": 6.144, "percentage": 91.43, "elapsed_time": "2:09:07", "remaining_time": "0:12:06"}
 
 
 
 
 
 
 
 
62
  {"current_steps": 62, "total_steps": 70, "loss": 0.5251, "lr": 7.852378812959227e-07, "epoch": 5.952, "percentage": 88.57, "elapsed_time": "2:04:31", "remaining_time": "0:16:04"}
63
  {"current_steps": 63, "total_steps": 70, "loss": 0.5123, "lr": 6.030737921409169e-07, "epoch": 6.048, "percentage": 90.0, "elapsed_time": "2:07:11", "remaining_time": "0:14:07"}
64
  {"current_steps": 64, "total_steps": 70, "loss": 0.5244, "lr": 4.4427194213859216e-07, "epoch": 6.144, "percentage": 91.43, "elapsed_time": "2:09:07", "remaining_time": "0:12:06"}
65
+ {"current_steps": 65, "total_steps": 70, "loss": 0.525, "lr": 3.0922713770922155e-07, "epoch": 6.24, "percentage": 92.86, "elapsed_time": "2:11:02", "remaining_time": "0:10:04"}
66
+ {"current_steps": 66, "total_steps": 70, "loss": 0.5291, "lr": 1.9827512151456175e-07, "epoch": 6.336, "percentage": 94.29, "elapsed_time": "2:12:57", "remaining_time": "0:08:03"}
67
+ {"current_steps": 67, "total_steps": 70, "loss": 0.4929, "lr": 1.1169173774871478e-07, "epoch": 6.432, "percentage": 95.71, "elapsed_time": "2:14:50", "remaining_time": "0:06:02"}
68
+ {"current_steps": 68, "total_steps": 70, "loss": 0.5308, "lr": 4.9692246345985905e-08, "epoch": 6.5280000000000005, "percentage": 97.14, "elapsed_time": "2:16:52", "remaining_time": "0:04:01"}
69
+ {"current_steps": 69, "total_steps": 70, "loss": 0.5203, "lr": 1.2430787810776556e-08, "epoch": 6.624, "percentage": 98.57, "elapsed_time": "2:18:45", "remaining_time": "0:02:00"}
70
+ {"current_steps": 70, "total_steps": 70, "loss": 0.5348, "lr": 0.0, "epoch": 6.72, "percentage": 100.0, "elapsed_time": "2:20:46", "remaining_time": "0:00:00"}
71
+ {"current_steps": 70, "total_steps": 70, "epoch": 6.72, "percentage": 100.0, "elapsed_time": "2:22:32", "remaining_time": "0:00:00"}