Hugging Face's logo

mlfoundations-dev
/
stackexchange_dsp

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
sedrickkeh commited on
Commit
afb8a05
·
verified ·
1 Parent(s): 4ab3367

Training in progress, epoch 1

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 +5 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a149aac358fbe150734507b7b9ecc84f6a12b2e4a9d27ebeae9d942a1cf151ad
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3bc102901b5bbcea5e733abb2bd1adb3094e39f3387a86aa04fc4f5bf52c625
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:ef6e15cb2141e265557dd68bb99d467caea78d98035762cc82f0db20dbdd13b2
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:934aaf2bd9e099048a732beacd1779aed8a828b89a76bd06d36b6a3474512ab9
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:e92493516878306ff25255d26825d8e404cf88096ae5cb70ae4692efb84dde63
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d2024e8f7afaa6897721d11f1b60f1338bb30c93122b740817aee7ed8ca960a
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:ef2a1156826ff3f3d7db95598a02febd8e0abe7f3cfe7dd5f402d1bf399ec385
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2497bcdf2a3dc27b6e1cb7d0c7fa060548f0e856deb5e124edbf4ff10e93759e
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -3,3 +3,8 @@
3
  {"current_steps": 30, "total_steps": 126, "loss": 0.8677, "lr": 5e-06, "epoch": 0.7100591715976331, "percentage": 23.81, "elapsed_time": "0:16:11", "remaining_time": "0:51:49"}
4
  {"current_steps": 40, "total_steps": 126, "loss": 0.8493, "lr": 5e-06, "epoch": 0.9467455621301775, "percentage": 31.75, "elapsed_time": "0:21:33", "remaining_time": "0:46:21"}
5
  {"current_steps": 42, "total_steps": 126, "eval_loss": 0.8392977118492126, "epoch": 0.9940828402366864, "percentage": 33.33, "elapsed_time": "0:23:15", "remaining_time": "0:46:31"}
 
 
 
 
 
 
3
  {"current_steps": 30, "total_steps": 126, "loss": 0.8677, "lr": 5e-06, "epoch": 0.7100591715976331, "percentage": 23.81, "elapsed_time": "0:16:11", "remaining_time": "0:51:49"}
4
  {"current_steps": 40, "total_steps": 126, "loss": 0.8493, "lr": 5e-06, "epoch": 0.9467455621301775, "percentage": 31.75, "elapsed_time": "0:21:33", "remaining_time": "0:46:21"}
5
  {"current_steps": 42, "total_steps": 126, "eval_loss": 0.8392977118492126, "epoch": 0.9940828402366864, "percentage": 33.33, "elapsed_time": "0:23:15", "remaining_time": "0:46:31"}
6
+ {"current_steps": 50, "total_steps": 126, "loss": 0.8734, "lr": 5e-06, "epoch": 1.183431952662722, "percentage": 39.68, "elapsed_time": "0:28:36", "remaining_time": "0:43:29"}
7
+ {"current_steps": 60, "total_steps": 126, "loss": 0.7941, "lr": 5e-06, "epoch": 1.4201183431952662, "percentage": 47.62, "elapsed_time": "0:33:58", "remaining_time": "0:37:22"}
8
+ {"current_steps": 70, "total_steps": 126, "loss": 0.787, "lr": 5e-06, "epoch": 1.6568047337278107, "percentage": 55.56, "elapsed_time": "0:39:20", "remaining_time": "0:31:28"}
9
+ {"current_steps": 80, "total_steps": 126, "loss": 0.7843, "lr": 5e-06, "epoch": 1.893491124260355, "percentage": 63.49, "elapsed_time": "0:44:42", "remaining_time": "0:25:42"}
10
+ {"current_steps": 84, "total_steps": 126, "eval_loss": 0.8069051504135132, "epoch": 1.9881656804733727, "percentage": 66.67, "elapsed_time": "0:47:34", "remaining_time": "0:23:47"}