Hugging Face's logo

mlfoundations-dev
/
stackexchange_photo

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
sedrickkeh commited on
Commit
fc5640f
·
verified ·
1 Parent(s): b1ecbc0

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 +4 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e1022cd5c9f241d34dfd8cd922a18aad628c44f52c509395283bb344111836bd
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcfc1302566ff05c46b21d903a5ae73353332a693a14d71e352e13013d8f446d
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3555048a6e4161790328cfaaa1641f2e9d076dd54519ab9488b1425e203f0b14
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e96166708b4bec9fac964965e054b63d401ae484c3582283cf75cdc4c7a36d8
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2239d1c57d887e43edb955f627bf7e21e084935859e2552a98e2b3f5e39b0be9
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fb6c623cb24f37f520a63a077c7524cd7f79e55e7dfba6999ac795773042e1d
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:d3524f39c72b3a56af52ce5faaa20d2591e9ded1e6ab47fffa3c250883503895
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1aaaac5b9f6d28c4fb29fa142c8fcd9b5a23ca7e7e0cc3c47d3a399de31b51e1
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -2,3 +2,7 @@
2
  {"current_steps": 20, "total_steps": 87, "loss": 1.0586, "lr": 5e-06, "epoch": 0.6837606837606838, "percentage": 22.99, "elapsed_time": "0:10:41", "remaining_time": "0:35:47"}
3
  {"current_steps": 29, "total_steps": 87, "eval_loss": 0.9911791086196899, "epoch": 0.9914529914529915, "percentage": 33.33, "elapsed_time": "0:15:56", "remaining_time": "0:31:52"}
4
  {"current_steps": 30, "total_steps": 87, "loss": 1.0822, "lr": 5e-06, "epoch": 1.0256410256410255, "percentage": 34.48, "elapsed_time": "0:17:30", "remaining_time": "0:33:16"}
 
 
 
 
 
2
  {"current_steps": 20, "total_steps": 87, "loss": 1.0586, "lr": 5e-06, "epoch": 0.6837606837606838, "percentage": 22.99, "elapsed_time": "0:10:41", "remaining_time": "0:35:47"}
3
  {"current_steps": 29, "total_steps": 87, "eval_loss": 0.9911791086196899, "epoch": 0.9914529914529915, "percentage": 33.33, "elapsed_time": "0:15:56", "remaining_time": "0:31:52"}
4
  {"current_steps": 30, "total_steps": 87, "loss": 1.0822, "lr": 5e-06, "epoch": 1.0256410256410255, "percentage": 34.48, "elapsed_time": "0:17:30", "remaining_time": "0:33:16"}
5
+ {"current_steps": 40, "total_steps": 87, "loss": 0.9553, "lr": 5e-06, "epoch": 1.3675213675213675, "percentage": 45.98, "elapsed_time": "0:22:46", "remaining_time": "0:26:45"}
6
+ {"current_steps": 50, "total_steps": 87, "loss": 0.9318, "lr": 5e-06, "epoch": 1.7094017094017095, "percentage": 57.47, "elapsed_time": "0:28:01", "remaining_time": "0:20:44"}
7
+ {"current_steps": 58, "total_steps": 87, "eval_loss": 0.9310455918312073, "epoch": 1.982905982905983, "percentage": 66.67, "elapsed_time": "0:32:48", "remaining_time": "0:16:24"}
8
+ {"current_steps": 60, "total_steps": 87, "loss": 0.9805, "lr": 5e-06, "epoch": 2.051282051282051, "percentage": 68.97, "elapsed_time": "0:34:53", "remaining_time": "0:15:41"}