Hugging Face's logo

mlfoundations-dev
/
stackexchange_linguistics

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
sedrickkeh commited on
Commit
1e611c3
·
verified ·
1 Parent(s): 30fbc30

Training in progress, epoch 3

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 +3 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6746bb77c850bf521a503a0d58cafe5e9663c6f9d3a47cb26218b5365d23dfca
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8726f56025e967aea1a3981c1287d82d5f24b2a9ec1bb7f576a2de7dc868d290
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d1e5bfe3d57247384b3b8f35c7517c6571cff6a270c07301f9ea32681da80fd
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89929cde1f92fdc29cef52147ab7473c5afbb235ac7e28ef6ee79af44c85c4c7
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:856af1dc7a346d630c04cc32033bc7e8e3fd5061808519ec0ac44ea4fc1f0938
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d33f4294951de6da9c8c9a0c96201982ed10153128faeb89134c46aee6edac67
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:d57137b8849f92deb773053c25b96213c1304b6e0ba5878e2ab52f2c77fe34be
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d559e519b905c69da031546eb31f8b3a1d8ce9c6faa80c0da4b8b82150282a7d
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -3,3 +3,6 @@
3
  {"current_steps": 20, "total_steps": 48, "loss": 1.09, "lr": 5e-06, "epoch": 1.25, "percentage": 41.67, "elapsed_time": "0:12:10", "remaining_time": "0:17:02"}
4
  {"current_steps": 30, "total_steps": 48, "loss": 1.031, "lr": 5e-06, "epoch": 1.875, "percentage": 62.5, "elapsed_time": "0:17:32", "remaining_time": "0:10:31"}
5
  {"current_steps": 32, "total_steps": 48, "eval_loss": 1.0452321767807007, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:18:47", "remaining_time": "0:09:23"}
 
 
 
 
3
  {"current_steps": 20, "total_steps": 48, "loss": 1.09, "lr": 5e-06, "epoch": 1.25, "percentage": 41.67, "elapsed_time": "0:12:10", "remaining_time": "0:17:02"}
4
  {"current_steps": 30, "total_steps": 48, "loss": 1.031, "lr": 5e-06, "epoch": 1.875, "percentage": 62.5, "elapsed_time": "0:17:32", "remaining_time": "0:10:31"}
5
  {"current_steps": 32, "total_steps": 48, "eval_loss": 1.0452321767807007, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:18:47", "remaining_time": "0:09:23"}
6
+ {"current_steps": 40, "total_steps": 48, "loss": 0.9746, "lr": 5e-06, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "0:24:23", "remaining_time": "0:04:52"}
7
+ {"current_steps": 48, "total_steps": 48, "eval_loss": 1.021416425704956, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:30:08", "remaining_time": "0:00:00"}
8
+ {"current_steps": 48, "total_steps": 48, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:31:23", "remaining_time": "0:00:00"}