Hugging Face's logo

mlfoundations-dev
/
stackexchange_space

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
sedrickkeh commited on
Commit
93de2e2
·
verified ·
1 Parent(s): 3330266

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 +3 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:422b5e421e998644a5e429df8c16b8841a097df070b78fc0b3def6c12676b16d
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a20a710107719734e9aafbe47fe85872ea1f0f76a4e074ac930eeb99ce041ad0
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6eb35cd429deed9dc46edea03b02e98a58ea2f0e58bdd4fbe3d0648a6ce28157
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20ea9a4cf4e934d3f7b516af7c9ad0cecd5d62de9745d4689b474c91f0c07032
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:d5e3cc8bc253efdf01214bbe6fbe36ceaec89fe55f083e0c21cf7863567d03ec
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07bd31229fb4ecf11e02c739d4b3ccf1c9ccbf2acec659a2ada919580382bbca
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5e780e3a983d318399a9fdd35559e9bb947370b25e0436aa85cccd3b611f8dc8
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91d9234edc5b1ac7546e1369ab0ec35e418f28759ee40ad2e137646c3b805454
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -2,3 +2,6 @@
2
  {"current_steps": 20, "total_steps": 81, "loss": 1.129, "lr": 5e-06, "epoch": 0.7207207207207207, "percentage": 24.69, "elapsed_time": "0:10:47", "remaining_time": "0:32:53"}
3
  {"current_steps": 27, "total_steps": 81, "eval_loss": 1.0856622457504272, "epoch": 0.972972972972973, "percentage": 33.33, "elapsed_time": "0:15:15", "remaining_time": "0:30:31"}
4
  {"current_steps": 30, "total_steps": 81, "loss": 1.1105, "lr": 5e-06, "epoch": 1.0810810810810811, "percentage": 37.04, "elapsed_time": "0:17:44", "remaining_time": "0:30:09"}
 
 
 
 
2
  {"current_steps": 20, "total_steps": 81, "loss": 1.129, "lr": 5e-06, "epoch": 0.7207207207207207, "percentage": 24.69, "elapsed_time": "0:10:47", "remaining_time": "0:32:53"}
3
  {"current_steps": 27, "total_steps": 81, "eval_loss": 1.0856622457504272, "epoch": 0.972972972972973, "percentage": 33.33, "elapsed_time": "0:15:15", "remaining_time": "0:30:31"}
4
  {"current_steps": 30, "total_steps": 81, "loss": 1.1105, "lr": 5e-06, "epoch": 1.0810810810810811, "percentage": 37.04, "elapsed_time": "0:17:44", "remaining_time": "0:30:09"}
5
+ {"current_steps": 40, "total_steps": 81, "loss": 1.0347, "lr": 5e-06, "epoch": 1.4414414414414414, "percentage": 49.38, "elapsed_time": "0:23:02", "remaining_time": "0:23:36"}
6
+ {"current_steps": 50, "total_steps": 81, "loss": 1.015, "lr": 5e-06, "epoch": 1.8018018018018018, "percentage": 61.73, "elapsed_time": "0:28:23", "remaining_time": "0:17:35"}
7
+ {"current_steps": 55, "total_steps": 81, "eval_loss": 1.0293084383010864, "epoch": 1.981981981981982, "percentage": 67.9, "elapsed_time": "0:31:32", "remaining_time": "0:14:54"}