Hugging Face's logo

mlfoundations-dev
/
stackexchange_security

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
sedrickkeh commited on
Commit
b3dc1db
·
verified ·
1 Parent(s): ea604db

Training in progress, epoch 0

Browse files
Files changed (6) 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 -14
  6. training_args.bin +1 -1
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1a0ac81fe8826a8cd4027117bccdd1505047beb58ed7f737bd03f1181ebfcc0e
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74db0d93d257967843fd1d62c81a2d62d34d37320d6efc5faf94877ca2082aa9
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:72834f87efd4ec6b0cf1d30a100c71eb7d529f083b9b7d14ae0475ffb96dc6dd
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03428f1959c784a92b6c8811302b1c080eab82abc311b8fa2f68d726ee7c41c8
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d64c8cbcf87b531cfa4a7a1c3f85d34d63f324e6d4a9c7c36e062cdaddc8a5c
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1065a9be81ff1e785a2521693864d36816c94bea773a4969072554653f4af7be
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:62677635ca90bab109a50348713f68f5c679dcb976669532cf7e7fdce4dcdff2
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05fdc1eb92b6e02d99e0e1bc109572e7c5274466c19a5259b3a53cc8ebff89d0
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -1,14 +1,4 @@
1
- {"current_steps": 10, "total_steps": 105, "loss": 1.1889, "lr": 5e-06, "epoch": 0.2826855123674912, "percentage": 9.52, "elapsed_time": "0:05:25", "remaining_time": "0:51:28"}
2
- {"current_steps": 20, "total_steps": 105, "loss": 1.0785, "lr": 5e-06, "epoch": 0.5653710247349824, "percentage": 19.05, "elapsed_time": "0:10:44", "remaining_time": "0:45:38"}
3
- {"current_steps": 30, "total_steps": 105, "loss": 1.0426, "lr": 5e-06, "epoch": 0.8480565371024735, "percentage": 28.57, "elapsed_time": "0:16:03", "remaining_time": "0:40:08"}
4
- {"current_steps": 35, "total_steps": 105, "eval_loss": 1.022178053855896, "epoch": 0.9893992932862191, "percentage": 33.33, "elapsed_time": "0:19:15", "remaining_time": "0:38:31"}
5
- {"current_steps": 40, "total_steps": 105, "loss": 1.0834, "lr": 5e-06, "epoch": 1.1342756183745584, "percentage": 38.1, "elapsed_time": "0:22:59", "remaining_time": "0:37:21"}
6
- {"current_steps": 50, "total_steps": 105, "loss": 0.9727, "lr": 5e-06, "epoch": 1.4169611307420495, "percentage": 47.62, "elapsed_time": "0:28:19", "remaining_time": "0:31:09"}
7
- {"current_steps": 60, "total_steps": 105, "loss": 0.9609, "lr": 5e-06, "epoch": 1.6996466431095407, "percentage": 57.14, "elapsed_time": "0:33:39", "remaining_time": "0:25:14"}
8
- {"current_steps": 70, "total_steps": 105, "loss": 0.953, "lr": 5e-06, "epoch": 1.9823321554770317, "percentage": 66.67, "elapsed_time": "0:38:59", "remaining_time": "0:19:29"}
9
- {"current_steps": 70, "total_steps": 105, "eval_loss": 0.9813353419303894, "epoch": 1.9823321554770317, "percentage": 66.67, "elapsed_time": "0:39:38", "remaining_time": "0:19:49"}
10
- {"current_steps": 80, "total_steps": 105, "loss": 0.9773, "lr": 5e-06, "epoch": 2.2685512367491167, "percentage": 76.19, "elapsed_time": "0:46:00", "remaining_time": "0:14:22"}
11
- {"current_steps": 90, "total_steps": 105, "loss": 0.8981, "lr": 5e-06, "epoch": 2.5512367491166077, "percentage": 85.71, "elapsed_time": "0:51:19", "remaining_time": "0:08:33"}
12
- {"current_steps": 100, "total_steps": 105, "loss": 0.8934, "lr": 5e-06, "epoch": 2.833922261484099, "percentage": 95.24, "elapsed_time": "0:56:39", "remaining_time": "0:02:49"}
13
- {"current_steps": 105, "total_steps": 105, "eval_loss": 0.9675137996673584, "epoch": 2.9752650176678443, "percentage": 100.0, "elapsed_time": "1:01:00", "remaining_time": "0:00:00"}
14
- {"current_steps": 105, "total_steps": 105, "epoch": 2.9752650176678443, "percentage": 100.0, "elapsed_time": "1:02:14", "remaining_time": "0:00:00"}
 
1
+ {"current_steps": 10, "total_steps": 105, "loss": 1.1885, "lr": 5e-06, "epoch": 0.2826855123674912, "percentage": 9.52, "elapsed_time": "0:05:26", "remaining_time": "0:51:44"}
2
+ {"current_steps": 20, "total_steps": 105, "loss": 1.0832, "lr": 5e-06, "epoch": 0.5653710247349824, "percentage": 19.05, "elapsed_time": "0:10:48", "remaining_time": "0:45:56"}
3
+ {"current_steps": 30, "total_steps": 105, "loss": 1.0481, "lr": 5e-06, "epoch": 0.8480565371024735, "percentage": 28.57, "elapsed_time": "0:16:10", "remaining_time": "0:40:25"}
4
+ {"current_steps": 35, "total_steps": 105, "eval_loss": 1.0256564617156982, "epoch": 0.9893992932862191, "percentage": 33.33, "elapsed_time": "0:19:24", "remaining_time": "0:38:48"}
 
 
 
 
 
 
 
 
 
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:79ee649ce0a14d538cd417071611aec2a108983e484ae4167835d126bb9754bf
3
  size 7160
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc1332adc2c157a179e719370655c39e69fb097ad5868d005788fa4fe9c14827
3
  size 7160