Hugging Face's logo

mlfoundations-dev
/
stackexchange_stackoverflow

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
sedrickkeh commited on
Commit
2ae5c9b
·
verified ·
1 Parent(s): a99f11d

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 +5 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:28847d940ed0b879b0ed614ccc58f9be4995b0ccf0ef853e83154e43725fa16c
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8166aa658efc4630002b7825b277646e569640557a5674eafbb03f644775b3b6
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e5010a332a9c663a12a706b4eb79122f4feeb56cc012e3fa3c17ee77336ea0c
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b47790a2db896650601c2b5330adea5a0bb8e3d2f755a81d7e938ecb46d2a111
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:f7dba0d9e4b64f9e7cb21a1bf03da2908d456d877d04bec64abff5f3bdbd749d
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57689de7fbbef8faa0ff8c1e7c906cc149fc8d729c18c7a234fa0ab532b0c27d
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:30cfc1bec53275e2d5e8b1ff081b0c8d1cb224d4f4913ee33f5505f905daf359
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6e561b2739e3b0a5d94628a4f78b69c32ccd4c5a1d0e917b1cb0eeef1c71c89
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -7,3 +7,8 @@
7
  {"current_steps": 60, "total_steps": 105, "loss": 0.7745, "lr": 5e-06, "epoch": 1.7142857142857144, "percentage": 57.14, "elapsed_time": "0:33:49", "remaining_time": "0:25:21"}
8
  {"current_steps": 70, "total_steps": 105, "loss": 0.7677, "lr": 5e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:39:07", "remaining_time": "0:19:33"}
9
  {"current_steps": 70, "total_steps": 105, "eval_loss": 0.8009844422340393, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:39:32", "remaining_time": "0:19:46"}
 
 
 
 
 
 
7
  {"current_steps": 60, "total_steps": 105, "loss": 0.7745, "lr": 5e-06, "epoch": 1.7142857142857144, "percentage": 57.14, "elapsed_time": "0:33:49", "remaining_time": "0:25:21"}
8
  {"current_steps": 70, "total_steps": 105, "loss": 0.7677, "lr": 5e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:39:07", "remaining_time": "0:19:33"}
9
  {"current_steps": 70, "total_steps": 105, "eval_loss": 0.8009844422340393, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:39:32", "remaining_time": "0:19:46"}
10
+ {"current_steps": 80, "total_steps": 105, "loss": 0.7107, "lr": 5e-06, "epoch": 2.2857142857142856, "percentage": 76.19, "elapsed_time": "0:46:11", "remaining_time": "0:14:26"}
11
+ {"current_steps": 90, "total_steps": 105, "loss": 0.7068, "lr": 5e-06, "epoch": 2.571428571428571, "percentage": 85.71, "elapsed_time": "0:51:30", "remaining_time": "0:08:35"}
12
+ {"current_steps": 100, "total_steps": 105, "loss": 0.7058, "lr": 5e-06, "epoch": 2.857142857142857, "percentage": 95.24, "elapsed_time": "0:56:51", "remaining_time": "0:02:50"}
13
+ {"current_steps": 105, "total_steps": 105, "eval_loss": 0.8002719879150391, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:01:19", "remaining_time": "0:00:00"}
14
+ {"current_steps": 105, "total_steps": 105, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:02:37", "remaining_time": "0:00:00"}