Hugging Face's logo

mlfoundations-dev
/
llama3-1_8b_mlfoundations-dev-stackexchange_scifi

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
EtashGuha commited on
Commit
857ef6b
·
verified ·
1 Parent(s): 2bf50d5

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:afd27483807f8f8b287ab70b2109f394692985e3371bf577d320c18e7cee48b3
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84c9f057bbf2158940eb7c21dce56956c4528e003df48727ddddfff5ee7da63c
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ea55f52349da93c606179cb495aad8093b2a0ebc33cc99f89863a8a55bd55b8
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c369d2c455321ee2d25f052383400033c8c3885557fca8550784243e0a6f75a8
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:16025a36ce3cb0065eba0edc94c9bc5025fd08ab16995c7b339e5aa6c7065584
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51d2f6c24dfdd46cd427a3f5c563a489ca1034ea62f2038ed87c3dc0bc53345e
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59d90651a50ed72f32dd550f9ff09d1edfe1202fe196088358cc78370dab3635
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c6c611adb3a7b3237b17453cf85373cdd263626a796a2bb4aab631a93abd28b
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -1,3 +1,6 @@
1
  {"current_steps": 10, "total_steps": 63, "loss": 1.3702, "lr": 5e-06, "epoch": 0.47477744807121663, "percentage": 15.87, "elapsed_time": "0:25:57", "remaining_time": "2:17:32"}
2
  {"current_steps": 20, "total_steps": 63, "loss": 1.2286, "lr": 5e-06, "epoch": 0.9495548961424333, "percentage": 31.75, "elapsed_time": "0:51:48", "remaining_time": "1:51:22"}
3
  {"current_steps": 21, "total_steps": 63, "eval_loss": 1.193329095840454, "epoch": 0.9970326409495549, "percentage": 33.33, "elapsed_time": "0:55:38", "remaining_time": "1:51:16"}
 
 
 
 
1
  {"current_steps": 10, "total_steps": 63, "loss": 1.3702, "lr": 5e-06, "epoch": 0.47477744807121663, "percentage": 15.87, "elapsed_time": "0:25:57", "remaining_time": "2:17:32"}
2
  {"current_steps": 20, "total_steps": 63, "loss": 1.2286, "lr": 5e-06, "epoch": 0.9495548961424333, "percentage": 31.75, "elapsed_time": "0:51:48", "remaining_time": "1:51:22"}
3
  {"current_steps": 21, "total_steps": 63, "eval_loss": 1.193329095840454, "epoch": 0.9970326409495549, "percentage": 33.33, "elapsed_time": "0:55:38", "remaining_time": "1:51:16"}
4
+ {"current_steps": 30, "total_steps": 63, "loss": 1.162, "lr": 5e-06, "epoch": 1.4243323442136497, "percentage": 47.62, "elapsed_time": "1:20:08", "remaining_time": "1:28:09"}
5
+ {"current_steps": 40, "total_steps": 63, "loss": 1.122, "lr": 5e-06, "epoch": 1.8991097922848663, "percentage": 63.49, "elapsed_time": "1:45:59", "remaining_time": "1:00:56"}
6
+ {"current_steps": 42, "total_steps": 63, "eval_loss": 1.1249243021011353, "epoch": 1.9940652818991098, "percentage": 66.67, "elapsed_time": "1:52:34", "remaining_time": "0:56:17"}