Hugging Face's logo

mlfoundations-dev
/
stackexchange_matheducators

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
sedrickkeh commited on
Commit
6065fc5
·
verified ·
1 Parent(s): 9b02fa4

Training in progress, epoch 2

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:bfc51003dc3c9bd18c97d1e679a5b1b3aba566cae3c6d2ec098caf69c12c7c2f
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9948825685bf1cc26a6299573387a38695389b20e2b31eef31c8a52a74b23c4
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:62ecafe328807ebc261ba83eb47a645a6192b818bf266a6debe2c7c219bd271a
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a3732d1fd7d8d2e23f5cdce91529acb7fcb540d835d96bbe3938e490d755dd5
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:c76298a34e1da58a62cf60e46618ef6d4a34deccf5100f5b03d98791ca3f741c
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1942f611c19db459b4dbfd6c22d97a7f88d10889b47b6ed506a96de2b637306
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:cdaedecbf814096d0092d42aa53e2f586fa2d0c7d80feea0802f4f0e63f98cb9
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7edf595e07419f79f14c57efb085c96905088a9576b7f33022da1a0b35bf0f06
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -2,3 +2,6 @@
2
  {"current_steps": 11, "total_steps": 33, "eval_loss": 1.0667738914489746, "epoch": 0.9565217391304348, "percentage": 33.33, "elapsed_time": "0:06:15", "remaining_time": "0:12:31"}
3
  {"current_steps": 20, "total_steps": 33, "loss": 1.1156, "lr": 5e-06, "epoch": 1.7608695652173914, "percentage": 60.61, "elapsed_time": "0:12:08", "remaining_time": "0:07:53"}
4
  {"current_steps": 22, "total_steps": 33, "eval_loss": 1.0284854173660278, "epoch": 1.9347826086956523, "percentage": 66.67, "elapsed_time": "0:13:35", "remaining_time": "0:06:47"}
 
 
 
 
2
  {"current_steps": 11, "total_steps": 33, "eval_loss": 1.0667738914489746, "epoch": 0.9565217391304348, "percentage": 33.33, "elapsed_time": "0:06:15", "remaining_time": "0:12:31"}
3
  {"current_steps": 20, "total_steps": 33, "loss": 1.1156, "lr": 5e-06, "epoch": 1.7608695652173914, "percentage": 60.61, "elapsed_time": "0:12:08", "remaining_time": "0:07:53"}
4
  {"current_steps": 22, "total_steps": 33, "eval_loss": 1.0284854173660278, "epoch": 1.9347826086956523, "percentage": 66.67, "elapsed_time": "0:13:35", "remaining_time": "0:06:47"}
5
+ {"current_steps": 30, "total_steps": 33, "loss": 1.0483, "lr": 5e-06, "epoch": 2.6521739130434785, "percentage": 90.91, "elapsed_time": "0:18:55", "remaining_time": "0:01:53"}
6
+ {"current_steps": 33, "total_steps": 33, "eval_loss": 0.9905301332473755, "epoch": 2.9130434782608696, "percentage": 100.0, "elapsed_time": "0:21:57", "remaining_time": "0:00:00"}
7
+ {"current_steps": 33, "total_steps": 33, "epoch": 2.9130434782608696, "percentage": 100.0, "elapsed_time": "0:23:10", "remaining_time": "0:00:00"}