Hugging Face's logo

mlfoundations-dev
/
llama3-1_8b_webinstruct_750k

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
gsmyrnis commited on
Commit
dd5b5f6
·
verified ·
1 Parent(s): c51d7d0

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 +10 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d9afe66544c6437ea435af8c6108f648bd0f9fe9a1da163f6121ce650a94167e
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3a0e21f835d20ee9602a0e13df413aedc22a2a520dbf06eac084cf053b39476
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:11e49571d5ca4eeb0001921b93fee7dc8529107997bfd65bb51fb7453957d92f
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f39b3588e51d2e098b0ff554990b4ca72ad1a0b5e110adc39f62645c6a0deb50
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:56a7e543d4706507626f86f72205192715a42a09a75f11e832f275cabda928ac
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ee5304d913e4cac863e9ba090d781734ffdef6c9cae4c385366422505c4eb58
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:11433614fd936a70c1d5ef9767de04ace78359acca7d7518309c824057bfbba3
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ede2dd636e3e2795e8b01d3147b5cb8d3df80bfdbc8475a1590d31615dcc9427
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -22,3 +22,13 @@
22
  {"current_steps": 200, "total_steps": 300, "eval_loss": 0.9496641159057617, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:21:26", "remaining_time": "0:10:43"}
23
  {"current_steps": 210, "total_steps": 300, "loss": 0.8388, "learning_rate": 5e-06, "epoch": 2.1, "percentage": 70.0, "elapsed_time": "0:24:10", "remaining_time": "0:10:21"}
24
  {"current_steps": 220, "total_steps": 300, "loss": 0.8356, "learning_rate": 5e-06, "epoch": 2.2, "percentage": 73.33, "elapsed_time": "0:25:08", "remaining_time": "0:09:08"}
 
 
 
 
 
 
 
 
 
 
 
22
  {"current_steps": 200, "total_steps": 300, "eval_loss": 0.9496641159057617, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:21:26", "remaining_time": "0:10:43"}
23
  {"current_steps": 210, "total_steps": 300, "loss": 0.8388, "learning_rate": 5e-06, "epoch": 2.1, "percentage": 70.0, "elapsed_time": "0:24:10", "remaining_time": "0:10:21"}
24
  {"current_steps": 220, "total_steps": 300, "loss": 0.8356, "learning_rate": 5e-06, "epoch": 2.2, "percentage": 73.33, "elapsed_time": "0:25:08", "remaining_time": "0:09:08"}
25
+ {"current_steps": 230, "total_steps": 300, "loss": 0.838, "learning_rate": 5e-06, "epoch": 2.3, "percentage": 76.67, "elapsed_time": "0:26:07", "remaining_time": "0:07:57"}
26
+ {"current_steps": 240, "total_steps": 300, "loss": 0.8426, "learning_rate": 5e-06, "epoch": 2.4, "percentage": 80.0, "elapsed_time": "0:27:07", "remaining_time": "0:06:46"}
27
+ {"current_steps": 250, "total_steps": 300, "loss": 0.845, "learning_rate": 5e-06, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "0:28:06", "remaining_time": "0:05:37"}
28
+ {"current_steps": 260, "total_steps": 300, "loss": 0.8307, "learning_rate": 5e-06, "epoch": 2.6, "percentage": 86.67, "elapsed_time": "0:29:05", "remaining_time": "0:04:28"}
29
+ {"current_steps": 270, "total_steps": 300, "loss": 0.8391, "learning_rate": 5e-06, "epoch": 2.7, "percentage": 90.0, "elapsed_time": "0:30:04", "remaining_time": "0:03:20"}
30
+ {"current_steps": 280, "total_steps": 300, "loss": 0.8426, "learning_rate": 5e-06, "epoch": 2.8, "percentage": 93.33, "elapsed_time": "0:31:04", "remaining_time": "0:02:13"}
31
+ {"current_steps": 290, "total_steps": 300, "loss": 0.8447, "learning_rate": 5e-06, "epoch": 2.9, "percentage": 96.67, "elapsed_time": "0:32:03", "remaining_time": "0:01:06"}
32
+ {"current_steps": 300, "total_steps": 300, "loss": 0.841, "learning_rate": 5e-06, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:33:02", "remaining_time": "0:00:00"}
33
+ {"current_steps": 300, "total_steps": 300, "eval_loss": 0.9554556012153625, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:34:47", "remaining_time": "0:00:00"}
34
+ {"current_steps": 300, "total_steps": 300, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:36:23", "remaining_time": "0:00:00"}