Hugging Face's logo

mlfoundations-dev
/
hp_ablations_grid_mistral_bsz4096_lr5e-6_scheduler-cosine-warmup0.05-minlr5e-7

Text Generation
Transformers
Safetensors
mistral
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
sedrickkeh commited on
Commit
849770e
•
1 Parent(s): 6ffba9f

Training in progress, epoch 3

Browse files
Files changed (4) hide show
  1. model-00001-of-00003.safetensors +1 -1
  2. model-00002-of-00003.safetensors +1 -1
  3. model-00003-of-00003.safetensors +1 -1
  4. trainer_log.jsonl +10 -0
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:de77d3ab9a4ea03eb1f8882911e96aa300952e4cd9ce1e00efb1150ce1abeb4e
3
  size 4943162336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc466038cc6c6c62719ad7524eedbec1d81e261b9940cf90af6fb2b35f825922
3
  size 4943162336
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a6dcdf1bc90893dfafcf679724a5d7b1abb216571859bdc3b455ec6cd35decc6
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dac3a393327995bfc980301b637f51c0214463c0aed322ad82a14f7149cbc331
3
  size 4999819336
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e8dbb9e34c47972e0cacbb718e4f23ec2c363fe51b055277592322e50ec5e90c
3
  size 4540516344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f3a08580cbde0eef7816d71bd1b3650b4c1784e83abaa414d1a823a770d18af
3
  size 4540516344
trainer_log.jsonl CHANGED
@@ -17,3 +17,13 @@
17
  {"current_steps": 160, "total_steps": 252, "loss": 0.4614, "lr": 1.9542666212969685e-06, "epoch": 1.9047619047619047, "percentage": 63.49, "elapsed_time": "2:36:22", "remaining_time": "1:29:55"}
18
  {"current_steps": 168, "total_steps": 252, "eval_loss": 0.06041712313890457, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "2:45:33", "remaining_time": "1:22:46"}
19
  {"current_steps": 170, "total_steps": 252, "loss": 0.4551, "lr": 1.6852840498821444e-06, "epoch": 2.0238095238095237, "percentage": 67.46, "elapsed_time": "2:48:13", "remaining_time": "1:21:08"}
 
 
 
 
 
 
 
 
 
 
 
17
  {"current_steps": 160, "total_steps": 252, "loss": 0.4614, "lr": 1.9542666212969685e-06, "epoch": 1.9047619047619047, "percentage": 63.49, "elapsed_time": "2:36:22", "remaining_time": "1:29:55"}
18
  {"current_steps": 168, "total_steps": 252, "eval_loss": 0.06041712313890457, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "2:45:33", "remaining_time": "1:22:46"}
19
  {"current_steps": 170, "total_steps": 252, "loss": 0.4551, "lr": 1.6852840498821444e-06, "epoch": 2.0238095238095237, "percentage": 67.46, "elapsed_time": "2:48:13", "remaining_time": "1:21:08"}
20
+ {"current_steps": 180, "total_steps": 252, "loss": 0.4354, "lr": 1.4346716108828857e-06, "epoch": 2.142857142857143, "percentage": 71.43, "elapsed_time": "2:57:50", "remaining_time": "1:11:08"}
21
+ {"current_steps": 190, "total_steps": 252, "loss": 0.4335, "lr": 1.2067532591426361e-06, "epoch": 2.261904761904762, "percentage": 75.4, "elapsed_time": "3:07:29", "remaining_time": "1:01:10"}
22
+ {"current_steps": 200, "total_steps": 252, "loss": 0.43, "lr": 1.0054613958815923e-06, "epoch": 2.380952380952381, "percentage": 79.37, "elapsed_time": "3:17:07", "remaining_time": "0:51:15"}
23
+ {"current_steps": 210, "total_steps": 252, "loss": 0.4288, "lr": 8.342690208062692e-07, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "3:26:46", "remaining_time": "0:41:21"}
24
+ {"current_steps": 220, "total_steps": 252, "loss": 0.4306, "lr": 6.961298105271477e-07, "epoch": 2.619047619047619, "percentage": 87.3, "elapsed_time": "3:36:24", "remaining_time": "0:31:28"}
25
+ {"current_steps": 230, "total_steps": 252, "loss": 0.4294, "lr": 5.9342715714456e-07, "epoch": 2.738095238095238, "percentage": 91.27, "elapsed_time": "3:46:02", "remaining_time": "0:21:37"}
26
+ {"current_steps": 240, "total_steps": 252, "loss": 0.4283, "lr": 5.27933046268245e-07, "epoch": 2.857142857142857, "percentage": 95.24, "elapsed_time": "3:55:41", "remaining_time": "0:11:47"}
27
+ {"current_steps": 250, "total_steps": 252, "loss": 0.426, "lr": 5.007774839708124e-07, "epoch": 2.9761904761904763, "percentage": 99.21, "elapsed_time": "4:05:20", "remaining_time": "0:01:57"}
28
+ {"current_steps": 252, "total_steps": 252, "eval_loss": 0.05939801409840584, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "4:09:28", "remaining_time": "0:00:00"}
29
+ {"current_steps": 252, "total_steps": 252, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "4:10:07", "remaining_time": "0:00:00"}