Hugging Face's logo

mlfoundations-dev
/
hp_ablations_mistral_bsz2048

Text Generation
Transformers
Safetensors
mistral
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
 Community
sedrickkeh commited on
Commit
6f33727
·
verified ·
1 Parent(s): 797dda7

Training in progress, epoch 2

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 +14 -0
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:651ab6cd7864d859dca28b2ebf105606a6c90db0087692bd94ded541b372f2db
3
  size 4943162336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80d027ef296f8f81aec7701e696cfa92375a2afb2685e6235a6ce79d92f41f04
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:a8248831d7aafd3006e02b57701f37b1ba91fe09d0907f2ede9fb315f2440328
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28fc8da213b137dd03f89a2913a699b3ca1b73bcf7446c989759318e5138ed84
3
  size 4999819336
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65db4ccd4e8f893d368943e3318bc328b261fe67535bbb774fe4ed570e95455f
3
  size 4540516344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92b027a4dd7560f1273571d1ad213489cfe4b104d0b88e244a73745cfa1565fe
3
  size 4540516344
trainer_log.jsonl CHANGED
@@ -11,3 +11,17 @@
11
  {"current_steps": 110, "total_steps": 369, "loss": 0.5615, "learning_rate": 5e-06, "epoch": 0.8906882591093117, "percentage": 29.81, "elapsed_time": "1:44:46", "remaining_time": "4:06:42"}
12
  {"current_steps": 120, "total_steps": 369, "loss": 0.5579, "learning_rate": 5e-06, "epoch": 0.97165991902834, "percentage": 32.52, "elapsed_time": "1:54:16", "remaining_time": "3:57:06"}
13
  {"current_steps": 123, "total_steps": 369, "eval_loss": 0.06959892809391022, "epoch": 0.9959514170040485, "percentage": 33.33, "elapsed_time": "1:59:42", "remaining_time": "3:59:24"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  {"current_steps": 110, "total_steps": 369, "loss": 0.5615, "learning_rate": 5e-06, "epoch": 0.8906882591093117, "percentage": 29.81, "elapsed_time": "1:44:46", "remaining_time": "4:06:42"}
12
  {"current_steps": 120, "total_steps": 369, "loss": 0.5579, "learning_rate": 5e-06, "epoch": 0.97165991902834, "percentage": 32.52, "elapsed_time": "1:54:16", "remaining_time": "3:57:06"}
13
  {"current_steps": 123, "total_steps": 369, "eval_loss": 0.06959892809391022, "epoch": 0.9959514170040485, "percentage": 33.33, "elapsed_time": "1:59:42", "remaining_time": "3:59:24"}
14
+ {"current_steps": 130, "total_steps": 369, "loss": 0.5311, "learning_rate": 5e-06, "epoch": 1.0526315789473684, "percentage": 35.23, "elapsed_time": "2:06:40", "remaining_time": "3:52:52"}
15
+ {"current_steps": 140, "total_steps": 369, "loss": 0.514, "learning_rate": 5e-06, "epoch": 1.1336032388663968, "percentage": 37.94, "elapsed_time": "2:16:11", "remaining_time": "3:42:46"}
16
+ {"current_steps": 150, "total_steps": 369, "loss": 0.5142, "learning_rate": 5e-06, "epoch": 1.214574898785425, "percentage": 40.65, "elapsed_time": "2:25:42", "remaining_time": "3:32:43"}
17
+ {"current_steps": 160, "total_steps": 369, "loss": 0.5122, "learning_rate": 5e-06, "epoch": 1.2955465587044535, "percentage": 43.36, "elapsed_time": "2:35:13", "remaining_time": "3:22:46"}
18
+ {"current_steps": 170, "total_steps": 369, "loss": 0.5122, "learning_rate": 5e-06, "epoch": 1.376518218623482, "percentage": 46.07, "elapsed_time": "2:44:46", "remaining_time": "3:12:52"}
19
+ {"current_steps": 180, "total_steps": 369, "loss": 0.5125, "learning_rate": 5e-06, "epoch": 1.45748987854251, "percentage": 48.78, "elapsed_time": "2:54:18", "remaining_time": "3:03:01"}
20
+ {"current_steps": 190, "total_steps": 369, "loss": 0.512, "learning_rate": 5e-06, "epoch": 1.5384615384615383, "percentage": 51.49, "elapsed_time": "3:03:49", "remaining_time": "2:53:10"}
21
+ {"current_steps": 200, "total_steps": 369, "loss": 0.5101, "learning_rate": 5e-06, "epoch": 1.6194331983805668, "percentage": 54.2, "elapsed_time": "3:13:21", "remaining_time": "2:43:23"}
22
+ {"current_steps": 210, "total_steps": 369, "loss": 0.5065, "learning_rate": 5e-06, "epoch": 1.7004048582995952, "percentage": 56.91, "elapsed_time": "3:22:53", "remaining_time": "2:33:36"}
23
+ {"current_steps": 220, "total_steps": 369, "loss": 0.511, "learning_rate": 5e-06, "epoch": 1.7813765182186234, "percentage": 59.62, "elapsed_time": "3:32:25", "remaining_time": "2:23:51"}
24
+ {"current_steps": 230, "total_steps": 369, "loss": 0.5106, "learning_rate": 5e-06, "epoch": 1.8623481781376519, "percentage": 62.33, "elapsed_time": "3:41:57", "remaining_time": "2:14:08"}
25
+ {"current_steps": 240, "total_steps": 369, "loss": 0.5102, "learning_rate": 5e-06, "epoch": 1.9433198380566803, "percentage": 65.04, "elapsed_time": "3:51:28", "remaining_time": "2:04:25"}
26
+ {"current_steps": 247, "total_steps": 369, "eval_loss": 0.06831000745296478, "epoch": 2.0, "percentage": 66.94, "elapsed_time": "4:00:11", "remaining_time": "1:58:38"}
27
+ {"current_steps": 250, "total_steps": 369, "loss": 0.4952, "learning_rate": 5e-06, "epoch": 2.0242914979757085, "percentage": 67.75, "elapsed_time": "4:03:49", "remaining_time": "1:56:03"}