Hugging Face's logo

mlfoundations-dev
/
oh_scale_x.125_compute_equal

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
sedrickkeh commited on
Commit
f41365e
·
verified ·
1 Parent(s): 420dfee

Training in progress, epoch 80

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 +6 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b68319b67ba69d9c390e0c4616c6c9bbba179deebbffbaa572c80eb0737177ad
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f8ee349fa758afe45d8d90b3d0ce54ed65df755c01bcf34c44afb7831b462f0
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:c3d6127ab08148c373cb808eacd8cc775e12935a3377674bda045396de8573b2
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed37d7c5ecc5ab7666e0e1ad06a0398f9a1f2ccdc23dd26be3e88272a7bd517b
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ffacbbae02aa0732a968d2093827900eefa54b7a2b16579e289670c1c19b962
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:079d12f03040d3b9021a71d0b59836d0e9dd8cd92bbbb11d1b4f1a0b63a78dca
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:d9ad8729689452ec97a1d22b1c628ad347e451e02c1a761094556f1a94426ab9
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1ef42f571c64f2b74e5fe30b52e55f55667cd42f5f3ca2ad48e8b4fc0df2c35
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -449,3 +449,9 @@
449
  {"current_steps": 3710, "total_steps": 4183, "loss": 0.0032, "lr": 5e-06, "epoch": 78.72679045092838, "percentage": 88.69, "elapsed_time": "1 day, 11:40:10", "remaining_time": "4:32:51"}
450
  {"current_steps": 3720, "total_steps": 4183, "loss": 0.0031, "lr": 5e-06, "epoch": 78.93899204244032, "percentage": 88.93, "elapsed_time": "1 day, 11:45:33", "remaining_time": "4:27:02"}
451
  {"current_steps": 3722, "total_steps": 4183, "eval_loss": 2.0912187099456787, "epoch": 78.9814323607427, "percentage": 88.98, "elapsed_time": "1 day, 11:47:33", "remaining_time": "4:25:59"}
 
 
 
 
 
 
 
449
  {"current_steps": 3710, "total_steps": 4183, "loss": 0.0032, "lr": 5e-06, "epoch": 78.72679045092838, "percentage": 88.69, "elapsed_time": "1 day, 11:40:10", "remaining_time": "4:32:51"}
450
  {"current_steps": 3720, "total_steps": 4183, "loss": 0.0031, "lr": 5e-06, "epoch": 78.93899204244032, "percentage": 88.93, "elapsed_time": "1 day, 11:45:33", "remaining_time": "4:27:02"}
451
  {"current_steps": 3722, "total_steps": 4183, "eval_loss": 2.0912187099456787, "epoch": 78.9814323607427, "percentage": 88.98, "elapsed_time": "1 day, 11:47:33", "remaining_time": "4:25:59"}
452
+ {"current_steps": 3730, "total_steps": 4183, "loss": 0.0032, "lr": 5e-06, "epoch": 79.15119363395226, "percentage": 89.17, "elapsed_time": "1 day, 11:53:00", "remaining_time": "4:21:28"}
453
+ {"current_steps": 3740, "total_steps": 4183, "loss": 0.0031, "lr": 5e-06, "epoch": 79.36339522546419, "percentage": 89.41, "elapsed_time": "1 day, 11:58:34", "remaining_time": "4:15:40"}
454
+ {"current_steps": 3750, "total_steps": 4183, "loss": 0.0031, "lr": 5e-06, "epoch": 79.57559681697613, "percentage": 89.65, "elapsed_time": "1 day, 12:04:11", "remaining_time": "4:09:53"}
455
+ {"current_steps": 3760, "total_steps": 4183, "loss": 0.0034, "lr": 5e-06, "epoch": 79.78779840848806, "percentage": 89.89, "elapsed_time": "1 day, 12:09:45", "remaining_time": "4:04:05"}
456
+ {"current_steps": 3770, "total_steps": 4183, "loss": 0.0035, "lr": 5e-06, "epoch": 80.0, "percentage": 90.13, "elapsed_time": "1 day, 12:15:13", "remaining_time": "3:58:17"}
457
+ {"current_steps": 3770, "total_steps": 4183, "eval_loss": 2.0766139030456543, "epoch": 80.0, "percentage": 90.13, "elapsed_time": "1 day, 12:15:49", "remaining_time": "3:58:21"}