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
a55a6fd
·
verified ·
1 Parent(s): 002cd3f

Training in progress, epoch 74

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 +5 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e8b20eed09adcdc4d206f016a96b023ba2b86cd0b9b00acc9f1d1bda3ff9d60
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0c42b8d72a64082fb1f0f986d68da9cf146ae02cd671386f86ff1144df70e4c
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08433f4401ac84bf3b6e57ddeed334395c9ff6c9714fe7346cba053d194a0add
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c59a7f6678fd2e4ba20369604d7d05c45921eee693bcc825ae26624126aefa3
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:cec2ad74ab0fc97b474753fce50ded6922323fef44eb1b1d1aa13e49d2147b88
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30dfcc788ab1833316d852f26d0601b4080db099a278cd36c319a0dc6ebac41d
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:22c4430dce037f9a378f74aab81da62ced2686bb5f78df372ce2d870c2c3ce22
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16e771ebcbd43eb904e8841187723b46853f42f9438087d734ca4790e3602446
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -421,3 +421,8 @@
421
  {"current_steps": 3480, "total_steps": 4183, "loss": 0.0036, "lr": 5e-06, "epoch": 73.84615384615384, "percentage": 83.19, "elapsed_time": "1 day, 9:25:45", "remaining_time": "6:45:11"}
422
  {"current_steps": 3487, "total_steps": 4183, "eval_loss": 2.0650992393493652, "epoch": 73.9946949602122, "percentage": 83.36, "elapsed_time": "1 day, 9:30:06", "remaining_time": "6:41:12"}
423
  {"current_steps": 3490, "total_steps": 4183, "loss": 0.0035, "lr": 5e-06, "epoch": 74.05835543766578, "percentage": 83.43, "elapsed_time": "1 day, 9:32:59", "remaining_time": "6:39:42"}
 
 
 
 
 
 
421
  {"current_steps": 3480, "total_steps": 4183, "loss": 0.0036, "lr": 5e-06, "epoch": 73.84615384615384, "percentage": 83.19, "elapsed_time": "1 day, 9:25:45", "remaining_time": "6:45:11"}
422
  {"current_steps": 3487, "total_steps": 4183, "eval_loss": 2.0650992393493652, "epoch": 73.9946949602122, "percentage": 83.36, "elapsed_time": "1 day, 9:30:06", "remaining_time": "6:41:12"}
423
  {"current_steps": 3490, "total_steps": 4183, "loss": 0.0035, "lr": 5e-06, "epoch": 74.05835543766578, "percentage": 83.43, "elapsed_time": "1 day, 9:32:59", "remaining_time": "6:39:42"}
424
+ {"current_steps": 3500, "total_steps": 4183, "loss": 0.0033, "lr": 5e-06, "epoch": 74.27055702917772, "percentage": 83.67, "elapsed_time": "1 day, 9:38:19", "remaining_time": "6:33:51"}
425
+ {"current_steps": 3510, "total_steps": 4183, "loss": 0.0035, "lr": 5e-06, "epoch": 74.48275862068965, "percentage": 83.91, "elapsed_time": "1 day, 9:43:40", "remaining_time": "6:28:00"}
426
+ {"current_steps": 3520, "total_steps": 4183, "loss": 0.0035, "lr": 5e-06, "epoch": 74.6949602122016, "percentage": 84.15, "elapsed_time": "1 day, 9:49:01", "remaining_time": "6:22:10"}
427
+ {"current_steps": 3530, "total_steps": 4183, "loss": 0.0035, "lr": 5e-06, "epoch": 74.90716180371352, "percentage": 84.39, "elapsed_time": "1 day, 9:54:21", "remaining_time": "6:16:19"}
428
+ {"current_steps": 3534, "total_steps": 4183, "eval_loss": 2.0981507301330566, "epoch": 74.9920424403183, "percentage": 84.48, "elapsed_time": "1 day, 9:57:11", "remaining_time": "6:14:07"}