Hugging Face's logo

mlfoundations-dev
/
oh_v3-1_only_metamath_40k

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
esfrankel17 commited on
Commit
272fc5e
·
verified ·
1 Parent(s): 40a2f18

Training in progress, epoch 1

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 +3 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d7fc75b3034615768644e05d502168764a5e23253f7a8f279d54191c3461564a
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90d55bf7af01f1578948925e98359218c72b29643801e8c5c07b8119099e7328
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:c56c2e4fb0210719e75e3655ab9ddb723c3bddcadc2022ff54964a8c6acf36b3
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:362ef6362626c236134434502d1d8de8a606bd4af857c96460f23c416008c2d8
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:cb129ba9327ff0388e52240b3b5c64f53727ecede80f9ddeecf81a58b509acb5
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:992820d125a299a41788ee7bea10f78ac2e2b4952a3997fe224bd56ed5796497
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9603bc21dfc9c6ac67d7b9062947c24dc2317447c919ece60d6f8d9120bef7b5
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bf0d01966c107a3c258d95901a64f0e5cc0caaf2f57744b2c92d9a3c4d0595e
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -1,2 +1,5 @@
1
  {"current_steps": 10, "total_steps": 45, "loss": 0.4671, "learning_rate": 5e-06, "epoch": 0.642570281124498, "percentage": 22.22, "elapsed_time": "0:45:08", "remaining_time": "2:38:01"}
2
  {"current_steps": 15, "total_steps": 45, "eval_loss": 0.33529338240623474, "epoch": 0.963855421686747, "percentage": 33.33, "elapsed_time": "1:11:28", "remaining_time": "2:22:57"}
 
 
 
 
1
  {"current_steps": 10, "total_steps": 45, "loss": 0.4671, "learning_rate": 5e-06, "epoch": 0.642570281124498, "percentage": 22.22, "elapsed_time": "0:45:08", "remaining_time": "2:38:01"}
2
  {"current_steps": 15, "total_steps": 45, "eval_loss": 0.33529338240623474, "epoch": 0.963855421686747, "percentage": 33.33, "elapsed_time": "1:11:28", "remaining_time": "2:22:57"}
3
+ {"current_steps": 20, "total_steps": 45, "loss": 0.3359, "learning_rate": 5e-06, "epoch": 1.285140562248996, "percentage": 44.44, "elapsed_time": "1:32:44", "remaining_time": "1:55:55"}
4
+ {"current_steps": 30, "total_steps": 45, "loss": 0.3019, "learning_rate": 5e-06, "epoch": 1.927710843373494, "percentage": 66.67, "elapsed_time": "2:17:49", "remaining_time": "1:08:54"}
5
+ {"current_steps": 31, "total_steps": 45, "eval_loss": 0.2970140278339386, "epoch": 1.9919678714859437, "percentage": 68.89, "elapsed_time": "2:24:08", "remaining_time": "1:05:05"}