Hugging Face's logo

mlfoundations-dev
/
seed_math_math_instruct

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
sedrickkeh commited on
Commit
5fef341
·
verified ·
1 Parent(s): 74929af

Training in progress, epoch 2

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:c567eb671bc467047a1ecd2c527f2fb965853b9d9b91ff8b885c34045a0d67d6
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a67e1e61a10e442ed951858b3f2e77e750cbdee96d586322efeee153825397b
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:ac370f7cb146d181b9abdd891ed5c822b1d7902266d5e39197a6136f1a32d91d
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:356312f6254806f48269690927de5df5c3abc6dc8d6b63748d094bbb3dcb3a6c
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:f4cfdf21aeaac5c9c6b22808d94d717bfbc8cec4cc7822e0e5ec740a0a3ca24c
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03928f387fbf026ae42e8d301b6296b804012ed6877374cd675de0e6d8b52ffb
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3ca4c34a040b2d839f95f8525785da078afa1c58f08a5fe4f2b3e5c018c91f46
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91d2ebf98ef18d7872165ba548662d804e6b962544a7a98752e3561499919aa4
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -1,3 +1,6 @@
1
  {"current_steps": 10, "total_steps": 60, "loss": 0.523, "lr": 5e-06, "epoch": 0.5, "percentage": 16.67, "elapsed_time": "0:09:44", "remaining_time": "0:48:41"}
2
  {"current_steps": 20, "total_steps": 60, "loss": 0.386, "lr": 5e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:19:26", "remaining_time": "0:38:52"}
3
  {"current_steps": 20, "total_steps": 60, "eval_loss": 0.34043166041374207, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:19:49", "remaining_time": "0:39:38"}
 
 
 
 
1
  {"current_steps": 10, "total_steps": 60, "loss": 0.523, "lr": 5e-06, "epoch": 0.5, "percentage": 16.67, "elapsed_time": "0:09:44", "remaining_time": "0:48:41"}
2
  {"current_steps": 20, "total_steps": 60, "loss": 0.386, "lr": 5e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:19:26", "remaining_time": "0:38:52"}
3
  {"current_steps": 20, "total_steps": 60, "eval_loss": 0.34043166041374207, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:19:49", "remaining_time": "0:39:38"}
4
+ {"current_steps": 30, "total_steps": 60, "loss": 0.3382, "lr": 5e-06, "epoch": 1.5, "percentage": 50.0, "elapsed_time": "0:30:39", "remaining_time": "0:30:39"}
5
+ {"current_steps": 40, "total_steps": 60, "loss": 0.3162, "lr": 5e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:40:22", "remaining_time": "0:20:11"}
6
+ {"current_steps": 40, "total_steps": 60, "eval_loss": 0.3004086911678314, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:40:45", "remaining_time": "0:20:22"}