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 Community
sedrickkeh commited on
Commit
ce158ff
·
verified ·
1 Parent(s): 5fef341

Training in progress, epoch 3

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 +4 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7a67e1e61a10e442ed951858b3f2e77e750cbdee96d586322efeee153825397b
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f4acd51df4d514960caf47fe77054657acf5c37cfcc6d1f50a3de8191b88fda
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:356312f6254806f48269690927de5df5c3abc6dc8d6b63748d094bbb3dcb3a6c
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2874cf871cb4194a5138be849d37990ed4188cfe218551ab8a6a09694784b169
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:03928f387fbf026ae42e8d301b6296b804012ed6877374cd675de0e6d8b52ffb
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b803629de7a44a19c7fcd4027d3b9af85c96d12235cce63ef370a0ec5432971
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:91d2ebf98ef18d7872165ba548662d804e6b962544a7a98752e3561499919aa4
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a93b031919f9726c30f18bbd2e1fe14adc586e4547bbd80dab38dbc0e0fcf68
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -4,3 +4,7 @@
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"}
 
 
 
 
 
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"}
7
+ {"current_steps": 50, "total_steps": 60, "loss": 0.2959, "lr": 5e-06, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "0:51:39", "remaining_time": "0:10:19"}
8
+ {"current_steps": 60, "total_steps": 60, "loss": 0.2852, "lr": 5e-06, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:01:21", "remaining_time": "0:00:00"}
9
+ {"current_steps": 60, "total_steps": 60, "eval_loss": 0.2846110165119171, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:02:56", "remaining_time": "0:00:00"}
10
+ {"current_steps": 60, "total_steps": 60, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:04:12", "remaining_time": "0:00:00"}