Hugging Face's logo

mlfoundations-dev
/
seed_math_mathcoder

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
sedrickkeh commited on
Commit
fc42993
·
verified ·
1 Parent(s): 8b81c9d

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 sha256:2ad0e30e17ed43e0838798d90328d0333d49cacb926973467259bca1ce6e41f4
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27b4e5a6155692f16e015cd0e13acf254722514766b45ceb3c0e612d8c03bc15
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f4e083fc3648f5c2e8e25d43fe8090cb6103d5b646a2ea3a0d06b09eb37511b
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e2a46383ffb84cdc952135d9725b4dc5ede5ea43695f129459c31da0091beb1
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:95f430dc6801a7e522f1a588d8ae91d1c14a810ad7c6da8cf33a095adf570c07
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:119179e1b2b2537ca8b1b97d77fb4d37fb06d4169641aebf912dbae35ebb343c
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c4d5a37068fd49d4e1fa6867a80d8e76ee22699da1f4bed219b22d299ff5dc0
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:763e42628cdc6516fd5916c9fec0df68b9428ce444d6778bb96368b2d107920f
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -1,3 +1,6 @@
1
  {"current_steps": 7, "total_steps": 21, "eval_loss": 0.2620887756347656, "epoch": 0.8888888888888888, "percentage": 33.33, "elapsed_time": "0:07:40", "remaining_time": "0:15:21"}
2
  {"current_steps": 10, "total_steps": 21, "loss": 0.4273, "lr": 5e-06, "epoch": 1.2857142857142856, "percentage": 47.62, "elapsed_time": "0:11:01", "remaining_time": "0:12:07"}
3
  {"current_steps": 15, "total_steps": 21, "eval_loss": 0.2767665386199951, "epoch": 1.9206349206349205, "percentage": 71.43, "elapsed_time": "0:16:22", "remaining_time": "0:06:33"}
 
 
 
 
1
  {"current_steps": 7, "total_steps": 21, "eval_loss": 0.2620887756347656, "epoch": 0.8888888888888888, "percentage": 33.33, "elapsed_time": "0:07:40", "remaining_time": "0:15:21"}
2
  {"current_steps": 10, "total_steps": 21, "loss": 0.4273, "lr": 5e-06, "epoch": 1.2857142857142856, "percentage": 47.62, "elapsed_time": "0:11:01", "remaining_time": "0:12:07"}
3
  {"current_steps": 15, "total_steps": 21, "eval_loss": 0.2767665386199951, "epoch": 1.9206349206349205, "percentage": 71.43, "elapsed_time": "0:16:22", "remaining_time": "0:06:33"}
4
+ {"current_steps": 20, "total_steps": 21, "loss": 0.2692, "lr": 5e-06, "epoch": 2.571428571428571, "percentage": 95.24, "elapsed_time": "0:21:56", "remaining_time": "0:01:05"}
5
+ {"current_steps": 21, "total_steps": 21, "eval_loss": 0.21467676758766174, "epoch": 2.6984126984126986, "percentage": 100.0, "elapsed_time": "0:24:17", "remaining_time": "0:00:00"}
6
+ {"current_steps": 21, "total_steps": 21, "epoch": 2.6984126984126986, "percentage": 100.0, "elapsed_time": "0:25:33", "remaining_time": "0:00:00"}