Hugging Face's logo

mlfoundations-dev
/
seed_math_open2math

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
sedrickkeh commited on
Commit
312dccb
·
verified ·
1 Parent(s): 493bb2c

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 +4 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f920013b9c2debe1ab68254603d55bb59413413f509ee0df7c4f4af733187167
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:900f30c2f16e8e15231a969141ff7834965455b6a421c5ed2b5fe32bd7d31696
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:022beb8ba74db7b8739e5226144e47f820cce9e6167a171d457da72fff9ed1cd
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:542efee75928c5b488298120fff4313037ef2866c12a4948a913255cadc1c98b
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:f2a1e9ee6269901a20a909d37e591ecf809671f1d60f8496ed5f78b3384d72d5
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6a2bf2ea06ee00021eee45770c33f4702d583335ffceaedc4a0b08ac1e0a2f3
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:c42bd06c99684dd0d45283b0efaa8d444a1bb1b841462e83e459af3e5107494e
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b1cefe296648616a03eb14fffb41ef0f96da67cef395df32bca29ea131eb314
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -2,3 +2,7 @@
2
  {"current_steps": 20, "total_steps": 96, "loss": 0.5117, "lr": 5e-06, "epoch": 0.6130268199233716, "percentage": 20.83, "elapsed_time": "0:19:24", "remaining_time": "1:13:46"}
3
  {"current_steps": 30, "total_steps": 96, "loss": 0.4837, "lr": 5e-06, "epoch": 0.9195402298850575, "percentage": 31.25, "elapsed_time": "0:29:04", "remaining_time": "1:03:57"}
4
  {"current_steps": 32, "total_steps": 96, "eval_loss": 0.45525598526000977, "epoch": 0.9808429118773946, "percentage": 33.33, "elapsed_time": "0:31:50", "remaining_time": "1:03:41"}
 
 
 
 
 
2
  {"current_steps": 20, "total_steps": 96, "loss": 0.5117, "lr": 5e-06, "epoch": 0.6130268199233716, "percentage": 20.83, "elapsed_time": "0:19:24", "remaining_time": "1:13:46"}
3
  {"current_steps": 30, "total_steps": 96, "loss": 0.4837, "lr": 5e-06, "epoch": 0.9195402298850575, "percentage": 31.25, "elapsed_time": "0:29:04", "remaining_time": "1:03:57"}
4
  {"current_steps": 32, "total_steps": 96, "eval_loss": 0.45525598526000977, "epoch": 0.9808429118773946, "percentage": 33.33, "elapsed_time": "0:31:50", "remaining_time": "1:03:41"}
5
+ {"current_steps": 40, "total_steps": 96, "loss": 0.4907, "lr": 5e-06, "epoch": 1.2375478927203065, "percentage": 41.67, "elapsed_time": "0:40:30", "remaining_time": "0:56:42"}
6
+ {"current_steps": 50, "total_steps": 96, "loss": 0.4442, "lr": 5e-06, "epoch": 1.5440613026819925, "percentage": 52.08, "elapsed_time": "0:50:12", "remaining_time": "0:46:11"}
7
+ {"current_steps": 60, "total_steps": 96, "loss": 0.4322, "lr": 5e-06, "epoch": 1.8505747126436782, "percentage": 62.5, "elapsed_time": "0:59:53", "remaining_time": "0:35:55"}
8
+ {"current_steps": 64, "total_steps": 96, "eval_loss": 0.4297981858253479, "epoch": 1.9731800766283525, "percentage": 66.67, "elapsed_time": "1:04:49", "remaining_time": "0:32:24"}