Hugging Face's logo

sedrickkeh
/
checkpoints

Text Generation
Transformers
Safetensors
gemma2
llama-factory
full
trl
dpo
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
sedrickkeh commited on
Commit
a75f56c
·
verified ·
1 Parent(s): a371b3f

Training in progress, epoch 0

Browse files
Files changed (6) 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 +2 -10
  6. training_args.bin +1 -1
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5fe539379e2d7db955eeb676cd8d9f54e2e235f030bf3e11e1e28087bf9a2d87
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73c53aebc6ee435f5c78778bb1d720c034e0cf14545bd533296835984981be7e
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6464d95d51be7644f72596bcb8be974b9763735a7b9f9716f6fc23a9cbb258a6
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:762d72415b982da7d54dd523faa800c82053c57c76a4e9eadff6917b8a12d81a
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2411be315fd7e1c238c0c358255a9ca8cb559ac7c9f9df7d3145fc0374654aa2
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1379e9cc25286428a50f34378dcd51e4672ddfa50b5a36c827fc633121e5c1a
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ea974b209c1000324a60d7522f76fad8acd259f36bb4d3acf7b044acf4b1b0b
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e30fa23a78b99d053e5fba93c17133de4c4b3389384d6b082640f7e73a7181c
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -1,10 +1,2 @@
1
- {"current_steps": 1, "total_steps": 9, "loss": 1.9082, "learning_rate": 5e-06, "epoch": 0.26666666666666666, "percentage": 11.11, "elapsed_time": "0:00:29", "remaining_time": "0:03:59"}
2
- {"current_steps": 2, "total_steps": 9, "loss": 1.829, "learning_rate": 5e-06, "epoch": 0.5333333333333333, "percentage": 22.22, "elapsed_time": "0:00:59", "remaining_time": "0:03:27"}
3
- {"current_steps": 3, "total_steps": 9, "loss": 1.7257, "learning_rate": 5e-06, "epoch": 0.8, "percentage": 33.33, "elapsed_time": "0:01:28", "remaining_time": "0:02:57"}
4
- {"current_steps": 3, "total_steps": 9, "eval_loss": NaN, "epoch": 0.8, "percentage": 33.33, "elapsed_time": "0:01:51", "remaining_time": "0:03:43"}
5
- {"current_steps": 4, "total_steps": 9, "loss": 0.0, "learning_rate": 5e-06, "epoch": 1.0666666666666667, "percentage": 44.44, "elapsed_time": "0:03:21", "remaining_time": "0:04:12"}
6
- {"current_steps": 5, "total_steps": 9, "loss": 0.0, "learning_rate": 5e-06, "epoch": 1.3333333333333333, "percentage": 55.56, "elapsed_time": "0:03:51", "remaining_time": "0:03:05"}
7
- {"current_steps": 6, "total_steps": 9, "loss": 0.0, "learning_rate": 5e-06, "epoch": 1.6, "percentage": 66.67, "elapsed_time": "0:04:20", "remaining_time": "0:02:10"}
8
- {"current_steps": 7, "total_steps": 9, "loss": 0.0, "learning_rate": 5e-06, "epoch": 1.8666666666666667, "percentage": 77.78, "elapsed_time": "0:04:49", "remaining_time": "0:01:22"}
9
- {"current_steps": 7, "total_steps": 9, "eval_loss": NaN, "epoch": 1.8666666666666667, "percentage": 77.78, "elapsed_time": "0:05:05", "remaining_time": "0:01:27"}
10
- {"current_steps": 8, "total_steps": 9, "loss": 0.0, "learning_rate": 5e-06, "epoch": 2.1333333333333333, "percentage": 88.89, "elapsed_time": "0:06:46", "remaining_time": "0:00:50"}
 
1
+ {"current_steps": 3, "total_steps": 9, "eval_loss": 1.67874276638031, "epoch": 0.8, "percentage": 33.33, "elapsed_time": "0:01:52", "remaining_time": "0:03:45"}
2
+ {"current_steps": 7, "total_steps": 9, "eval_loss": NaN, "epoch": 1.8666666666666667, "percentage": 77.78, "elapsed_time": "0:05:06", "remaining_time": "0:01:27"}
 
 
 
 
 
 
 
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59b134d213eed746340b280ef13b873c711f02d68ac55523ea3cc50a307053bc
3
  size 6776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46b125cf5d6eb88a6f5b6ffb0ea91abf97d7c96474a2f2f1e326375f629887c5
3
  size 6776