Hugging Face's logo

parth0908
/
peft-starcoder-finetuned

PEFT
TensorBoard
Safetensors
gpt_bigcode
Generated from Trainer
Model card Files Metrics Community
parth0908 commited on
Commit
0ae049b
•
1 Parent(s): fe9784b

Training in progress, step 2000

Browse files
Files changed (14) hide show
  1. config.json +39 -0
  2. model.safetensors +3 -0
  3. runs/Nov16_17-41-30_localhost/events.out.tfevents.1731759091.localhost +3 -0
  4. runs/Nov16_17-46-03_localhost/events.out.tfevents.1731759364.localhost +3 -0
  5. runs/Nov16_17-50-21_localhost/events.out.tfevents.1731759622.localhost +3 -0
  6. runs/Nov16_17-56-31_localhost/events.out.tfevents.1731759991.localhost +3 -0
  7. runs/Nov16_21-07-16_localhost/events.out.tfevents.1731771437.localhost +3 -0
  8. runs/Nov16_21-33-57_localhost/events.out.tfevents.1731773039.localhost +3 -0
  9. runs/Nov16_21-56-09_localhost/events.out.tfevents.1731774370.localhost +3 -0
  10. runs/Nov16_22-25-58_localhost/events.out.tfevents.1731776162.localhost +3 -0
  11. runs/Nov16_22-31-21_localhost/events.out.tfevents.1731776483.localhost +3 -0
  12. runs/Nov16_22-34-27_localhost/events.out.tfevents.1731776669.localhost +3 -0
  13. runs/Nov17_00-07-21_localhost/events.out.tfevents.1731782243.localhost +3 -0
  14. training_args.bin +2 -2
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bigcode/starcoderbase-1b",
3
+ "activation_function": "gelu_pytorch_tanh",
4
+ "architectures": [
5
+ "GPTBigCodeForCausalLM"
6
+ ],
7
+ "attention_softmax_in_fp32": true,
8
+ "attn_pdrop": 0.1,
9
+ "bos_token_id": 0,
10
+ "embd_pdrop": 0.1,
11
+ "eos_token_id": 0,
12
+ "inference_runner": 0,
13
+ "initializer_range": 0.02,
14
+ "layer_norm_epsilon": 1e-05,
15
+ "max_batch_size": null,
16
+ "max_sequence_length": null,
17
+ "model_type": "gpt_bigcode",
18
+ "multi_query": true,
19
+ "n_embd": 2048,
20
+ "n_head": 16,
21
+ "n_inner": 8192,
22
+ "n_layer": 24,
23
+ "n_positions": 8192,
24
+ "pad_key_length": true,
25
+ "pre_allocate_kv_cache": false,
26
+ "resid_pdrop": 0.1,
27
+ "scale_attention_softmax_in_fp32": true,
28
+ "scale_attn_weights": true,
29
+ "summary_activation": null,
30
+ "summary_first_dropout": 0.1,
31
+ "summary_proj_to_labels": true,
32
+ "summary_type": "cls_index",
33
+ "summary_use_proj": true,
34
+ "torch_dtype": "float16",
35
+ "transformers_version": "4.46.2",
36
+ "use_cache": false,
37
+ "validate_runner_input": true,
38
+ "vocab_size": 49152
39
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe3fee2b70d55209c282d583d308213b7bfc68441f9a5f1f657e2c124d8eee5e
3
+ size 2274445000
runs/Nov16_17-41-30_localhost/events.out.tfevents.1731759091.localhost ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f014be15c27cb91ce731632274def1ea4dd4a7f4fe4e185ef8c54a6969ef2dd6
3
+ size 5405
runs/Nov16_17-46-03_localhost/events.out.tfevents.1731759364.localhost ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:807f4b24d9f026fdf0f25a07c0f5269498a10515e2bdd9d6b17b81e80da2f8e9
3
+ size 5405
runs/Nov16_17-50-21_localhost/events.out.tfevents.1731759622.localhost ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6289079d5dc40be0574fd1969acc5adbe1da300be6dd4595de0cc9315e5ff9a4
3
+ size 5405
runs/Nov16_17-56-31_localhost/events.out.tfevents.1731759991.localhost ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f2433f3cb45600c40c3706131323e8572788da1ce67e5ea194d054b058d8e6f
3
+ size 6084
runs/Nov16_21-07-16_localhost/events.out.tfevents.1731771437.localhost ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6672952e89b13edb4628a2e55b59f2b50a4fc2e9e4cace21bdd6184a26dd0c57
3
+ size 5818
runs/Nov16_21-33-57_localhost/events.out.tfevents.1731773039.localhost ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb6c6255b9bf13b258d372ef0881ad83699a17dd55b52710587286626b9fc6aa
3
+ size 5611
runs/Nov16_21-56-09_localhost/events.out.tfevents.1731774370.localhost ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7d3ed0ef68fdc7938add8f938467fdc501d2a22862166691233c8361e3a1e84
3
+ size 7444
runs/Nov16_22-25-58_localhost/events.out.tfevents.1731776162.localhost ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:254b82634d44726019aa98e4d8333218a132fa3bc2952ecd555b034b7bf2f622
3
+ size 5400
runs/Nov16_22-31-21_localhost/events.out.tfevents.1731776483.localhost ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cc5a84a46e0be34073ae8f7740454bc2d59be22ab71622c5c04905857a249a5
3
+ size 4262
runs/Nov16_22-34-27_localhost/events.out.tfevents.1731776669.localhost ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4cd834f7f2fde750946c71809f9282a583818f53ee087881f1f36d3e0ea610e
3
+ size 7854
runs/Nov17_00-07-21_localhost/events.out.tfevents.1731782243.localhost ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cedb5f398e779854ea209449aef0c6cc572eca211dbaba5cb00611f57c634ed
3
+ size 19606
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:798ba988e0527117931043335121d25a5946700261810a929743ab8d139c41ab
3
- size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa42ca44218fc8c801de5af36377d87895d26ab0eb0d7aab7ba93fb9d218be55
3
+ size 5304