Training in progress, epoch 1
Browse files- config.json +1 -12
- pytorch_model.bin +2 -2
- training_args.bin +1 -1
config.json
CHANGED
@@ -22,19 +22,8 @@
|
|
22 |
"pad_token_id": 1,
|
23 |
"position_embedding_type": "rotary",
|
24 |
"problem_type": "single_label_classification",
|
25 |
-
"quantization_config": {
|
26 |
-
"bnb_4bit_compute_dtype": "float32",
|
27 |
-
"bnb_4bit_quant_type": "fp4",
|
28 |
-
"bnb_4bit_use_double_quant": false,
|
29 |
-
"llm_int8_enable_fp32_cpu_offload": false,
|
30 |
-
"llm_int8_has_fp16_weight": false,
|
31 |
-
"llm_int8_skip_modules": null,
|
32 |
-
"llm_int8_threshold": 6.0,
|
33 |
-
"load_in_4bit": false,
|
34 |
-
"load_in_8bit": true
|
35 |
-
},
|
36 |
"token_dropout": true,
|
37 |
-
"torch_dtype": "
|
38 |
"transformers_version": "4.31.0",
|
39 |
"use_cache": true,
|
40 |
"vocab_list": null,
|
|
|
22 |
"pad_token_id": 1,
|
23 |
"position_embedding_type": "rotary",
|
24 |
"problem_type": "single_label_classification",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
25 |
"token_dropout": true,
|
26 |
+
"torch_dtype": "float32",
|
27 |
"transformers_version": "4.31.0",
|
28 |
"use_cache": true,
|
29 |
"vocab_list": null,
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fbafb3bbca982740175cabf68ac5f591354fa1f164bff086d4651b159973f6b7
|
3 |
+
size 2609624697
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4027
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed234b1823f669796312a7d2385490a2c047dbd7a9ad601142b6b79af633e56a
|
3 |
size 4027
|