Training in progress, step 200
Browse files- config.json +42 -0
- model.safetensors +3 -0
- runs/Sep29_06-54-10_iit-p/events.out.tfevents.1727573055.iit-p +3 -0
- runs/Sep29_06-54-52_iit-p/events.out.tfevents.1727573098.iit-p +3 -0
- runs/Sep29_06-56-13_iit-p/events.out.tfevents.1727573180.iit-p +3 -0
- runs/Sep29_06-57-01_iit-p/events.out.tfevents.1727573227.iit-p +3 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/flan-t5-large",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"classifier_dropout": 0.0,
|
| 7 |
+
"d_ff": 2816,
|
| 8 |
+
"d_kv": 64,
|
| 9 |
+
"d_model": 1024,
|
| 10 |
+
"decoder_start_token_id": 0,
|
| 11 |
+
"dense_act_fn": "gelu_new",
|
| 12 |
+
"dropout_rate": 0.1,
|
| 13 |
+
"eos_token_id": 1,
|
| 14 |
+
"feed_forward_proj": "gated-gelu",
|
| 15 |
+
"id2label": {
|
| 16 |
+
"0": "0",
|
| 17 |
+
"1": "1"
|
| 18 |
+
},
|
| 19 |
+
"initializer_factor": 1.0,
|
| 20 |
+
"is_encoder_decoder": true,
|
| 21 |
+
"is_gated_act": true,
|
| 22 |
+
"label2id": {
|
| 23 |
+
"0": 0,
|
| 24 |
+
"1": 1
|
| 25 |
+
},
|
| 26 |
+
"layer_norm_epsilon": 1e-06,
|
| 27 |
+
"model_type": "t5",
|
| 28 |
+
"n_positions": 512,
|
| 29 |
+
"num_decoder_layers": 24,
|
| 30 |
+
"num_heads": 16,
|
| 31 |
+
"num_layers": 24,
|
| 32 |
+
"output_past": true,
|
| 33 |
+
"pad_token_id": 0,
|
| 34 |
+
"problem_type": "single_label_classification",
|
| 35 |
+
"relative_attention_max_distance": 128,
|
| 36 |
+
"relative_attention_num_buckets": 32,
|
| 37 |
+
"tie_word_embeddings": false,
|
| 38 |
+
"torch_dtype": "float32",
|
| 39 |
+
"transformers_version": "4.44.2",
|
| 40 |
+
"use_cache": true,
|
| 41 |
+
"vocab_size": 32128
|
| 42 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71d354d7051a86799a3454a08a5a4ca3ac980025b01ac03858b2ad83c6554696
|
| 3 |
+
size 3005286112
|
runs/Sep29_06-54-10_iit-p/events.out.tfevents.1727573055.iit-p
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc6b1d06a9286d3b27a230ed0eb0c008b3436e50c54575fe2ded2732791fbd59
|
| 3 |
+
size 4195
|
runs/Sep29_06-54-52_iit-p/events.out.tfevents.1727573098.iit-p
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:202027042c647e5ada20e5d7c62a699f057ddabf53c2c478a12eb5d45c8a1aa9
|
| 3 |
+
size 4195
|
runs/Sep29_06-56-13_iit-p/events.out.tfevents.1727573180.iit-p
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc9a8c487f4cc2f5b9e7627cfa2b93e965d3c255d478534e575f56dbfdb7f4db
|
| 3 |
+
size 4195
|
runs/Sep29_06-57-01_iit-p/events.out.tfevents.1727573227.iit-p
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bfee1365f60144a9a4d49432623ebfb2ca1962dd7b303b2aacc40fd6a7909ade
|
| 3 |
+
size 5850
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8cb61399f5b2cbe54922b05d8f397cc8c38dbc84595670529608ebc666c9c937
|
| 3 |
+
size 5240
|