Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +53 -0
- pytorch_model.bin +3 -0
- runs/Jan20_19-15-38_29985f6e87fb/1642706170.861696/events.out.tfevents.1642706170.29985f6e87fb.65.1 +3 -0
- runs/Jan20_19-15-38_29985f6e87fb/events.out.tfevents.1642706170.29985f6e87fb.65.0 +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "deepmind/language-perceiver",
|
3 |
+
"architectures": [
|
4 |
+
"PerceiverForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"audio_samples_per_frame": 1920,
|
8 |
+
"cross_attention_shape_for_attention": "kv",
|
9 |
+
"cross_attention_widening_factor": 1,
|
10 |
+
"d_latents": 1280,
|
11 |
+
"d_model": 768,
|
12 |
+
"hidden_act": "gelu",
|
13 |
+
"id2label": {
|
14 |
+
"0": "negative",
|
15 |
+
"1": "neutral",
|
16 |
+
"2": "positive"
|
17 |
+
},
|
18 |
+
"image_size": 56,
|
19 |
+
"initializer_range": 0.02,
|
20 |
+
"label2id": {
|
21 |
+
"negative": 0,
|
22 |
+
"neutral": 1,
|
23 |
+
"positive": 2
|
24 |
+
},
|
25 |
+
"layer_norm_eps": 1e-12,
|
26 |
+
"max_position_embeddings": 2048,
|
27 |
+
"model_type": "perceiver",
|
28 |
+
"num_blocks": 1,
|
29 |
+
"num_cross_attention_heads": 8,
|
30 |
+
"num_frames": 16,
|
31 |
+
"num_latents": 256,
|
32 |
+
"num_self_attends_per_block": 26,
|
33 |
+
"num_self_attention_heads": 8,
|
34 |
+
"output_shape": [
|
35 |
+
1,
|
36 |
+
16,
|
37 |
+
224,
|
38 |
+
224
|
39 |
+
],
|
40 |
+
"problem_type": "single_label_classification",
|
41 |
+
"qk_channels": 256,
|
42 |
+
"samples_per_patch": 16,
|
43 |
+
"self_attention_widening_factor": 1,
|
44 |
+
"torch_dtype": "float32",
|
45 |
+
"train_size": [
|
46 |
+
368,
|
47 |
+
496
|
48 |
+
],
|
49 |
+
"transformers_version": "4.15.0",
|
50 |
+
"use_query_residual": true,
|
51 |
+
"v_channels": 1280,
|
52 |
+
"vocab_size": 262
|
53 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c0d39f7f2c84cd12dee4738e2d40a4b7a3d6331fa91a3183df4848d5d7bfed0
|
3 |
+
size 824551789
|
runs/Jan20_19-15-38_29985f6e87fb/1642706170.861696/events.out.tfevents.1642706170.29985f6e87fb.65.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c655646c5aad425d0acf331fa5ae0e0a604b763f24b1f90d2cf0b26f4f34ea5
|
3 |
+
size 4761
|
runs/Jan20_19-15-38_29985f6e87fb/events.out.tfevents.1642706170.29985f6e87fb.65.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:30b3cf7ef609dfbab8a96466e562ace849f78d530a8811efac05eb4ce78fa88c
|
3 |
+
size 12765
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": {"content": "[BOS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "[EOS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "[SEP]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "[PAD]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "[CLS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"pad_token": {"content": "[PAD]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "[BOS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "[EOS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "[CLS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sep_token": {"content": "[SEP]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 2048, "special_tokens_map_file": "/root/.cache/huggingface/transformers/1e672f45699664b4878133bd3625998f38651ea1b4f36cb5722aff0fe0404bd8.7ff539969264e209ec2a7e131831ba24df744708e52840079a10a7a1412761fb", "tokenizer_file": null, "name_or_path": "deepmind/language-perceiver", "tokenizer_class": "PerceiverTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5863bb712e166cc2f8cc31818bb880ab744659b8bece2add13355cbbce0d4bf
|
3 |
+
size 2991
|