Training in progress, epoch 0
Browse files- config.json +9 -9
- model.safetensors +2 -2
- runs/Mar20_18-29-58_45f23eced1db/events.out.tfevents.1710959808.45f23eced1db.34.0 +3 -0
- runs/Mar20_18-29-58_45f23eced1db/events.out.tfevents.1710960791.45f23eced1db.34.1 +3 -0
- runs/Mar20_19-00-48_45f23eced1db/events.out.tfevents.1710961251.45f23eced1db.172.0 +3 -0
- runs/Mar20_19-09-20_45f23eced1db/events.out.tfevents.1710961763.45f23eced1db.259.0 +3 -0
- special_tokens_map.json +3 -21
- tokenizer_config.json +0 -2
- training_args.bin +1 -1
config.json
CHANGED
|
@@ -3,7 +3,7 @@
|
|
| 3 |
"VisionEncoderDecoderModel"
|
| 4 |
],
|
| 5 |
"decoder": {
|
| 6 |
-
"_name_or_path": "
|
| 7 |
"activation_function": "gelu_new",
|
| 8 |
"add_cross_attention": true,
|
| 9 |
"architectures": [
|
|
@@ -43,10 +43,10 @@
|
|
| 43 |
"min_length": 0,
|
| 44 |
"model_type": "gpt2",
|
| 45 |
"n_ctx": 1024,
|
| 46 |
-
"n_embd":
|
| 47 |
-
"n_head":
|
| 48 |
"n_inner": null,
|
| 49 |
-
"n_layer":
|
| 50 |
"n_positions": 1024,
|
| 51 |
"no_repeat_ngram_size": 0,
|
| 52 |
"num_beam_groups": 1,
|
|
@@ -96,7 +96,7 @@
|
|
| 96 |
},
|
| 97 |
"decoder_start_token_id": 50256,
|
| 98 |
"encoder": {
|
| 99 |
-
"_name_or_path": "
|
| 100 |
"add_cross_attention": false,
|
| 101 |
"architectures": [
|
| 102 |
"ViTForImageClassification"
|
|
@@ -120,7 +120,7 @@
|
|
| 120 |
"forced_eos_token_id": null,
|
| 121 |
"hidden_act": "gelu",
|
| 122 |
"hidden_dropout_prob": 0.0,
|
| 123 |
-
"hidden_size":
|
| 124 |
"id2label": {
|
| 125 |
"0": "tench, Tinca tinca",
|
| 126 |
"1": "goldfish, Carassius auratus",
|
|
@@ -1125,7 +1125,7 @@
|
|
| 1125 |
},
|
| 1126 |
"image_size": 224,
|
| 1127 |
"initializer_range": 0.02,
|
| 1128 |
-
"intermediate_size":
|
| 1129 |
"is_decoder": false,
|
| 1130 |
"is_encoder_decoder": false,
|
| 1131 |
"label2id": {
|
|
@@ -2135,7 +2135,7 @@
|
|
| 2135 |
"min_length": 0,
|
| 2136 |
"model_type": "vit",
|
| 2137 |
"no_repeat_ngram_size": 0,
|
| 2138 |
-
"num_attention_heads":
|
| 2139 |
"num_beam_groups": 1,
|
| 2140 |
"num_beams": 1,
|
| 2141 |
"num_channels": 3,
|
|
@@ -2164,7 +2164,7 @@
|
|
| 2164 |
"tokenizer_class": null,
|
| 2165 |
"top_k": 50,
|
| 2166 |
"top_p": 1.0,
|
| 2167 |
-
"torch_dtype":
|
| 2168 |
"torchscript": false,
|
| 2169 |
"typical_p": 1.0,
|
| 2170 |
"use_bfloat16": false
|
|
|
|
| 3 |
"VisionEncoderDecoderModel"
|
| 4 |
],
|
| 5 |
"decoder": {
|
| 6 |
+
"_name_or_path": "gpt2",
|
| 7 |
"activation_function": "gelu_new",
|
| 8 |
"add_cross_attention": true,
|
| 9 |
"architectures": [
|
|
|
|
| 43 |
"min_length": 0,
|
| 44 |
"model_type": "gpt2",
|
| 45 |
"n_ctx": 1024,
|
| 46 |
+
"n_embd": 768,
|
| 47 |
+
"n_head": 12,
|
| 48 |
"n_inner": null,
|
| 49 |
+
"n_layer": 12,
|
| 50 |
"n_positions": 1024,
|
| 51 |
"no_repeat_ngram_size": 0,
|
| 52 |
"num_beam_groups": 1,
|
|
|
|
| 96 |
},
|
| 97 |
"decoder_start_token_id": 50256,
|
| 98 |
"encoder": {
|
| 99 |
+
"_name_or_path": "google/vit-base-patch16-224",
|
| 100 |
"add_cross_attention": false,
|
| 101 |
"architectures": [
|
| 102 |
"ViTForImageClassification"
|
|
|
|
| 120 |
"forced_eos_token_id": null,
|
| 121 |
"hidden_act": "gelu",
|
| 122 |
"hidden_dropout_prob": 0.0,
|
| 123 |
+
"hidden_size": 768,
|
| 124 |
"id2label": {
|
| 125 |
"0": "tench, Tinca tinca",
|
| 126 |
"1": "goldfish, Carassius auratus",
|
|
|
|
| 1125 |
},
|
| 1126 |
"image_size": 224,
|
| 1127 |
"initializer_range": 0.02,
|
| 1128 |
+
"intermediate_size": 3072,
|
| 1129 |
"is_decoder": false,
|
| 1130 |
"is_encoder_decoder": false,
|
| 1131 |
"label2id": {
|
|
|
|
| 2135 |
"min_length": 0,
|
| 2136 |
"model_type": "vit",
|
| 2137 |
"no_repeat_ngram_size": 0,
|
| 2138 |
+
"num_attention_heads": 12,
|
| 2139 |
"num_beam_groups": 1,
|
| 2140 |
"num_beams": 1,
|
| 2141 |
"num_channels": 3,
|
|
|
|
| 2164 |
"tokenizer_class": null,
|
| 2165 |
"top_k": 50,
|
| 2166 |
"top_p": 1.0,
|
| 2167 |
+
"torch_dtype": null,
|
| 2168 |
"torchscript": false,
|
| 2169 |
"typical_p": 1.0,
|
| 2170 |
"use_bfloat16": false
|
model.safetensors
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 sha256:315e940cb8704045e86fade76e710b02487a0c937a6694fac76c4955b7913680
|
| 3 |
+
size 956835520
|
runs/Mar20_18-29-58_45f23eced1db/events.out.tfevents.1710959808.45f23eced1db.34.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ed520060c959d327c869474433ea11884f583f2be557800f65091d7adf35045c
|
| 3 |
+
size 81922
|
runs/Mar20_18-29-58_45f23eced1db/events.out.tfevents.1710960791.45f23eced1db.34.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71a0f4400243c7fcdab769aada5d3d4a2cd962cad5fac7ee71a3ddeee3c28ed5
|
| 3 |
+
size 81922
|
runs/Mar20_19-00-48_45f23eced1db/events.out.tfevents.1710961251.45f23eced1db.172.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e38b75aea13f56be7f09ea0c42d5909e2578c2ef7284c1a93605e5b3d92144f7
|
| 3 |
+
size 81922
|
runs/Mar20_19-09-20_45f23eced1db/events.out.tfevents.1710961763.45f23eced1db.259.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e76f6056509841d75a6913f41379ce6de9d523238ea699f34d604b837477d9d
|
| 3 |
+
size 82188
|
special_tokens_map.json
CHANGED
|
@@ -1,24 +1,6 @@
|
|
| 1 |
{
|
| 2 |
-
"bos_token":
|
| 3 |
-
|
| 4 |
-
"lstrip": false,
|
| 5 |
-
"normalized": true,
|
| 6 |
-
"rstrip": false,
|
| 7 |
-
"single_word": false
|
| 8 |
-
},
|
| 9 |
-
"eos_token": {
|
| 10 |
-
"content": "<|endoftext|>",
|
| 11 |
-
"lstrip": false,
|
| 12 |
-
"normalized": true,
|
| 13 |
-
"rstrip": false,
|
| 14 |
-
"single_word": false
|
| 15 |
-
},
|
| 16 |
"pad_token": "<|endoftext|>",
|
| 17 |
-
"unk_token":
|
| 18 |
-
"content": "<|endoftext|>",
|
| 19 |
-
"lstrip": false,
|
| 20 |
-
"normalized": true,
|
| 21 |
-
"rstrip": false,
|
| 22 |
-
"single_word": false
|
| 23 |
-
}
|
| 24 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"pad_token": "<|endoftext|>",
|
| 5 |
+
"unk_token": "<|endoftext|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
}
|
tokenizer_config.json
CHANGED
|
@@ -1,5 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"add_bos_token": false,
|
| 3 |
"add_prefix_space": false,
|
| 4 |
"added_tokens_decoder": {
|
| 5 |
"50256": {
|
|
@@ -14,7 +13,6 @@
|
|
| 14 |
"bos_token": "<|endoftext|>",
|
| 15 |
"clean_up_tokenization_spaces": true,
|
| 16 |
"eos_token": "<|endoftext|>",
|
| 17 |
-
"errors": "replace",
|
| 18 |
"model_max_length": 1024,
|
| 19 |
"pad_token": "<|endoftext|>",
|
| 20 |
"tokenizer_class": "GPT2Tokenizer",
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"add_prefix_space": false,
|
| 3 |
"added_tokens_decoder": {
|
| 4 |
"50256": {
|
|
|
|
| 13 |
"bos_token": "<|endoftext|>",
|
| 14 |
"clean_up_tokenization_spaces": true,
|
| 15 |
"eos_token": "<|endoftext|>",
|
|
|
|
| 16 |
"model_max_length": 1024,
|
| 17 |
"pad_token": "<|endoftext|>",
|
| 18 |
"tokenizer_class": "GPT2Tokenizer",
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5048
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a56a8c87d0f8ff727b696024fc1dc35eb2c3ac75417c10c2d724d9e20de85c6
|
| 3 |
size 5048
|