sivan22 commited on
Commit
fdc4b3e
1 Parent(s): 3947bd0

Training in progress, step 2500

Browse files
config.json CHANGED
@@ -1,7 +1,10 @@
1
  {
2
  "_commit_hash": null,
 
 
 
3
  "decoder": {
4
- "_name_or_path": "imvladikon/alephbertgimmel-base-512",
5
  "add_cross_attention": true,
6
  "architectures": [
7
  "BertForMaskedLM"
@@ -76,13 +79,13 @@
76
  "torch_dtype": null,
77
  "torchscript": false,
78
  "transformers_version": "4.28.1",
79
- "type_vocab_size": 2,
80
  "typical_p": 1.0,
81
  "use_bfloat16": false,
82
  "use_cache": true,
83
- "vocab_size": 128000
84
  },
85
- "decoder_start_token_id": 1,
86
  "early_stopping": true,
87
  "encoder": {
88
  "_name_or_path": "google/vit-base-patch16-224-in21k",
@@ -164,15 +167,16 @@
164
  "typical_p": 1.0,
165
  "use_bfloat16": false
166
  },
167
- "eos_token_id": 2,
168
  "is_encoder_decoder": true,
169
  "length_penalty": 2.0,
170
- "max_length": 4,
171
  "model_type": "vision-encoder-decoder",
172
  "no_repeat_ngram_size": 3,
173
  "num_beams": 4,
174
- "pad_token_id": 3,
175
  "tie_word_embeddings": false,
 
176
  "transformers_version": null,
177
- "vocab_size": 128000
178
  }
 
1
  {
2
  "_commit_hash": null,
3
+ "architectures": [
4
+ "VisionEncoderDecoderModel"
5
+ ],
6
  "decoder": {
7
+ "_name_or_path": "onlplab/alephbert-base",
8
  "add_cross_attention": true,
9
  "architectures": [
10
  "BertForMaskedLM"
 
79
  "torch_dtype": null,
80
  "torchscript": false,
81
  "transformers_version": "4.28.1",
82
+ "type_vocab_size": 1,
83
  "typical_p": 1.0,
84
  "use_bfloat16": false,
85
  "use_cache": true,
86
+ "vocab_size": 52000
87
  },
88
+ "decoder_start_token_id": 2,
89
  "early_stopping": true,
90
  "encoder": {
91
  "_name_or_path": "google/vit-base-patch16-224-in21k",
 
167
  "typical_p": 1.0,
168
  "use_bfloat16": false
169
  },
170
+ "eos_token_id": 3,
171
  "is_encoder_decoder": true,
172
  "length_penalty": 2.0,
173
+ "max_length": 5,
174
  "model_type": "vision-encoder-decoder",
175
  "no_repeat_ngram_size": 3,
176
  "num_beams": 4,
177
+ "pad_token_id": 0,
178
  "tie_word_embeddings": false,
179
+ "torch_dtype": "float32",
180
  "transformers_version": null,
181
+ "vocab_size": 52000
182
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ee2c6f549fa2f9541b26b5c6f063fde015dcef40eba3af9c2a6c0bdd85fd98d
3
- size 1197111289
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:865f5978fd554caffca001fca84089c3fd7a48e80f6bb909dc1dc2b50b6d88f9
3
+ size 963332153
runs/May18_20-54-14_b5b0e8d5e2bb/1684443638.8033147/events.out.tfevents.1684443638.b5b0e8d5e2bb.31.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12a026e11d1694e4f0232c70b8539386976e0f82165b392fe4440200ee59dc7e
3
+ size 6110
runs/May18_20-54-14_b5b0e8d5e2bb/events.out.tfevents.1684443638.b5b0e8d5e2bb.31.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96c999cc7f8678322f98fad10fcc5cf031ed58d38cb897fa3cad3f3025e0d7bd
3
+ size 204958
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d415711f902130199574557cc354cc65dd6331dbfea11f02fb8b35dfb17c2866
3
  size 3771
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9fa47d41396598585d7ce306df647931184ae087af3d20a550b324155b4e149
3
  size 3771