Training in progress, step 500

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,193 @@
+{
+  "_commit_hash": null,
+  "architectures": [
+    "VisionEncoderDecoderModel"
+  ],
+  "decoder": {
+    "_name_or_path": "distilgpt2",
+    "_num_labels": 1,
+    "activation_function": "gelu_new",
+    "add_cross_attention": true,
+    "architectures": [
+      "GPT2LMHeadModel"
+    ],
+    "attn_pdrop": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 50256,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "embd_pdrop": 0.1,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 50256,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "id2label": {
+      "0": "LABEL_0"
+    },
+    "initializer_range": 0.02,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0
+    },
+    "layer_norm_epsilon": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "gpt2",
+    "n_ctx": 1024,
+    "n_embd": 768,
+    "n_head": 12,
+    "n_inner": null,
+    "n_layer": 6,
+    "n_positions": 1024,
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "reorder_and_upcast_attn": false,
+    "repetition_penalty": 1.0,
+    "resid_pdrop": 0.1,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "scale_attn_by_inverse_layer_idx": false,
+    "scale_attn_weights": true,
+    "sep_token_id": null,
+    "summary_activation": null,
+    "summary_first_dropout": 0.1,
+    "summary_proj_to_labels": true,
+    "summary_type": "cls_index",
+    "summary_use_proj": true,
+    "suppress_tokens": null,
+    "task_specific_params": {
+      "text-generation": {
+        "do_sample": true,
+        "max_length": 50
+      }
+    },
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.25.1",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 50258
+  },
+  "decoder_start_token_id": 50256,
+  "early_stopping": true,
+  "encoder": {
+    "_name_or_path": "google/vit-base-patch16-224-in21k",
+    "add_cross_attention": false,
+    "architectures": [
+      "ViTModel"
+    ],
+    "attention_probs_dropout_prob": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "encoder_stride": 16,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.0,
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 224,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-12,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "vit",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 16,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "qkv_bias": true,
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.25.1",
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "eos_token_id": 50256,
+  "ignore_mismatched_sizes": true,
+  "is_encoder_decoder": true,
+  "length_penalty": 2.0,
+  "max_length": 64,
+  "model_type": "vision-encoder-decoder",
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 50256,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": null,
+  "vocab_size": 50257
+}

preprocessor_config.json

@@ -0,0 +1,22 @@
+{
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "ViTImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:febcc2118480fccb2a3afa8ed42a287858a970513a9f460ee8fce758dea04b70
+size 742646077

runs/Dec15_18-23-16_4ed7e00c4157/1671128777.5433903/events.out.tfevents.1671128777.4ed7e00c4157.115.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1f78b3976812db60e813486ff25681566fe9abb69d5118561f7e03da2705b23
+size 5886

runs/Dec15_18-23-16_4ed7e00c4157/events.out.tfevents.1671128777.4ed7e00c4157.115.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f314f27a4c57c537ebea7b5438765c12bc8b1b63c6fe08c1fdf9b6299e1ace4
+size 8383

runs/Dec15_18-29-10_4ed7e00c4157/1671129101.8125823/events.out.tfevents.1671129101.4ed7e00c4157.115.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43442709e20ce57c9f03fc95970840413fb797eb3cff0b65cb1ec33296fe4807
+size 5886

runs/Dec15_18-29-10_4ed7e00c4157/events.out.tfevents.1671129101.4ed7e00c4157.115.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18ccd3e9cc1bc653e001379dd5a182efba447f6e0d542f20c19016efbc861159
+size 8383

runs/Dec15_18-38-46_4ed7e00c4157/1671129548.305052/events.out.tfevents.1671129548.4ed7e00c4157.115.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:730c0e2ea4b2e09dfd40ec99552616b83ab6552bee72f88e95a400dc4d825c40
+size 5886

runs/Dec15_18-38-46_4ed7e00c4157/events.out.tfevents.1671129548.4ed7e00c4157.115.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e964ec79196207578f76bca8047e93726dd3b6b4364f9b98fec4904ff98892a
+size 8381

runs/Dec15_18-40-11_4ed7e00c4157/1671129625.9460235/events.out.tfevents.1671129625.4ed7e00c4157.115.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c3e4b9be30dbb5d49123e1f4c0eb92e6385ad90a027c025c4d0a718ccc2ba77
+size 5886

runs/Dec15_18-40-11_4ed7e00c4157/events.out.tfevents.1671129625.4ed7e00c4157.115.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c5a9481b8a246295ff05ab786a66a96e9359478b001a4f3cfab118bd632d42a
+size 8540

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:167b9e4e3ee58267845a415f53043aabf3a506b3de66e0affd9cf352d50c8a25
+size 3643