add trained model

model/config.json

@@ -0,0 +1,152 @@
+{
+  "architectures": [
+    "MedCLIP"
+  ],
+  "initializer_factor": 1.0,
+  "model_type": "hybrid-clip",
+  "projection_dim": 512,
+  "seed": 42,
+  "text_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "gradient_checkpointing": false,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "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,
+    "max_position_embeddings": 512,
+    "min_length": 0,
+    "model_type": "bert",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "position_embedding_type": "absolute",
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torchscript": false,
+    "transformers_version": "4.8.2",
+    "type_vocab_size": 2,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 31090
+  },
+  "transformers_version": null,
+  "vision_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "gradient_checkpointing": false,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 224,
+    "initializer_factor": 1.0,
+    "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-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "clip_vision_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 32,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torchscript": false,
+    "transformers_version": "4.8.2",
+    "use_bfloat16": false
+  }
+}

model/flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68b52339f7fa55829d502cf70bf3e445634a1f94ce86b9770e70c6e451f4d0b4
+size 792657752

model/logs/events.out.tfevents.1626406050.t1v-n-f700bfbb-w-0.233317.3.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fba1b0d22399209ed281ae9e176f5c05c7f844134c9802dd29b93e47cd315e2f
+size 396714

model/logs/events.out.tfevents.1626408834.t1v-n-f700bfbb-w-0.261335.3.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a022b3284b4ace7f067a9c6e0f98431ff61cc2b425e0dfb20ac8d78bd0210e89
+size 40

model/logs/events.out.tfevents.1626409141.t1v-n-f700bfbb-w-0.268430.3.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72585e9ff1d5bc5b9b3b87079673e98172dbe1276652e75fdc1588e39bd036c0
+size 39400

model/logs/events.out.tfevents.1626409572.t1v-n-f700bfbb-w-0.282371.3.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8ca278fd54e647dd9696c6eee20cf5c1fe6c8208593560c7d70937e5da88de3
+size 321490

train_model.sh

@@ -1,5 +1,5 @@
 python run_medclip.py \
-    --output_dir "flax-community/medclip" \
+    --output_dir "model" \
     --overwrite_output_dir \
     --text_model_name_or_path="allenai/scibert_scivocab_uncased" \
     --vision_model_name_or_path="openai/clip-vit-base-patch32" \
@@ -10,9 +10,9 @@ python run_medclip.py \
     --mimic_mode="docs" \
     --roco_data_dir="/home/shpotes/medclip/data/roco-dataset/" \
     --do_train --do_eval \
-    --num_train_epochs="20" \
+    --num_train_epochs="18" \
     --preprocessing_num_workers=32 \
     --per_device_train_batch_size=64 \
     --per_device_eval_batch_size=64 \
-    --warmup_steps=3000 \
-    --learning_rate="3e-4" 
+    --warmup_steps=5000 \
+    --learning_rate="3e-4"