Upload 10 files

README.md

@@ -1,6 +1,53 @@
 ---
-datasets:
-- axiong/pmc_oa
-language:
-- en
----
+base_model: openai/clip-vit-large-patch14
+tags:
+- generated_from_trainer
+model-index:
+- name: clip-vit-l-14-pmc-finetuned
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# clip-vit-l-14-pmc-finetuned
+
+This model is a fine-tuned version of [openai/clip-vit-large-patch14](https://huggingface.co/openai/clip-vit-large-patch14) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0125
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.31.0
+- Pytorch 2.0.1
+- Datasets 2.14.4
+- Tokenizers 0.13.3

all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 1.0124750137329102,
+    "eval_runtime": 97.9114,
+    "eval_samples_per_second": 55.54,
+    "eval_steps_per_second": 6.945,
+    "train_loss": 0.30929526851019973,
+    "train_runtime": 55900.09,
+    "train_samples_per_second": 11.761,
+    "train_steps_per_second": 0.735
+}

config.json

@@ -0,0 +1,168 @@
+{
+  "_commit_hash": "8d052a0f05efbaefbc9e8786ba291cfdf93e5bff",
+  "_name_or_path": "openai/clip-vit-large-patch14",
+  "architectures": [
+    "CLIPModel"
+  ],
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "clip",
+  "projection_dim": 768,
+  "text_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 49406,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "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": 49407,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "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,
+    "max_position_embeddings": 77,
+    "min_length": 0,
+    "model_type": "clip_text_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": 1,
+    "prefix": null,
+    "problem_type": null,
+    "projection_dim": 768,
+    "pruned_heads": {},
+    "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": "4.31.0",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "vocab_size": 49408
+  },
+  "torch_dtype": "float32",
+  "transformers_version": null,
+  "vision_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 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,
+    "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 224,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "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": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_hidden_layers": 24,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 14,
+    "prefix": null,
+    "problem_type": null,
+    "projection_dim": 768,
+    "pruned_heads": {},
+    "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": "4.31.0",
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  }
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 1.0124750137329102,
+    "eval_runtime": 97.9114,
+    "eval_samples_per_second": 55.54,
+    "eval_steps_per_second": 6.945
+}

preprocessor_config.json

@@ -0,0 +1,19 @@
+{
+  "crop_size": 224,
+  "do_center_crop": true,
+  "do_normalize": true,
+  "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "size": 224
+}

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+    "unk_token": {
+        "content": "<|endoftext|>",
+        "single_word": false,
+        "lstrip": false,
+        "rstrip": false,
+        "normalized": true,
+        "__type": "AddedToken"
+    },
+    "bos_token": {
+        "content": "<|startoftext|>",
+        "single_word": false,
+        "lstrip": false,
+        "rstrip": false,
+        "normalized": true,
+        "__type": "AddedToken"
+    },
+    "eos_token": {
+        "content": "<|endoftext|>",
+        "single_word": false,
+        "lstrip": false,
+        "rstrip": false,
+        "normalized": true,
+        "__type": "AddedToken"
+    },
+    "pad_token": "<|endoftext|>",
+    "add_prefix_space": false,
+    "errors": "replace",
+    "do_lower_case": true,
+    "name_or_path": "openai/clip-vit-base-patch32",
+    "model_max_length": 77,
+    "special_tokens_map_file": "./special_tokens_map.json",
+    "tokenizer_class": "CLIPTokenizer"
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 10.0,
+    "train_loss": 0.30929526851019973,
+    "train_runtime": 55900.09,
+    "train_samples_per_second": 11.761,
+    "train_steps_per_second": 0.735
+}

trainer_state.json

@@ -0,0 +1,517 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "global_step": 41090,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.9391579459722564e-05,
+      "loss": 1.7982,
+      "step": 500
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.878315891944512e-05,
+      "loss": 1.2914,
+      "step": 1000
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 4.817473837916768e-05,
+      "loss": 1.1456,
+      "step": 1500
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 4.756631783889024e-05,
+      "loss": 1.0345,
+      "step": 2000
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 4.6957897298612804e-05,
+      "loss": 0.9665,
+      "step": 2500
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 4.6349476758335365e-05,
+      "loss": 0.9272,
+      "step": 3000
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 4.574105621805793e-05,
+      "loss": 0.8571,
+      "step": 3500
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 4.513263567778048e-05,
+      "loss": 0.8139,
+      "step": 4000
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 4.4524215137503043e-05,
+      "loss": 0.6986,
+      "step": 4500
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 4.3915794597225605e-05,
+      "loss": 0.6375,
+      "step": 5000
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 4.330737405694817e-05,
+      "loss": 0.6407,
+      "step": 5500
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 4.269895351667073e-05,
+      "loss": 0.6139,
+      "step": 6000
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 4.209053297639329e-05,
+      "loss": 0.5973,
+      "step": 6500
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 4.1482112436115845e-05,
+      "loss": 0.6094,
+      "step": 7000
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 4.0873691895838406e-05,
+      "loss": 0.5824,
+      "step": 7500
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 4.026527135556097e-05,
+      "loss": 0.5459,
+      "step": 8000
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 3.965685081528352e-05,
+      "loss": 0.4764,
+      "step": 8500
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 3.9048430275006084e-05,
+      "loss": 0.427,
+      "step": 9000
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 3.8440009734728646e-05,
+      "loss": 0.4192,
+      "step": 9500
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 3.783158919445121e-05,
+      "loss": 0.4278,
+      "step": 10000
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 3.722316865417377e-05,
+      "loss": 0.4157,
+      "step": 10500
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 3.6614748113896324e-05,
+      "loss": 0.4156,
+      "step": 11000
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 3.6006327573618886e-05,
+      "loss": 0.4137,
+      "step": 11500
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 3.539790703334145e-05,
+      "loss": 0.3731,
+      "step": 12000
+    },
+    {
+      "epoch": 3.04,
+      "learning_rate": 3.4789486493064e-05,
+      "loss": 0.3516,
+      "step": 12500
+    },
+    {
+      "epoch": 3.16,
+      "learning_rate": 3.418106595278657e-05,
+      "loss": 0.3098,
+      "step": 13000
+    },
+    {
+      "epoch": 3.29,
+      "learning_rate": 3.357264541250913e-05,
+      "loss": 0.3051,
+      "step": 13500
+    },
+    {
+      "epoch": 3.41,
+      "learning_rate": 3.296422487223169e-05,
+      "loss": 0.3029,
+      "step": 14000
+    },
+    {
+      "epoch": 3.53,
+      "learning_rate": 3.235580433195425e-05,
+      "loss": 0.3107,
+      "step": 14500
+    },
+    {
+      "epoch": 3.65,
+      "learning_rate": 3.174738379167681e-05,
+      "loss": 0.2969,
+      "step": 15000
+    },
+    {
+      "epoch": 3.77,
+      "learning_rate": 3.1138963251399365e-05,
+      "loss": 0.2886,
+      "step": 15500
+    },
+    {
+      "epoch": 3.89,
+      "learning_rate": 3.053054271112193e-05,
+      "loss": 0.2887,
+      "step": 16000
+    },
+    {
+      "epoch": 4.02,
+      "learning_rate": 2.9922122170844492e-05,
+      "loss": 0.2803,
+      "step": 16500
+    },
+    {
+      "epoch": 4.14,
+      "learning_rate": 2.9313701630567047e-05,
+      "loss": 0.2256,
+      "step": 17000
+    },
+    {
+      "epoch": 4.26,
+      "learning_rate": 2.8705281090289608e-05,
+      "loss": 0.2209,
+      "step": 17500
+    },
+    {
+      "epoch": 4.38,
+      "learning_rate": 2.8096860550012173e-05,
+      "loss": 0.2197,
+      "step": 18000
+    },
+    {
+      "epoch": 4.5,
+      "learning_rate": 2.7488440009734728e-05,
+      "loss": 0.2305,
+      "step": 18500
+    },
+    {
+      "epoch": 4.62,
+      "learning_rate": 2.688001946945729e-05,
+      "loss": 0.2252,
+      "step": 19000
+    },
+    {
+      "epoch": 4.75,
+      "learning_rate": 2.627159892917985e-05,
+      "loss": 0.207,
+      "step": 19500
+    },
+    {
+      "epoch": 4.87,
+      "learning_rate": 2.566317838890241e-05,
+      "loss": 0.2187,
+      "step": 20000
+    },
+    {
+      "epoch": 4.99,
+      "learning_rate": 2.505475784862497e-05,
+      "loss": 0.207,
+      "step": 20500
+    },
+    {
+      "epoch": 5.11,
+      "learning_rate": 2.444633730834753e-05,
+      "loss": 0.1685,
+      "step": 21000
+    },
+    {
+      "epoch": 5.23,
+      "learning_rate": 2.383791676807009e-05,
+      "loss": 0.1772,
+      "step": 21500
+    },
+    {
+      "epoch": 5.35,
+      "learning_rate": 2.3229496227792653e-05,
+      "loss": 0.1728,
+      "step": 22000
+    },
+    {
+      "epoch": 5.48,
+      "learning_rate": 2.262107568751521e-05,
+      "loss": 0.1678,
+      "step": 22500
+    },
+    {
+      "epoch": 5.6,
+      "learning_rate": 2.201265514723777e-05,
+      "loss": 0.1642,
+      "step": 23000
+    },
+    {
+      "epoch": 5.72,
+      "learning_rate": 2.1404234606960334e-05,
+      "loss": 0.1664,
+      "step": 23500
+    },
+    {
+      "epoch": 5.84,
+      "learning_rate": 2.0795814066682892e-05,
+      "loss": 0.1575,
+      "step": 24000
+    },
+    {
+      "epoch": 5.96,
+      "learning_rate": 2.018739352640545e-05,
+      "loss": 0.1599,
+      "step": 24500
+    },
+    {
+      "epoch": 6.08,
+      "learning_rate": 1.9578972986128012e-05,
+      "loss": 0.1249,
+      "step": 25000
+    },
+    {
+      "epoch": 6.21,
+      "learning_rate": 1.8970552445850574e-05,
+      "loss": 0.1266,
+      "step": 25500
+    },
+    {
+      "epoch": 6.33,
+      "learning_rate": 1.8362131905573132e-05,
+      "loss": 0.1304,
+      "step": 26000
+    },
+    {
+      "epoch": 6.45,
+      "learning_rate": 1.7753711365295694e-05,
+      "loss": 0.1161,
+      "step": 26500
+    },
+    {
+      "epoch": 6.57,
+      "learning_rate": 1.7145290825018255e-05,
+      "loss": 0.1253,
+      "step": 27000
+    },
+    {
+      "epoch": 6.69,
+      "learning_rate": 1.6536870284740814e-05,
+      "loss": 0.1215,
+      "step": 27500
+    },
+    {
+      "epoch": 6.81,
+      "learning_rate": 1.5928449744463375e-05,
+      "loss": 0.1158,
+      "step": 28000
+    },
+    {
+      "epoch": 6.94,
+      "learning_rate": 1.5320029204185933e-05,
+      "loss": 0.1219,
+      "step": 28500
+    },
+    {
+      "epoch": 7.06,
+      "learning_rate": 1.4711608663908493e-05,
+      "loss": 0.1039,
+      "step": 29000
+    },
+    {
+      "epoch": 7.18,
+      "learning_rate": 1.4103188123631053e-05,
+      "loss": 0.081,
+      "step": 29500
+    },
+    {
+      "epoch": 7.3,
+      "learning_rate": 1.3494767583353615e-05,
+      "loss": 0.0922,
+      "step": 30000
+    },
+    {
+      "epoch": 7.42,
+      "learning_rate": 1.2886347043076175e-05,
+      "loss": 0.0844,
+      "step": 30500
+    },
+    {
+      "epoch": 7.54,
+      "learning_rate": 1.2277926502798735e-05,
+      "loss": 0.0759,
+      "step": 31000
+    },
+    {
+      "epoch": 7.67,
+      "learning_rate": 1.1669505962521295e-05,
+      "loss": 0.0882,
+      "step": 31500
+    },
+    {
+      "epoch": 7.79,
+      "learning_rate": 1.1061085422243855e-05,
+      "loss": 0.0856,
+      "step": 32000
+    },
+    {
+      "epoch": 7.91,
+      "learning_rate": 1.0452664881966416e-05,
+      "loss": 0.0881,
+      "step": 32500
+    },
+    {
+      "epoch": 8.03,
+      "learning_rate": 9.844244341688976e-06,
+      "loss": 0.0708,
+      "step": 33000
+    },
+    {
+      "epoch": 8.15,
+      "learning_rate": 9.235823801411536e-06,
+      "loss": 0.0538,
+      "step": 33500
+    },
+    {
+      "epoch": 8.27,
+      "learning_rate": 8.627403261134098e-06,
+      "loss": 0.0554,
+      "step": 34000
+    },
+    {
+      "epoch": 8.4,
+      "learning_rate": 8.018982720856656e-06,
+      "loss": 0.06,
+      "step": 34500
+    },
+    {
+      "epoch": 8.52,
+      "learning_rate": 7.410562180579217e-06,
+      "loss": 0.0514,
+      "step": 35000
+    },
+    {
+      "epoch": 8.64,
+      "learning_rate": 6.802141640301777e-06,
+      "loss": 0.0536,
+      "step": 35500
+    },
+    {
+      "epoch": 8.76,
+      "learning_rate": 6.193721100024337e-06,
+      "loss": 0.0583,
+      "step": 36000
+    },
+    {
+      "epoch": 8.88,
+      "learning_rate": 5.585300559746897e-06,
+      "loss": 0.052,
+      "step": 36500
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 4.976880019469458e-06,
+      "loss": 0.0481,
+      "step": 37000
+    },
+    {
+      "epoch": 9.13,
+      "learning_rate": 4.368459479192018e-06,
+      "loss": 0.0378,
+      "step": 37500
+    },
+    {
+      "epoch": 9.25,
+      "learning_rate": 3.760038938914578e-06,
+      "loss": 0.0296,
+      "step": 38000
+    },
+    {
+      "epoch": 9.37,
+      "learning_rate": 3.151618398637138e-06,
+      "loss": 0.037,
+      "step": 38500
+    },
+    {
+      "epoch": 9.49,
+      "learning_rate": 2.543197858359698e-06,
+      "loss": 0.0339,
+      "step": 39000
+    },
+    {
+      "epoch": 9.61,
+      "learning_rate": 1.9347773180822585e-06,
+      "loss": 0.0369,
+      "step": 39500
+    },
+    {
+      "epoch": 9.73,
+      "learning_rate": 1.3263567778048189e-06,
+      "loss": 0.0344,
+      "step": 40000
+    },
+    {
+      "epoch": 9.86,
+      "learning_rate": 7.17936237527379e-07,
+      "loss": 0.0301,
+      "step": 40500
+    },
+    {
+      "epoch": 9.98,
+      "learning_rate": 1.0951569724993917e-07,
+      "loss": 0.0325,
+      "step": 41000
+    },
+    {
+      "epoch": 10.0,
+      "step": 41090,
+      "total_flos": 1.1825796643443088e+17,
+      "train_loss": 0.30929526851019973,
+      "train_runtime": 55900.09,
+      "train_samples_per_second": 11.761,
+      "train_steps_per_second": 0.735
+    }
+  ],
+  "max_steps": 41090,
+  "num_train_epochs": 10,
+  "total_flos": 1.1825796643443088e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:615c91ee2578bd75aa451a22a60b066acc3c6666c6372a7566fcb99c95aae679
+size 3963