Upload 7 files

config.json

@@ -0,0 +1,166 @@
+{
+  "_name_or_path": "./clip-roberta",
+  "architectures": [
+    "VisionTextDualEncoderModel"
+  ],
+  "logit_scale_init_value": 2.6592,
+  "model_type": "vision-text-dual-encoder",
+  "projection_dim": 512,
+  "text_config": {
+    "_name_or_path": "dumitrescustefan/bert-base-romanian-cased-v1",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": null,
+    "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,
+    "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": 0.1,
+    "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,
+    "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,
+    "type_vocab_size": 2,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 50000
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.0.dev0",
+  "vision_config": {
+    "_name_or_path": "openai/clip-vit-base-patch32",
+    "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": 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_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": 32,
+    "prefix": null,
+    "problem_type": null,
+    "projection_dim": 512,
+    "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,
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26d9f7bb79b4b16a5789e9e01494067bcac19ca081bb8f7e145c768d4459d89d
+size 850786436

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70659941693398d8eedb54100abb81df732400d5f0cf3c1ceb023b693fb9f265
+size 1701805829

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b345a1606c8f4c03ae0fca3728d391b7d58f1637ce535f7bc221ecf88470a8de
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a18b4b828461f3923a10b83e07c604218895dc423055505133806be2b52154c0
+size 1064

trainer_state.json

@@ -0,0 +1,105 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.8666985188724317,
+  "eval_steps": 500,
+  "global_step": 6000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.24,
+      "grad_norm": 24.413671493530273,
+      "learning_rate": 4.601847427934385e-05,
+      "loss": 1.7935,
+      "step": 500
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 27.336660385131836,
+      "learning_rate": 4.203694855868769e-05,
+      "loss": 1.2168,
+      "step": 1000
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 20.986051559448242,
+      "learning_rate": 3.805542283803154e-05,
+      "loss": 0.9801,
+      "step": 1500
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 21.99080467224121,
+      "learning_rate": 3.407389711737538e-05,
+      "loss": 0.83,
+      "step": 2000
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 16.28312873840332,
+      "learning_rate": 3.0092371396719225e-05,
+      "loss": 0.5681,
+      "step": 2500
+    },
+    {
+      "epoch": 1.43,
+      "grad_norm": 19.05654525756836,
+      "learning_rate": 2.6110845676063068e-05,
+      "loss": 0.4901,
+      "step": 3000
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 11.311978340148926,
+      "learning_rate": 2.2129319955406913e-05,
+      "loss": 0.4685,
+      "step": 3500
+    },
+    {
+      "epoch": 1.91,
+      "grad_norm": 7.999639987945557,
+      "learning_rate": 1.8147794234750756e-05,
+      "loss": 0.4105,
+      "step": 4000
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 7.035294532775879,
+      "learning_rate": 1.4166268514094602e-05,
+      "loss": 0.2915,
+      "step": 4500
+    },
+    {
+      "epoch": 2.39,
+      "grad_norm": 9.238717079162598,
+      "learning_rate": 1.0184742793438446e-05,
+      "loss": 0.2247,
+      "step": 5000
+    },
+    {
+      "epoch": 2.63,
+      "grad_norm": 5.481063365936279,
+      "learning_rate": 6.20321707278229e-06,
+      "loss": 0.2151,
+      "step": 5500
+    },
+    {
+      "epoch": 2.87,
+      "grad_norm": 5.940337181091309,
+      "learning_rate": 2.221691352126135e-06,
+      "loss": 0.1981,
+      "step": 6000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6279,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 5.126075524128e+16,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01c8264c6f6b99e8b77cb80b315acd27fc85ea9e54b7126d575f8e5da6d3fb7c
+size 4920