add epoch 3

config.json

@@ -1,147 +1,294 @@
 {
   "architectures": [
-    "ViTGPT2LMForConditionalGeneration"
+    "CLIPVisionMarianForConditionalGeneration"
   ],
-  "gpt2_config": {
-    "_name_or_path": ".",
-    "activation_function": "gelu_new",
-    "add_cross_attention": true,
+  "clip_vision_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
     "architectures": [
-      "GPT2LMHeadModel"
+      "CLIPModel"
     ],
-    "attn_pdrop": 0.0,
+    "attention_dropout": 0.0,
     "bad_words_ids": null,
-    "bos_token_id": 50256,
+    "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,
-    "embd_pdrop": 0.0,
     "encoder_no_repeat_ngram_size": 0,
-    "eos_token_id": 50256,
+    "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_epsilon": 1e-05,
+    "layer_norm_eps": 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": 12,
-    "n_positions": 1024,
+    "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,
+    "projection_dim": 512,
     "pruned_heads": {},
     "remove_invalid_values": false,
     "repetition_penalty": 1.0,
-    "resid_pdrop": 0.0,
     "return_dict": true,
     "return_dict_in_generate": 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,
-    "task_specific_params": {
-      "text-generation": {
-        "do_sample": true,
-        "max_length": 50
-      }
-    },
+    "task_specific_params": null,
     "temperature": 1.0,
+    "text_config": {
+      "_name_or_path": "",
+      "add_cross_attention": false,
+      "architectures": null,
+      "attention_dropout": 0.0,
+      "bad_words_ids": null,
+      "bos_token_id": 0,
+      "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": 2,
+      "finetuning_task": null,
+      "forced_bos_token_id": null,
+      "forced_eos_token_id": null,
+      "gradient_checkpointing": false,
+      "hidden_act": "quick_gelu",
+      "hidden_size": 512,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "initializer_factor": 1.0,
+      "initializer_range": 0.02,
+      "intermediate_size": 2048,
+      "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": 8,
+      "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,
+      "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": "4.7.0.dev0",
+      "use_bfloat16": false,
+      "vocab_size": 49408
+    },
+    "text_config_dict": null,
     "tie_encoder_decoder": false,
     "tie_word_embeddings": true,
     "tokenizer_class": null,
     "top_k": 50,
     "top_p": 1.0,
-    "torch_dtype": "float32",
+    "torch_dtype": null,
     "torchscript": false,
     "transformers_version": "4.9.0.dev0",
     "use_bfloat16": false,
-    "use_cache": true,
-    "vocab_size": 50257
+    "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": "4.7.0.dev0",
+      "use_bfloat16": false
+    },
+    "vision_config_dict": null
   },
-  "model_type": "vit-gpt2",
-  "transformers_version": null,
-  "vit_config": {
+  "is_encoder_decoder": true,
+  "marian_config": {
     "_name_or_path": "",
+    "_num_labels": 3,
+    "activation_dropout": 0.0,
+    "activation_function": "swish",
+    "add_bias_logits": false,
     "add_cross_attention": false,
+    "add_final_layer_norm": false,
     "architectures": [
-      "ViTModel"
+      "MarianMTModel"
     ],
-    "attention_probs_dropout_prob": 0.0,
-    "bad_words_ids": null,
-    "bos_token_id": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": [
+      [
+        54795
+      ]
+    ],
+    "bos_token_id": 0,
     "chunk_size_feed_forward": 0,
-    "decoder_start_token_id": null,
+    "classif_dropout": 0.0,
+    "classifier_dropout": 0.0,
+    "d_model": 512,
+    "decoder_attention_heads": 8,
+    "decoder_ffn_dim": 2048,
+    "decoder_layerdrop": 0.0,
+    "decoder_layers": 6,
+    "decoder_start_token_id": 54795,
     "diversity_penalty": 0.0,
     "do_sample": false,
+    "dropout": 0.1,
     "early_stopping": false,
+    "encoder_attention_heads": 8,
+    "encoder_ffn_dim": 2048,
+    "encoder_layerdrop": 0.0,
+    "encoder_layers": 6,
     "encoder_no_repeat_ngram_size": 0,
-    "eos_token_id": null,
+    "eos_token_id": 0,
     "finetuning_task": null,
     "forced_bos_token_id": null,
-    "forced_eos_token_id": null,
-    "hidden_act": "gelu",
-    "hidden_dropout_prob": 0.0,
-    "hidden_size": 768,
+    "forced_eos_token_id": 0,
+    "gradient_checkpointing": false,
     "id2label": {
       "0": "LABEL_0",
-      "1": "LABEL_1"
+      "1": "LABEL_1",
+      "2": "LABEL_2"
     },
-    "image_size": 224,
-    "initializer_range": 0.02,
-    "intermediate_size": 3072,
+    "init_std": 0.02,
     "is_decoder": false,
-    "is_encoder_decoder": false,
+    "is_encoder_decoder": true,
     "label2id": {
       "LABEL_0": 0,
-      "LABEL_1": 1
+      "LABEL_1": 1,
+      "LABEL_2": 2
     },
-    "layer_norm_eps": 1e-12,
     "length_penalty": 1.0,
-    "max_length": 20,
+    "max_length": 512,
+    "max_position_embeddings": 512,
     "min_length": 0,
-    "model_type": "vit",
+    "model_type": "marian",
     "no_repeat_ngram_size": 0,
-    "num_attention_heads": 12,
+    "normalize_before": false,
+    "normalize_embedding": false,
     "num_beam_groups": 1,
-    "num_beams": 1,
-    "num_channels": 3,
-    "num_hidden_layers": 12,
+    "num_beams": 4,
+    "num_hidden_layers": 6,
     "num_return_sequences": 1,
     "output_attentions": false,
     "output_hidden_states": false,
     "output_scores": false,
-    "pad_token_id": null,
-    "patch_size": 16,
+    "pad_token_id": 54795,
     "prefix": null,
     "problem_type": null,
     "pruned_heads": {},
@@ -149,7 +296,9 @@
     "repetition_penalty": 1.0,
     "return_dict": true,
     "return_dict_in_generate": false,
+    "scale_embedding": true,
     "sep_token_id": null,
+    "static_position_embeddings": true,
     "task_specific_params": null,
     "temperature": 1.0,
     "tie_encoder_decoder": false,
@@ -160,6 +309,11 @@
     "torch_dtype": null,
     "torchscript": false,
     "transformers_version": "4.9.0.dev0",
-    "use_bfloat16": false
-  }
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 54796
+  },
+  "model_type": "clip-vision-marian",
+  "seed": 42,
+  "transformers_version": null
 }

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd05a38812aaa66447e39582897d93b636238f297600139386bcdda642b4b51a
-size 1013496087
+oid sha256:c033c92bf0720f88fbacd6fd243d295e99cd2007d73f34b315c24f2bacc30bd2
+size 564749615

opt_state.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7044f0e712121ff4e6eecb07d786125d066cc33fad08c0f358be5f97dbf92d46
+size 1129499420

training_state.json

@@ -0,0 +1 @@
+{"step": 10400}