Saving weights and logs of epoch 4 - step 9228

ckpt_epoch_4_step_9228/config.json

@@ -0,0 +1,169 @@
+{
+  "architectures": [
+    "VisionEncoderDecoderModel"
+  ],
+  "bos_token_id": 50256,
+  "decoder": {
+    "_name_or_path": "",
+    "activation_function": "gelu_new",
+    "add_cross_attention": true,
+    "architectures": [
+      "GPT2LMHeadModel"
+    ],
+    "attn_pdrop": 0.1,
+    "bad_words_ids": null,
+    "bos_token_id": 50256,
+    "chunk_size_feed_forward": 0,
+    "decoder_start_token_id": 50256,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "embd_pdrop": 0.1,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 50256,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "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": 12,
+    "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": 50256,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "resid_pdrop": 0.1,
+    "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
+      }
+    },
+    "temperature": 1.0,
+    "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": "4.11.0.dev0",
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 50257
+  },
+  "decoder_start_token_id": 50256,
+  "encoder": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": [
+      "ViTModel"
+    ],
+    "attention_probs_dropout_prob": 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,
+    "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,
+    "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": {},
+    "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,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.11.0.dev0",
+    "use_bfloat16": false
+  },
+  "eos_token_id": 50256,
+  "is_encoder_decoder": true,
+  "model_type": "vision-encoder-decoder",
+  "pad_token_id": 50256,
+  "transformers_version": null
+}

ckpt_epoch_4_step_9228/flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf097b685e4c975c5c0bcef2040e49a3118d557a080d9ac5cdce548218bf6402
+size 956799284

ckpt_epoch_4_step_9228/special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>", "pad_token": "<|endoftext|>"}

ckpt_epoch_4_step_9228/tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "gpt2", "tokenizer_class": "GPT2Tokenizer"}

events.out.tfevents.1633443513.t1v-n-bb5dfd23-w-0.8655.0.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f152f6cd11c8a0da055463400d0c67df551f2837826c599bba23c83786dbe2e9
-size 6277293
+oid sha256:d02c255295909b9da92e097d463302c355b9e058b791558ad368577d018bc1bf
+size 6616913

report.txt

@@ -964,3 +964,27 @@ Epoch... (4/30 | Step: 8990 | Loss: 1.7301363945007324, Learning Rate: 2.6103596
 Epoch... (4/30 | Step: 9000 | Loss: 1.743155837059021, Learning Rate: 2.6099261958734132e-05)
 Epoch... (4/30 | Step: 9000 | Loss: 1.743155837059021, Learning Rate: 2.6099261958734132e-05)
 Epoch... (4/30 | Step: 9000 | Eval Loss: 1.8965791463851929 | Eval rouge1: 41.5249 | Eval rouge2: 15.9328 | Eval rougeL: 37.7734 | Eval rougeLsum: 37.7601 | Eval gen_len: 11.0642 |)
+Epoch... (4/30 | Step: 9010 | Loss: 1.757112741470337, Learning Rate: 2.6094929125974886e-05)
+Epoch... (4/30 | Step: 9020 | Loss: 1.6790308952331543, Learning Rate: 2.6090594474226236e-05)
+Epoch... (4/30 | Step: 9030 | Loss: 1.809779167175293, Learning Rate: 2.6086259822477587e-05)
+Epoch... (4/30 | Step: 9040 | Loss: 1.7617172002792358, Learning Rate: 2.6081923351739533e-05)
+Epoch... (4/30 | Step: 9050 | Loss: 1.7789397239685059, Learning Rate: 2.6077588699990883e-05)
+Epoch... (4/30 | Step: 9060 | Loss: 1.8057465553283691, Learning Rate: 2.6073254048242234e-05)
+Epoch... (4/30 | Step: 9070 | Loss: 1.8141238689422607, Learning Rate: 2.6068919396493584e-05)
+Epoch... (4/30 | Step: 9080 | Loss: 1.8108280897140503, Learning Rate: 2.6064584744744934e-05)
+Epoch... (4/30 | Step: 9090 | Loss: 1.8593292236328125, Learning Rate: 2.6060250092996284e-05)
+Epoch... (4/30 | Step: 9100 | Loss: 1.7626819610595703, Learning Rate: 2.6055917260237038e-05)
+Epoch... (4/30 | Step: 9110 | Loss: 1.741670846939087, Learning Rate: 2.605158260848839e-05)
+Epoch... (4/30 | Step: 9120 | Loss: 1.8072537183761597, Learning Rate: 2.6047246137750335e-05)
+Epoch... (4/30 | Step: 9130 | Loss: 1.7297160625457764, Learning Rate: 2.6042911486001685e-05)
+Epoch... (4/30 | Step: 9140 | Loss: 1.7664251327514648, Learning Rate: 2.6038576834253035e-05)
+Epoch... (4/30 | Step: 9150 | Loss: 1.753387689590454, Learning Rate: 2.6034242182504386e-05)
+Epoch... (4/30 | Step: 9160 | Loss: 1.8218653202056885, Learning Rate: 2.6029907530755736e-05)
+Epoch... (4/30 | Step: 9170 | Loss: 1.7087664604187012, Learning Rate: 2.6025572879007086e-05)
+Epoch... (4/30 | Step: 9180 | Loss: 1.7308189868927002, Learning Rate: 2.6021238227258436e-05)
+Epoch... (4/30 | Step: 9190 | Loss: 1.707600474357605, Learning Rate: 2.601690539449919e-05)
+Epoch... (4/30 | Step: 9200 | Loss: 1.7880096435546875, Learning Rate: 2.601257074275054e-05)
+Epoch... (4/30 | Step: 9210 | Loss: 1.7144484519958496, Learning Rate: 2.600823609100189e-05)
+Epoch... (4/30 | Step: 9220 | Loss: 1.7841001749038696, Learning Rate: 2.600390143925324e-05)
+Epoch... (4/30 | Step: 9228 | Loss: 1.7486577033996582, Learning Rate: 2.600043262646068e-05)
+Epoch... (4/30 | Step: 9228 | Eval Loss: 1.8944240808486938 | Eval rouge1: 41.2514 | Eval rouge2: 15.6625 | Eval rougeL: 37.5594 | Eval rougeLsum: 37.5542 | Eval gen_len: 11.2178 |)