Saving weights and logs of epoch 3 - step 6000

ckpt_epoch_3_step_6000/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_3_step_6000/flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83adda308294700b912ec3146e36039c3091ea529df958cd6d8adca1d2e9b6c5
+size 956799284

ckpt_epoch_3_step_6000/special_tokens_map.json

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

ckpt_epoch_3_step_6000/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 sha256:74a9a091de5253a70ff2f485006fc7c1f3e32947bf4c6469b33001324eb95b16
-size 3639513
+oid sha256:dd1863fba015ebcf435f120b60ad86fde74e528f1c432128d6846e426d57ae18
+size 3843746

report.txt

@@ -610,3 +610,35 @@ Epoch... (3/30 | Step: 5690 | Loss: 1.84775710105896, Learning Rate: 2.753402623
 Epoch... (3/30 | Step: 5700 | Loss: 1.8937106132507324, Learning Rate: 2.7529691578820348e-05)
 Epoch... (3/30 | Step: 5700 | Loss: 1.8937106132507324, Learning Rate: 2.7529691578820348e-05)
 Epoch... (3/30 | Step: 5700 | Eval Loss: 1.9317536354064941 | Eval rouge1: 41.2629 | Eval rouge2: 15.689 | Eval rougeL: 37.4603 | Eval rougeLsum: 37.46 | Eval gen_len: 11.1765 |)
+Epoch... (3/30 | Step: 5710 | Loss: 1.8048105239868164, Learning Rate: 2.7525356927071698e-05)
+Epoch... (3/30 | Step: 5720 | Loss: 1.8522942066192627, Learning Rate: 2.7521022275323048e-05)
+Epoch... (3/30 | Step: 5730 | Loss: 1.8378591537475586, Learning Rate: 2.75166876235744e-05)
+Epoch... (3/30 | Step: 5740 | Loss: 1.9069128036499023, Learning Rate: 2.751235297182575e-05)
+Epoch... (3/30 | Step: 5750 | Loss: 1.7947864532470703, Learning Rate: 2.75080183200771e-05)
+Epoch... (3/30 | Step: 5760 | Loss: 1.8484649658203125, Learning Rate: 2.750368366832845e-05)
+Epoch... (3/30 | Step: 5770 | Loss: 1.8341162204742432, Learning Rate: 2.74993490165798e-05)
+Epoch... (3/30 | Step: 5780 | Loss: 1.814949631690979, Learning Rate: 2.749501436483115e-05)
+Epoch... (3/30 | Step: 5790 | Loss: 1.869789958000183, Learning Rate: 2.74906797130825e-05)
+Epoch... (3/30 | Step: 5800 | Loss: 1.925891637802124, Learning Rate: 2.748634506133385e-05)
+Epoch... (3/30 | Step: 5810 | Loss: 1.845622181892395, Learning Rate: 2.74820104095852e-05)
+Epoch... (3/30 | Step: 5820 | Loss: 1.9024274349212646, Learning Rate: 2.747767575783655e-05)
+Epoch... (3/30 | Step: 5830 | Loss: 1.734498381614685, Learning Rate: 2.74733411060879e-05)
+Epoch... (3/30 | Step: 5840 | Loss: 1.8688403367996216, Learning Rate: 2.746900645433925e-05)
+Epoch... (3/30 | Step: 5850 | Loss: 1.858962059020996, Learning Rate: 2.74646718025906e-05)
+Epoch... (3/30 | Step: 5860 | Loss: 1.7663443088531494, Learning Rate: 2.746033715084195e-05)
+Epoch... (3/30 | Step: 5870 | Loss: 1.741565465927124, Learning Rate: 2.74560024990933e-05)
+Epoch... (3/30 | Step: 5880 | Loss: 1.8864623308181763, Learning Rate: 2.7451667847344652e-05)
+Epoch... (3/30 | Step: 5890 | Loss: 1.7897045612335205, Learning Rate: 2.7447333195596002e-05)
+Epoch... (3/30 | Step: 5900 | Loss: 1.794191837310791, Learning Rate: 2.7442998543847352e-05)
+Epoch... (3/30 | Step: 5910 | Loss: 1.9371439218521118, Learning Rate: 2.7438665711088106e-05)
+Epoch... (3/30 | Step: 5920 | Loss: 1.8133981227874756, Learning Rate: 2.7434331059339456e-05)
+Epoch... (3/30 | Step: 5930 | Loss: 1.9133797883987427, Learning Rate: 2.7429994588601403e-05)
+Epoch... (3/30 | Step: 5940 | Loss: 1.874544382095337, Learning Rate: 2.7425659936852753e-05)
+Epoch... (3/30 | Step: 5950 | Loss: 1.7396442890167236, Learning Rate: 2.7421325285104103e-05)
+Epoch... (3/30 | Step: 5960 | Loss: 1.8002548217773438, Learning Rate: 2.7416990633355454e-05)
+Epoch... (3/30 | Step: 5970 | Loss: 1.8371654748916626, Learning Rate: 2.7412655981606804e-05)
+Epoch... (3/30 | Step: 5980 | Loss: 1.7982285022735596, Learning Rate: 2.7408321329858154e-05)
+Epoch... (3/30 | Step: 5990 | Loss: 1.862635612487793, Learning Rate: 2.7403986678109504e-05)
+Epoch... (3/30 | Step: 6000 | Loss: 1.9368724822998047, Learning Rate: 2.7399653845350258e-05)
+Epoch... (3/30 | Step: 6000 | Loss: 1.9368724822998047, Learning Rate: 2.7399653845350258e-05)
+Epoch... (3/30 | Step: 6000 | Eval Loss: 1.9258944988250732 | Eval rouge1: 41.086 | Eval rouge2: 15.536 | Eval rougeL: 37.351 | Eval rougeLsum: 37.3528 | Eval gen_len: 11.2105 |)