Saving weights and logs of epoch 5 - step 9900

ckpt_epoch_5_step_9900/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_5_step_9900/flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:892ea8ade82500c1f4497cfa8988c6036cf32e6d37438b883720508e698b3773
+size 956799284

ckpt_epoch_5_step_9900/special_tokens_map.json

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

ckpt_epoch_5_step_9900/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 sha256:3cfb493453272d56fd6b199582cc52beabe8516bee7cf7c9918d5b5938cb69c1
-size 6683163
+oid sha256:66f5a94a9931df224c659d8f3a2bcec5be897a3940569ed9ee81261a7c50795c
+size 6782438

report.txt

@@ -1030,3 +1030,35 @@ Epoch... (5/30 | Step: 9590 | Loss: 1.7620255947113037, Learning Rate: 2.5843519
 Epoch... (5/30 | Step: 9600 | Loss: 1.6920902729034424, Learning Rate: 2.583918467280455e-05)
 Epoch... (5/30 | Step: 9600 | Loss: 1.6920902729034424, Learning Rate: 2.583918467280455e-05)
 Epoch... (5/30 | Step: 9600 | Eval Loss: 1.9057726860046387 | Eval rouge1: 41.2741 | Eval rouge2: 15.6549 | Eval rougeL: 37.5375 | Eval rougeLsum: 37.532 | Eval gen_len: 11.1091 |)
+Epoch... (5/30 | Step: 9610 | Loss: 1.6601548194885254, Learning Rate: 2.58348500210559e-05)
+Epoch... (5/30 | Step: 9620 | Loss: 1.7098666429519653, Learning Rate: 2.583051536930725e-05)
+Epoch... (5/30 | Step: 9630 | Loss: 1.7010070085525513, Learning Rate: 2.58261807175586e-05)
+Epoch... (5/30 | Step: 9640 | Loss: 1.6576883792877197, Learning Rate: 2.582184606580995e-05)
+Epoch... (5/30 | Step: 9650 | Loss: 1.7301459312438965, Learning Rate: 2.58175114140613e-05)
+Epoch... (5/30 | Step: 9660 | Loss: 1.7436121702194214, Learning Rate: 2.581317676231265e-05)
+Epoch... (5/30 | Step: 9670 | Loss: 1.6648035049438477, Learning Rate: 2.5808842110564e-05)
+Epoch... (5/30 | Step: 9680 | Loss: 1.7438665628433228, Learning Rate: 2.580450745881535e-05)
+Epoch... (5/30 | Step: 9690 | Loss: 1.75654137134552, Learning Rate: 2.58001728070667e-05)
+Epoch... (5/30 | Step: 9700 | Loss: 1.683147668838501, Learning Rate: 2.5795836336328648e-05)
+Epoch... (5/30 | Step: 9710 | Loss: 1.7194781303405762, Learning Rate: 2.5791501684579998e-05)
+Epoch... (5/30 | Step: 9720 | Loss: 1.6344068050384521, Learning Rate: 2.5787168851820752e-05)
+Epoch... (5/30 | Step: 9730 | Loss: 1.7670934200286865, Learning Rate: 2.5782834200072102e-05)
+Epoch... (5/30 | Step: 9740 | Loss: 1.6978838443756104, Learning Rate: 2.5778499548323452e-05)
+Epoch... (5/30 | Step: 9750 | Loss: 1.7312850952148438, Learning Rate: 2.5774164896574803e-05)
+Epoch... (5/30 | Step: 9760 | Loss: 1.7457375526428223, Learning Rate: 2.5769830244826153e-05)
+Epoch... (5/30 | Step: 9770 | Loss: 1.7089920043945312, Learning Rate: 2.5765495593077503e-05)
+Epoch... (5/30 | Step: 9780 | Loss: 1.63335120677948, Learning Rate: 2.5761160941328853e-05)
+Epoch... (5/30 | Step: 9790 | Loss: 1.6670801639556885, Learning Rate: 2.5756826289580204e-05)
+Epoch... (5/30 | Step: 9800 | Loss: 1.7053790092468262, Learning Rate: 2.5752491637831554e-05)
+Epoch... (5/30 | Step: 9810 | Loss: 1.6865639686584473, Learning Rate: 2.5748158805072308e-05)
+Epoch... (5/30 | Step: 9820 | Loss: 1.713914155960083, Learning Rate: 2.5743822334334254e-05)
+Epoch... (5/30 | Step: 9830 | Loss: 1.7460925579071045, Learning Rate: 2.5739487682585604e-05)
+Epoch... (5/30 | Step: 9840 | Loss: 1.6545546054840088, Learning Rate: 2.5735153030836955e-05)
+Epoch... (5/30 | Step: 9850 | Loss: 1.6956062316894531, Learning Rate: 2.5730818379088305e-05)
+Epoch... (5/30 | Step: 9860 | Loss: 1.7374149560928345, Learning Rate: 2.5726483727339655e-05)
+Epoch... (5/30 | Step: 9870 | Loss: 1.7367851734161377, Learning Rate: 2.5722149075591005e-05)
+Epoch... (5/30 | Step: 9880 | Loss: 1.634256362915039, Learning Rate: 2.5717814423842356e-05)
+Epoch... (5/30 | Step: 9890 | Loss: 1.7566869258880615, Learning Rate: 2.5713479772093706e-05)
+Epoch... (5/30 | Step: 9900 | Loss: 1.6606078147888184, Learning Rate: 2.5709145120345056e-05)
+Epoch... (5/30 | Step: 9900 | Loss: 1.6606078147888184, Learning Rate: 2.5709145120345056e-05)
+Epoch... (5/30 | Step: 9900 | Eval Loss: 1.900822401046753 | Eval rouge1: 41.2639 | Eval rouge2: 15.6396 | Eval rougeL: 37.5531 | Eval rougeLsum: 37.5453 | Eval gen_len: 11.1403 |)