Saving weights and logs of epoch 1 - step 600

ckpt_epoch_1_step_600/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_1_step_600/flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fdc64df991b95360f18f2c1c957cfb20109e3cc8e7212699b7ebe8338a076bc
+size 956799284

ckpt_epoch_1_step_600/special_tokens_map.json

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

ckpt_epoch_1_step_600/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:f49258f80d1097f4612202635e31b54f675d42a84c46c211f742f988f6405aa4
-size 44377
+oid sha256:562867a61556aee91ef3e0cf8f6cc2a70b213782f2e3c8d08adf155b7d68eb1c
+size 132814

report.txt

@@ -30,3 +30,35 @@ Epoch... (1/30 | Step: 290 | Loss: 2.36462140083313, Learning Rate: 2.9874727260
 Epoch... (1/30 | Step: 300 | Loss: 2.4654769897460938, Learning Rate: 2.9870392609154806e-05)
 Epoch... (1/30 | Step: 300 | Loss: 2.4654769897460938, Learning Rate: 2.9870392609154806e-05)
 Epoch... (1/30 | Step: 300 | Eval Loss: 2.3369832038879395 | Eval rouge1: 36.6481 | Eval rouge2: 12.0172 | Eval rougeL: 33.4031 | Eval rougeLsum: 33.4031 | Eval gen_len: 10.6758 |)
+Epoch... (1/30 | Step: 310 | Loss: 2.2441658973693848, Learning Rate: 2.9866057957406156e-05)
+Epoch... (1/30 | Step: 320 | Loss: 2.381657361984253, Learning Rate: 2.986172512464691e-05)
+Epoch... (1/30 | Step: 330 | Loss: 2.39951753616333, Learning Rate: 2.985739047289826e-05)
+Epoch... (1/30 | Step: 340 | Loss: 2.4004015922546387, Learning Rate: 2.985305582114961e-05)
+Epoch... (1/30 | Step: 350 | Loss: 2.3319690227508545, Learning Rate: 2.984872116940096e-05)
+Epoch... (1/30 | Step: 360 | Loss: 2.3237192630767822, Learning Rate: 2.984438651765231e-05)
+Epoch... (1/30 | Step: 370 | Loss: 2.381218671798706, Learning Rate: 2.984005186590366e-05)
+Epoch... (1/30 | Step: 380 | Loss: 2.309722900390625, Learning Rate: 2.9835715395165607e-05)
+Epoch... (1/30 | Step: 390 | Loss: 2.3941807746887207, Learning Rate: 2.9831380743416958e-05)
+Epoch... (1/30 | Step: 400 | Loss: 2.3451006412506104, Learning Rate: 2.9827046091668308e-05)
+Epoch... (1/30 | Step: 410 | Loss: 2.278620719909668, Learning Rate: 2.982271325890906e-05)
+Epoch... (1/30 | Step: 420 | Loss: 2.258894920349121, Learning Rate: 2.9818378607160412e-05)
+Epoch... (1/30 | Step: 430 | Loss: 2.334801197052002, Learning Rate: 2.9814043955411762e-05)
+Epoch... (1/30 | Step: 440 | Loss: 2.358175754547119, Learning Rate: 2.9809709303663112e-05)
+Epoch... (1/30 | Step: 450 | Loss: 2.342679977416992, Learning Rate: 2.9805374651914462e-05)
+Epoch... (1/30 | Step: 460 | Loss: 2.3427581787109375, Learning Rate: 2.9801040000165813e-05)
+Epoch... (1/30 | Step: 470 | Loss: 2.2662670612335205, Learning Rate: 2.9796705348417163e-05)
+Epoch... (1/30 | Step: 480 | Loss: 2.3363449573516846, Learning Rate: 2.979236887767911e-05)
+Epoch... (1/30 | Step: 490 | Loss: 2.3524205684661865, Learning Rate: 2.978803422593046e-05)
+Epoch... (1/30 | Step: 500 | Loss: 2.33699369430542, Learning Rate: 2.9783701393171214e-05)
+Epoch... (1/30 | Step: 510 | Loss: 2.254800319671631, Learning Rate: 2.9779366741422564e-05)
+Epoch... (1/30 | Step: 520 | Loss: 2.2564821243286133, Learning Rate: 2.9775032089673914e-05)
+Epoch... (1/30 | Step: 530 | Loss: 2.312403678894043, Learning Rate: 2.9770697437925264e-05)
+Epoch... (1/30 | Step: 540 | Loss: 2.361353874206543, Learning Rate: 2.9766362786176614e-05)
+Epoch... (1/30 | Step: 550 | Loss: 2.231563091278076, Learning Rate: 2.9762028134427965e-05)
+Epoch... (1/30 | Step: 560 | Loss: 2.23984956741333, Learning Rate: 2.9757693482679315e-05)
+Epoch... (1/30 | Step: 570 | Loss: 2.294980049133301, Learning Rate: 2.9753358830930665e-05)
+Epoch... (1/30 | Step: 580 | Loss: 2.234550952911377, Learning Rate: 2.9749022360192612e-05)
+Epoch... (1/30 | Step: 590 | Loss: 2.2543816566467285, Learning Rate: 2.9744689527433366e-05)
+Epoch... (1/30 | Step: 600 | Loss: 2.249704360961914, Learning Rate: 2.9740354875684716e-05)
+Epoch... (1/30 | Step: 600 | Loss: 2.249704360961914, Learning Rate: 2.9740354875684716e-05)
+Epoch... (1/30 | Step: 600 | Eval Loss: 2.2133584022521973 | Eval rouge1: 38.2794 | Eval rouge2: 13.1501 | Eval rougeL: 34.8961 | Eval rougeLsum: 34.8948 | Eval gen_len: 11.0128 |)