Saving weights and logs of epoch 2 - step 3900

ckpt_epoch_2_step_3900/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_2_step_3900/flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:304d2ac210d09caeedbc1fffb02c34891b770fed5476e8c7d9d39dafcbfe64d3
+size 956799284

ckpt_epoch_2_step_3900/special_tokens_map.json

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

ckpt_epoch_2_step_3900/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:f1d23f552fed3db112f38b466f5215e7ff61d9b537c8a4f736291fb3dc3630e6
-size 2087675
+oid sha256:07b76c9c1f2e7c24294f98dcc031ffc0b2f703a21056085a673734a060758f0f
+size 2322337

report.txt

@@ -384,3 +384,35 @@ Epoch... (2/30 | Step: 3590 | Loss: 2.0506675243377686, Learning Rate: 2.8444297
 Epoch... (2/30 | Step: 3600 | Loss: 1.9117717742919922, Learning Rate: 2.8439964808057994e-05)
 Epoch... (2/30 | Step: 3600 | Loss: 1.9117717742919922, Learning Rate: 2.8439964808057994e-05)
 Epoch... (2/30 | Step: 3600 | Eval Loss: 1.9778660535812378 | Eval rouge1: 40.6615 | Eval rouge2: 15.2172 | Eval rougeL: 36.9778 | Eval rougeLsum: 36.9785 | Eval gen_len: 10.9873 |)
+Epoch... (2/30 | Step: 3610 | Loss: 1.9407380819320679, Learning Rate: 2.8435630156309344e-05)
+Epoch... (2/30 | Step: 3620 | Loss: 1.8952865600585938, Learning Rate: 2.8431295504560694e-05)
+Epoch... (2/30 | Step: 3630 | Loss: 1.8948352336883545, Learning Rate: 2.8426960852812044e-05)
+Epoch... (2/30 | Step: 3640 | Loss: 2.03857421875, Learning Rate: 2.8422626201063395e-05)
+Epoch... (2/30 | Step: 3650 | Loss: 1.9013903141021729, Learning Rate: 2.8418291549314745e-05)
+Epoch... (2/30 | Step: 3660 | Loss: 1.845206618309021, Learning Rate: 2.8413956897566095e-05)
+Epoch... (2/30 | Step: 3670 | Loss: 1.7374927997589111, Learning Rate: 2.8409622245817445e-05)
+Epoch... (2/30 | Step: 3680 | Loss: 1.9721872806549072, Learning Rate: 2.8405285775079392e-05)
+Epoch... (2/30 | Step: 3690 | Loss: 1.9401315450668335, Learning Rate: 2.8400952942320146e-05)
+Epoch... (2/30 | Step: 3700 | Loss: 1.960228443145752, Learning Rate: 2.8396618290571496e-05)
+Epoch... (2/30 | Step: 3710 | Loss: 2.104597806930542, Learning Rate: 2.8392283638822846e-05)
+Epoch... (2/30 | Step: 3720 | Loss: 1.9455502033233643, Learning Rate: 2.8387948987074196e-05)
+Epoch... (2/30 | Step: 3730 | Loss: 2.000375747680664, Learning Rate: 2.8383614335325547e-05)
+Epoch... (2/30 | Step: 3740 | Loss: 2.044059991836548, Learning Rate: 2.8379279683576897e-05)
+Epoch... (2/30 | Step: 3750 | Loss: 1.90779447555542, Learning Rate: 2.8374945031828247e-05)
+Epoch... (2/30 | Step: 3760 | Loss: 1.958655595779419, Learning Rate: 2.8370610380079597e-05)
+Epoch... (2/30 | Step: 3770 | Loss: 1.943934440612793, Learning Rate: 2.8366275728330947e-05)
+Epoch... (2/30 | Step: 3780 | Loss: 1.9462363719940186, Learning Rate: 2.83619428955717e-05)
+Epoch... (2/30 | Step: 3790 | Loss: 2.00119686126709, Learning Rate: 2.8357606424833648e-05)
+Epoch... (2/30 | Step: 3800 | Loss: 1.8953402042388916, Learning Rate: 2.8353271773084998e-05)
+Epoch... (2/30 | Step: 3810 | Loss: 1.9074665307998657, Learning Rate: 2.834893712133635e-05)
+Epoch... (2/30 | Step: 3820 | Loss: 1.9436546564102173, Learning Rate: 2.83446024695877e-05)
+Epoch... (2/30 | Step: 3830 | Loss: 1.9025335311889648, Learning Rate: 2.834026781783905e-05)
+Epoch... (2/30 | Step: 3840 | Loss: 1.9439079761505127, Learning Rate: 2.83359331660904e-05)
+Epoch... (2/30 | Step: 3850 | Loss: 1.9517011642456055, Learning Rate: 2.833159851434175e-05)
+Epoch... (2/30 | Step: 3860 | Loss: 1.9390623569488525, Learning Rate: 2.83272638625931e-05)
+Epoch... (2/30 | Step: 3870 | Loss: 1.8799810409545898, Learning Rate: 2.8322931029833853e-05)
+Epoch... (2/30 | Step: 3880 | Loss: 1.9533662796020508, Learning Rate: 2.83185945590958e-05)
+Epoch... (2/30 | Step: 3890 | Loss: 2.0305581092834473, Learning Rate: 2.831425990734715e-05)
+Epoch... (2/30 | Step: 3900 | Loss: 1.985913872718811, Learning Rate: 2.83099252555985e-05)
+Epoch... (2/30 | Step: 3900 | Loss: 1.985913872718811, Learning Rate: 2.83099252555985e-05)
+Epoch... (2/30 | Step: 3900 | Eval Loss: 1.9652690887451172 | Eval rouge1: 41.1961 | Eval rouge2: 15.6232 | Eval rougeL: 37.4628 | Eval rougeLsum: 37.4635 | Eval gen_len: 10.8986 |)