Saving weights and logs of epoch 5 - step 11400

ckpt_epoch_5_step_11400/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_11400/flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcee950d429084dbb80d3633d87f53a21d0e80b2ef7a0e2ece462fd095a31a1b
+size 956799284

ckpt_epoch_5_step_11400/special_tokens_map.json

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

ckpt_epoch_5_step_11400/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 sha256:681a88aa5633a014c53c53c962c9516bf2db3b4cb49d076e3341238b2acab5d7
-size 7620538
+oid sha256:39443c410f343e9da2c6a5352fdaf42a4cbc74abe1f51ebf40bfde9397212853
+size 7940313

report.txt

@@ -1190,3 +1190,35 @@ Epoch... (5/30 | Step: 11090 | Loss: 1.6137720346450806, Learning Rate: 2.519332
 Epoch... (5/30 | Step: 11100 | Loss: 1.6390674114227295, Learning Rate: 2.5188988729496486e-05)
 Epoch... (5/30 | Step: 11100 | Loss: 1.6390674114227295, Learning Rate: 2.5188988729496486e-05)
 Epoch... (5/30 | Step: 11100 | Eval Loss: 1.8910801410675049 | Eval rouge1: 41.3667 | Eval rouge2: 15.8648 | Eval rougeL: 37.6418 | Eval rougeLsum: 37.64 | Eval gen_len: 11.2866 |)
+Epoch... (5/30 | Step: 11110 | Loss: 1.6775529384613037, Learning Rate: 2.5184654077747837e-05)
+Epoch... (5/30 | Step: 11120 | Loss: 1.6618034839630127, Learning Rate: 2.5180319425999187e-05)
+Epoch... (5/30 | Step: 11130 | Loss: 1.8106663227081299, Learning Rate: 2.5175984774250537e-05)
+Epoch... (5/30 | Step: 11140 | Loss: 1.7148308753967285, Learning Rate: 2.517165194149129e-05)
+Epoch... (5/30 | Step: 11150 | Loss: 1.7115646600723267, Learning Rate: 2.516731728974264e-05)
+Epoch... (5/30 | Step: 11160 | Loss: 1.7114417552947998, Learning Rate: 2.516298263799399e-05)
+Epoch... (5/30 | Step: 11170 | Loss: 1.6694353818893433, Learning Rate: 2.515864798624534e-05)
+Epoch... (5/30 | Step: 11180 | Loss: 1.7138220071792603, Learning Rate: 2.5154311515507288e-05)
+Epoch... (5/30 | Step: 11190 | Loss: 1.770442247390747, Learning Rate: 2.514997686375864e-05)
+Epoch... (5/30 | Step: 11200 | Loss: 1.634385108947754, Learning Rate: 2.514564221200999e-05)
+Epoch... (5/30 | Step: 11210 | Loss: 1.7121963500976562, Learning Rate: 2.514130756026134e-05)
+Epoch... (5/30 | Step: 11220 | Loss: 1.6640175580978394, Learning Rate: 2.5136974727502093e-05)
+Epoch... (5/30 | Step: 11230 | Loss: 1.72880220413208, Learning Rate: 2.5132640075753443e-05)
+Epoch... (5/30 | Step: 11240 | Loss: 1.7038096189498901, Learning Rate: 2.5128305424004793e-05)
+Epoch... (5/30 | Step: 11250 | Loss: 1.737168788909912, Learning Rate: 2.512396895326674e-05)
+Epoch... (5/30 | Step: 11260 | Loss: 1.6961932182312012, Learning Rate: 2.511963430151809e-05)
+Epoch... (5/30 | Step: 11270 | Loss: 1.7822821140289307, Learning Rate: 2.511529964976944e-05)
+Epoch... (5/30 | Step: 11280 | Loss: 1.7194281816482544, Learning Rate: 2.511096499802079e-05)
+Epoch... (5/30 | Step: 11290 | Loss: 1.680819034576416, Learning Rate: 2.510663034627214e-05)
+Epoch... (5/30 | Step: 11300 | Loss: 1.7248175144195557, Learning Rate: 2.510229569452349e-05)
+Epoch... (5/30 | Step: 11310 | Loss: 1.7197959423065186, Learning Rate: 2.5097962861764245e-05)
+Epoch... (5/30 | Step: 11320 | Loss: 1.6556663513183594, Learning Rate: 2.5093628210015595e-05)
+Epoch... (5/30 | Step: 11330 | Loss: 1.714162826538086, Learning Rate: 2.5089293558266945e-05)
+Epoch... (5/30 | Step: 11340 | Loss: 1.5587143898010254, Learning Rate: 2.5084958906518295e-05)
+Epoch... (5/30 | Step: 11350 | Loss: 1.675426959991455, Learning Rate: 2.5080624254769646e-05)
+Epoch... (5/30 | Step: 11360 | Loss: 1.6751116514205933, Learning Rate: 2.5076289603020996e-05)
+Epoch... (5/30 | Step: 11370 | Loss: 1.624657154083252, Learning Rate: 2.5071953132282943e-05)
+Epoch... (5/30 | Step: 11380 | Loss: 1.6660606861114502, Learning Rate: 2.5067618480534293e-05)
+Epoch... (5/30 | Step: 11390 | Loss: 1.6287914514541626, Learning Rate: 2.5063283828785643e-05)
+Epoch... (5/30 | Step: 11400 | Loss: 1.7122278213500977, Learning Rate: 2.5058950996026397e-05)
+Epoch... (5/30 | Step: 11400 | Loss: 1.7122278213500977, Learning Rate: 2.5058950996026397e-05)
+Epoch... (5/30 | Step: 11400 | Eval Loss: 1.8902904987335205 | Eval rouge1: 41.2493 | Eval rouge2: 15.7217 | Eval rougeL: 37.5034 | Eval rougeLsum: 37.4983 | Eval gen_len: 11.3028 |)