Saving weights and logs of epoch 5 - step 10500

ckpt_epoch_5_step_10500/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_10500/flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:674c1237e8cdc6ad843443333947f7e9a4e3e4b5fdc223a32fb7c62386647986
+size 956799284

ckpt_epoch_5_step_10500/special_tokens_map.json

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

ckpt_epoch_5_step_10500/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 sha256:7a9303b77e86d6f8e98142bfedd0b907a8d08982ad9d597a7e46393767dfd9f6
-size 6925813
+oid sha256:4cba0703b4801d675bfb41b213611e9c43ca8fd6d2b7ccd42b3e1e7524301f95
+size 7113288

report.txt

@@ -1094,3 +1094,35 @@ Epoch... (5/30 | Step: 10190 | Loss: 1.683748722076416, Learning Rate: 2.5583442
 Epoch... (5/30 | Step: 10200 | Loss: 1.7239928245544434, Learning Rate: 2.5579107386874966e-05)
 Epoch... (5/30 | Step: 10200 | Loss: 1.7239928245544434, Learning Rate: 2.5579107386874966e-05)
 Epoch... (5/30 | Step: 10200 | Eval Loss: 1.9000166654586792 | Eval rouge1: 41.1061 | Eval rouge2: 15.5697 | Eval rougeL: 37.3807 | Eval rougeLsum: 37.3711 | Eval gen_len: 11.2875 |)
+Epoch... (5/30 | Step: 10210 | Loss: 1.736351728439331, Learning Rate: 2.5574770916136913e-05)
+Epoch... (5/30 | Step: 10220 | Loss: 1.8017604351043701, Learning Rate: 2.5570436264388263e-05)
+Epoch... (5/30 | Step: 10230 | Loss: 1.728968858718872, Learning Rate: 2.5566101612639613e-05)
+Epoch... (5/30 | Step: 10240 | Loss: 1.6958348751068115, Learning Rate: 2.5561766960890964e-05)
+Epoch... (5/30 | Step: 10250 | Loss: 1.756436824798584, Learning Rate: 2.5557434128131717e-05)
+Epoch... (5/30 | Step: 10260 | Loss: 1.7174365520477295, Learning Rate: 2.5553099476383068e-05)
+Epoch... (5/30 | Step: 10270 | Loss: 1.7484798431396484, Learning Rate: 2.5548764824634418e-05)
+Epoch... (5/30 | Step: 10280 | Loss: 1.7174749374389648, Learning Rate: 2.5544428353896365e-05)
+Epoch... (5/30 | Step: 10290 | Loss: 1.7376658916473389, Learning Rate: 2.5540093702147715e-05)
+Epoch... (5/30 | Step: 10300 | Loss: 1.6888067722320557, Learning Rate: 2.5535759050399065e-05)
+Epoch... (5/30 | Step: 10310 | Loss: 1.798421859741211, Learning Rate: 2.5531424398650415e-05)
+Epoch... (5/30 | Step: 10320 | Loss: 1.7474887371063232, Learning Rate: 2.5527089746901765e-05)
+Epoch... (5/30 | Step: 10330 | Loss: 1.6072237491607666, Learning Rate: 2.5522755095153116e-05)
+Epoch... (5/30 | Step: 10340 | Loss: 1.7262811660766602, Learning Rate: 2.551842226239387e-05)
+Epoch... (5/30 | Step: 10350 | Loss: 1.7574151754379272, Learning Rate: 2.551408761064522e-05)
+Epoch... (5/30 | Step: 10360 | Loss: 1.6579294204711914, Learning Rate: 2.550975295889657e-05)
+Epoch... (5/30 | Step: 10370 | Loss: 1.648320198059082, Learning Rate: 2.550541830714792e-05)
+Epoch... (5/30 | Step: 10380 | Loss: 1.6719105243682861, Learning Rate: 2.550108365539927e-05)
+Epoch... (5/30 | Step: 10390 | Loss: 1.670508623123169, Learning Rate: 2.549674900365062e-05)
+Epoch... (5/30 | Step: 10400 | Loss: 1.714751124382019, Learning Rate: 2.5492412532912567e-05)
+Epoch... (5/30 | Step: 10410 | Loss: 1.757665753364563, Learning Rate: 2.5488077881163917e-05)
+Epoch... (5/30 | Step: 10420 | Loss: 1.6976799964904785, Learning Rate: 2.5483743229415268e-05)
+Epoch... (5/30 | Step: 10430 | Loss: 1.692623257637024, Learning Rate: 2.547941039665602e-05)
+Epoch... (5/30 | Step: 10440 | Loss: 1.737560749053955, Learning Rate: 2.5475075744907372e-05)
+Epoch... (5/30 | Step: 10450 | Loss: 1.7558751106262207, Learning Rate: 2.5470741093158722e-05)
+Epoch... (5/30 | Step: 10460 | Loss: 1.7576009035110474, Learning Rate: 2.5466406441410072e-05)
+Epoch... (5/30 | Step: 10470 | Loss: 1.7191178798675537, Learning Rate: 2.5462071789661422e-05)
+Epoch... (5/30 | Step: 10480 | Loss: 1.7180984020233154, Learning Rate: 2.545773531892337e-05)
+Epoch... (5/30 | Step: 10490 | Loss: 1.6861305236816406, Learning Rate: 2.545340066717472e-05)
+Epoch... (5/30 | Step: 10500 | Loss: 1.6550886631011963, Learning Rate: 2.544906601542607e-05)
+Epoch... (5/30 | Step: 10500 | Loss: 1.6550886631011963, Learning Rate: 2.544906601542607e-05)
+Epoch... (5/30 | Step: 10500 | Eval Loss: 1.8986282348632812 | Eval rouge1: 41.38 | Eval rouge2: 15.7211 | Eval rougeL: 37.5574 | Eval rougeLsum: 37.5556 | Eval gen_len: 11.2757 |)