Saving weights and logs of epoch 5 - step 11535

ckpt_epoch_5_step_11535/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_11535/flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:079e1b7a740adaebaaf2d689fae1ba9aa12cbb284d8bb5cfb3c4c256a8b676b3
+size 956799284

ckpt_epoch_5_step_11535/special_tokens_map.json

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

ckpt_epoch_5_step_11535/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 sha256:39443c410f343e9da2c6a5352fdaf42a4cbc74abe1f51ebf40bfde9397212853
-size 7940313
+oid sha256:04007cf6b329171749452c6fd460a130288f72a6679059781ec25c8a7157111a
+size 8279933

report.txt

@@ -1222,3 +1222,18 @@ Epoch... (5/30 | Step: 11390 | Loss: 1.6287914514541626, Learning Rate: 2.506328
 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 |)
+Epoch... (5/30 | Step: 11410 | Loss: 1.6782784461975098, Learning Rate: 2.5054616344277747e-05)
+Epoch... (5/30 | Step: 11420 | Loss: 1.742269515991211, Learning Rate: 2.5050281692529097e-05)
+Epoch... (5/30 | Step: 11430 | Loss: 1.603810429573059, Learning Rate: 2.5045947040780447e-05)
+Epoch... (5/30 | Step: 11440 | Loss: 1.6971403360366821, Learning Rate: 2.5041612389031798e-05)
+Epoch... (5/30 | Step: 11450 | Loss: 1.7365331649780273, Learning Rate: 2.5037275918293744e-05)
+Epoch... (5/30 | Step: 11460 | Loss: 1.7393994331359863, Learning Rate: 2.5032941266545095e-05)
+Epoch... (5/30 | Step: 11470 | Loss: 1.6623597145080566, Learning Rate: 2.5028606614796445e-05)
+Epoch... (5/30 | Step: 11480 | Loss: 1.687732219696045, Learning Rate: 2.5024271963047795e-05)
+Epoch... (5/30 | Step: 11490 | Loss: 1.7002153396606445, Learning Rate: 2.501993913028855e-05)
+Epoch... (5/30 | Step: 11500 | Loss: 1.730302095413208, Learning Rate: 2.50156044785399e-05)
+Epoch... (5/30 | Step: 11510 | Loss: 1.7404625415802002, Learning Rate: 2.501126982679125e-05)
+Epoch... (5/30 | Step: 11520 | Loss: 1.739749789237976, Learning Rate: 2.50069351750426e-05)
+Epoch... (5/30 | Step: 11530 | Loss: 1.7267487049102783, Learning Rate: 2.500260052329395e-05)
+Epoch... (5/30 | Step: 11535 | Loss: 1.6310797929763794, Learning Rate: 2.5000434106914327e-05)
+Epoch... (5/30 | Step: 11535 | Eval Loss: 1.8884644508361816 | Eval rouge1: 41.1904 | Eval rouge2: 15.6084 | Eval rougeL: 37.3854 | Eval rougeLsum: 37.3791 | Eval gen_len: 11.4548 |)