Saving weights and logs of epoch 3 - step 6900

ckpt_epoch_3_step_6900/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_3_step_6900/flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df01c05234220e7fea4e92598162988c48315bb6fa2475b5d66f002875710be9
+size 956799284

ckpt_epoch_3_step_6900/special_tokens_map.json

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

ckpt_epoch_3_step_6900/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 sha256:7393001306606ab94de4948649f7ed5a5b0fe88163d515b69fd6185ce019d4ed
-size 4384512
+oid sha256:22f21a2c86dfa4ac032800a3a00b2b032aca84a755debf64cf5043610e598bc6
+size 4721045

report.txt

@@ -706,3 +706,35 @@ Epoch... (3/30 | Step: 6590 | Loss: 1.836090326309204, Learning Rate: 2.71439093
 Epoch... (3/30 | Step: 6600 | Loss: 1.8392951488494873, Learning Rate: 2.7139572921441868e-05)
 Epoch... (3/30 | Step: 6600 | Loss: 1.8392951488494873, Learning Rate: 2.7139572921441868e-05)
 Epoch... (3/30 | Step: 6600 | Eval Loss: 1.9147193431854248 | Eval rouge1: 41.1766 | Eval rouge2: 15.6082 | Eval rougeL: 37.5075 | Eval rougeLsum: 37.5043 | Eval gen_len: 11.1454 |)
+Epoch... (3/30 | Step: 6610 | Loss: 1.8817616701126099, Learning Rate: 2.7135238269693218e-05)
+Epoch... (3/30 | Step: 6620 | Loss: 1.8995423316955566, Learning Rate: 2.7130905436933972e-05)
+Epoch... (3/30 | Step: 6630 | Loss: 1.7520475387573242, Learning Rate: 2.7126570785185322e-05)
+Epoch... (3/30 | Step: 6640 | Loss: 1.841223955154419, Learning Rate: 2.7122236133436672e-05)
+Epoch... (3/30 | Step: 6650 | Loss: 1.7794084548950195, Learning Rate: 2.7117901481688023e-05)
+Epoch... (3/30 | Step: 6660 | Loss: 1.8177577257156372, Learning Rate: 2.7113566829939373e-05)
+Epoch... (3/30 | Step: 6670 | Loss: 1.844765543937683, Learning Rate: 2.7109232178190723e-05)
+Epoch... (3/30 | Step: 6680 | Loss: 1.87111496925354, Learning Rate: 2.7104897526442073e-05)
+Epoch... (3/30 | Step: 6690 | Loss: 1.8403642177581787, Learning Rate: 2.7100562874693424e-05)
+Epoch... (3/30 | Step: 6700 | Loss: 1.819663643836975, Learning Rate: 2.7096228222944774e-05)
+Epoch... (3/30 | Step: 6710 | Loss: 1.8723413944244385, Learning Rate: 2.7091893571196124e-05)
+Epoch... (3/30 | Step: 6720 | Loss: 1.789346694946289, Learning Rate: 2.7087558919447474e-05)
+Epoch... (3/30 | Step: 6730 | Loss: 1.864307165145874, Learning Rate: 2.7083224267698824e-05)
+Epoch... (3/30 | Step: 6740 | Loss: 1.8256621360778809, Learning Rate: 2.7078889615950175e-05)
+Epoch... (3/30 | Step: 6750 | Loss: 1.8974370956420898, Learning Rate: 2.7074554964201525e-05)
+Epoch... (3/30 | Step: 6760 | Loss: 1.7825756072998047, Learning Rate: 2.7070220312452875e-05)
+Epoch... (3/30 | Step: 6770 | Loss: 1.768592357635498, Learning Rate: 2.7065885660704225e-05)
+Epoch... (3/30 | Step: 6780 | Loss: 1.8202202320098877, Learning Rate: 2.7061551008955576e-05)
+Epoch... (3/30 | Step: 6790 | Loss: 1.8324875831604004, Learning Rate: 2.7057216357206926e-05)
+Epoch... (3/30 | Step: 6800 | Loss: 1.862152099609375, Learning Rate: 2.7052881705458276e-05)
+Epoch... (3/30 | Step: 6810 | Loss: 1.855210781097412, Learning Rate: 2.7048547053709626e-05)
+Epoch... (3/30 | Step: 6820 | Loss: 1.8279563188552856, Learning Rate: 2.7044212401960976e-05)
+Epoch... (3/30 | Step: 6830 | Loss: 1.7613282203674316, Learning Rate: 2.7039877750212327e-05)
+Epoch... (3/30 | Step: 6840 | Loss: 1.8263907432556152, Learning Rate: 2.7035543098463677e-05)
+Epoch... (3/30 | Step: 6850 | Loss: 1.8450121879577637, Learning Rate: 2.7031208446715027e-05)
+Epoch... (3/30 | Step: 6860 | Loss: 1.8444921970367432, Learning Rate: 2.7026873794966377e-05)
+Epoch... (3/30 | Step: 6870 | Loss: 1.7890636920928955, Learning Rate: 2.7022539143217728e-05)
+Epoch... (3/30 | Step: 6880 | Loss: 1.8365561962127686, Learning Rate: 2.701820631045848e-05)
+Epoch... (3/30 | Step: 6890 | Loss: 1.871873378753662, Learning Rate: 2.701387165870983e-05)
+Epoch... (3/30 | Step: 6900 | Loss: 1.7828240394592285, Learning Rate: 2.7009535187971778e-05)
+Epoch... (3/30 | Step: 6900 | Loss: 1.7828240394592285, Learning Rate: 2.7009535187971778e-05)
+Epoch... (3/30 | Step: 6900 | Eval Loss: 1.9094223976135254 | Eval rouge1: 41.6785 | Eval rouge2: 15.9564 | Eval rougeL: 37.9578 | Eval rougeLsum: 37.96 | Eval gen_len: 11.0899 |)