Saving weights and logs of epoch 4 - step 9000

ckpt_epoch_4_step_9000/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_4_step_9000/flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f794310f21e32d145dda50ccc77f17a40a0c44259c96de886b6c45e5a3e56809
+size 956799284

ckpt_epoch_4_step_9000/special_tokens_map.json

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

ckpt_epoch_4_step_9000/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 sha256:25e990b0be71c86218c052fd96d52e84fc543525670ee97a9419c3c00374452f
-size 5971189
+oid sha256:f152f6cd11c8a0da055463400d0c67df551f2837826c599bba23c83786dbe2e9
+size 6277293

report.txt

@@ -932,3 +932,35 @@ Epoch... (4/30 | Step: 8690 | Loss: 1.7799428701400757, Learning Rate: 2.6233636
 Epoch... (4/30 | Step: 8700 | Loss: 1.7098944187164307, Learning Rate: 2.6229301511193626e-05)
 Epoch... (4/30 | Step: 8700 | Loss: 1.7098944187164307, Learning Rate: 2.6229301511193626e-05)
 Epoch... (4/30 | Step: 8700 | Eval Loss: 1.9023772478103638 | Eval rouge1: 41.0716 | Eval rouge2: 15.5551 | Eval rougeL: 37.3622 | Eval rougeLsum: 37.3627 | Eval gen_len: 11.3028 |)
+Epoch... (4/30 | Step: 8710 | Loss: 1.7892546653747559, Learning Rate: 2.6224966859444976e-05)
+Epoch... (4/30 | Step: 8720 | Loss: 1.82383131980896, Learning Rate: 2.6220632207696326e-05)
+Epoch... (4/30 | Step: 8730 | Loss: 1.7643616199493408, Learning Rate: 2.6216295736958273e-05)
+Epoch... (4/30 | Step: 8740 | Loss: 1.715694546699524, Learning Rate: 2.6211962904199027e-05)
+Epoch... (4/30 | Step: 8750 | Loss: 1.7043194770812988, Learning Rate: 2.6207628252450377e-05)
+Epoch... (4/30 | Step: 8760 | Loss: 1.7660789489746094, Learning Rate: 2.6203293600701727e-05)
+Epoch... (4/30 | Step: 8770 | Loss: 1.820483684539795, Learning Rate: 2.6198958948953077e-05)
+Epoch... (4/30 | Step: 8780 | Loss: 1.7926051616668701, Learning Rate: 2.6194624297204427e-05)
+Epoch... (4/30 | Step: 8790 | Loss: 1.743436336517334, Learning Rate: 2.6190289645455778e-05)
+Epoch... (4/30 | Step: 8800 | Loss: 1.7975858449935913, Learning Rate: 2.6185954993707128e-05)
+Epoch... (4/30 | Step: 8810 | Loss: 1.7968688011169434, Learning Rate: 2.6181620341958478e-05)
+Epoch... (4/30 | Step: 8820 | Loss: 1.7715320587158203, Learning Rate: 2.617728569020983e-05)
+Epoch... (4/30 | Step: 8830 | Loss: 1.7700495719909668, Learning Rate: 2.6172952857450582e-05)
+Epoch... (4/30 | Step: 8840 | Loss: 1.7371662855148315, Learning Rate: 2.6168618205701932e-05)
+Epoch... (4/30 | Step: 8850 | Loss: 1.6575849056243896, Learning Rate: 2.616428173496388e-05)
+Epoch... (4/30 | Step: 8860 | Loss: 1.7197023630142212, Learning Rate: 2.615994708321523e-05)
+Epoch... (4/30 | Step: 8870 | Loss: 1.7932194471359253, Learning Rate: 2.615561243146658e-05)
+Epoch... (4/30 | Step: 8880 | Loss: 1.7538230419158936, Learning Rate: 2.615127777971793e-05)
+Epoch... (4/30 | Step: 8890 | Loss: 1.8080253601074219, Learning Rate: 2.614694312796928e-05)
+Epoch... (4/30 | Step: 8900 | Loss: 1.7145426273345947, Learning Rate: 2.614260847622063e-05)
+Epoch... (4/30 | Step: 8910 | Loss: 1.7602368593215942, Learning Rate: 2.613827382447198e-05)
+Epoch... (4/30 | Step: 8920 | Loss: 1.7841060161590576, Learning Rate: 2.613393917272333e-05)
+Epoch... (4/30 | Step: 8930 | Loss: 1.7612416744232178, Learning Rate: 2.612960452097468e-05)
+Epoch... (4/30 | Step: 8940 | Loss: 1.7373647689819336, Learning Rate: 2.612526986922603e-05)
+Epoch... (4/30 | Step: 8950 | Loss: 1.8240079879760742, Learning Rate: 2.612093521747738e-05)
+Epoch... (4/30 | Step: 8960 | Loss: 1.81781005859375, Learning Rate: 2.611660056572873e-05)
+Epoch... (4/30 | Step: 8970 | Loss: 1.6823644638061523, Learning Rate: 2.611226591398008e-05)
+Epoch... (4/30 | Step: 8980 | Loss: 1.7390031814575195, Learning Rate: 2.6107931262231432e-05)
+Epoch... (4/30 | Step: 8990 | Loss: 1.7301363945007324, Learning Rate: 2.6103596610482782e-05)
+Epoch... (4/30 | Step: 9000 | Loss: 1.743155837059021, Learning Rate: 2.6099261958734132e-05)
+Epoch... (4/30 | Step: 9000 | Loss: 1.743155837059021, Learning Rate: 2.6099261958734132e-05)
+Epoch... (4/30 | Step: 9000 | Eval Loss: 1.8965791463851929 | Eval rouge1: 41.5249 | Eval rouge2: 15.9328 | Eval rougeL: 37.7734 | Eval rougeLsum: 37.7601 | Eval gen_len: 11.0642 |)