Saving weights and logs of epoch 1 - step 900

ckpt_epoch_1_step_900/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_1_step_900/flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1d0b927e570231d347e00243681983d57d4f3e538cc11a9068639e9238e6589
+size 956799284

ckpt_epoch_1_step_900/special_tokens_map.json

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

ckpt_epoch_1_step_900/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 sha256:562867a61556aee91ef3e0cf8f6cc2a70b213782f2e3c8d08adf155b7d68eb1c
-size 132814
+oid sha256:590ece01b6ce062357e7d3d3c9886190e92b2b3ebcc1ec9dde0ffea6bf971bd1
+size 265351

report.txt

@@ -62,3 +62,35 @@ Epoch... (1/30 | Step: 590 | Loss: 2.2543816566467285, Learning Rate: 2.97446895
 Epoch... (1/30 | Step: 600 | Loss: 2.249704360961914, Learning Rate: 2.9740354875684716e-05)
 Epoch... (1/30 | Step: 600 | Loss: 2.249704360961914, Learning Rate: 2.9740354875684716e-05)
 Epoch... (1/30 | Step: 600 | Eval Loss: 2.2133584022521973 | Eval rouge1: 38.2794 | Eval rouge2: 13.1501 | Eval rougeL: 34.8961 | Eval rougeLsum: 34.8948 | Eval gen_len: 11.0128 |)
+Epoch... (1/30 | Step: 610 | Loss: 2.2616004943847656, Learning Rate: 2.9736020223936066e-05)
+Epoch... (1/30 | Step: 620 | Loss: 2.280752658843994, Learning Rate: 2.9731685572187416e-05)
+Epoch... (1/30 | Step: 630 | Loss: 2.1695902347564697, Learning Rate: 2.9727350920438766e-05)
+Epoch... (1/30 | Step: 640 | Loss: 2.3159074783325195, Learning Rate: 2.9723016268690117e-05)
+Epoch... (1/30 | Step: 650 | Loss: 2.2354726791381836, Learning Rate: 2.9718681616941467e-05)
+Epoch... (1/30 | Step: 660 | Loss: 2.2967095375061035, Learning Rate: 2.9714346965192817e-05)
+Epoch... (1/30 | Step: 670 | Loss: 2.3010551929473877, Learning Rate: 2.9710012313444167e-05)
+Epoch... (1/30 | Step: 680 | Loss: 2.292668342590332, Learning Rate: 2.9705677661695518e-05)
+Epoch... (1/30 | Step: 690 | Loss: 2.195081949234009, Learning Rate: 2.9701343009946868e-05)
+Epoch... (1/30 | Step: 700 | Loss: 2.296633720397949, Learning Rate: 2.9697008358198218e-05)
+Epoch... (1/30 | Step: 710 | Loss: 2.149764060974121, Learning Rate: 2.9692673706449568e-05)
+Epoch... (1/30 | Step: 720 | Loss: 2.2461729049682617, Learning Rate: 2.968833905470092e-05)
+Epoch... (1/30 | Step: 730 | Loss: 2.2976291179656982, Learning Rate: 2.968400440295227e-05)
+Epoch... (1/30 | Step: 740 | Loss: 2.2700982093811035, Learning Rate: 2.967966975120362e-05)
+Epoch... (1/30 | Step: 750 | Loss: 2.2898383140563965, Learning Rate: 2.967533509945497e-05)
+Epoch... (1/30 | Step: 760 | Loss: 2.2785892486572266, Learning Rate: 2.967100044770632e-05)
+Epoch... (1/30 | Step: 770 | Loss: 2.1977713108062744, Learning Rate: 2.966666579595767e-05)
+Epoch... (1/30 | Step: 780 | Loss: 2.214864730834961, Learning Rate: 2.966233114420902e-05)
+Epoch... (1/30 | Step: 790 | Loss: 2.2334184646606445, Learning Rate: 2.965799649246037e-05)
+Epoch... (1/30 | Step: 800 | Loss: 2.2037973403930664, Learning Rate: 2.965366184071172e-05)
+Epoch... (1/30 | Step: 810 | Loss: 2.174184560775757, Learning Rate: 2.964932718896307e-05)
+Epoch... (1/30 | Step: 820 | Loss: 2.2716355323791504, Learning Rate: 2.964499253721442e-05)
+Epoch... (1/30 | Step: 830 | Loss: 2.193842887878418, Learning Rate: 2.964065788546577e-05)
+Epoch... (1/30 | Step: 840 | Loss: 2.249634265899658, Learning Rate: 2.963632323371712e-05)
+Epoch... (1/30 | Step: 850 | Loss: 2.237217426300049, Learning Rate: 2.963198858196847e-05)
+Epoch... (1/30 | Step: 860 | Loss: 2.172455310821533, Learning Rate: 2.9627655749209225e-05)
+Epoch... (1/30 | Step: 870 | Loss: 2.05983829498291, Learning Rate: 2.9623319278471172e-05)
+Epoch... (1/30 | Step: 880 | Loss: 2.3632073402404785, Learning Rate: 2.9618984626722522e-05)
+Epoch... (1/30 | Step: 890 | Loss: 2.254265785217285, Learning Rate: 2.9614649974973872e-05)
+Epoch... (1/30 | Step: 900 | Loss: 2.2401223182678223, Learning Rate: 2.9610315323225223e-05)
+Epoch... (1/30 | Step: 900 | Loss: 2.2401223182678223, Learning Rate: 2.9610315323225223e-05)
+Epoch... (1/30 | Step: 900 | Eval Loss: 2.152062177658081 | Eval rouge1: 39.5335 | Eval rouge2: 14.3557 | Eval rougeL: 35.8974 | Eval rougeLsum: 35.9057 | Eval gen_len: 10.8698 |)