Saving weights and logs of epoch 4 - step 8700

ckpt_epoch_4_step_8700/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_8700/flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ff36b431c23e7bce105a6846f384c34dd429dc31142684483746910741d9e73
+size 956799284

ckpt_epoch_4_step_8700/special_tokens_map.json

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

ckpt_epoch_4_step_8700/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 sha256:41bffc48241daedd8d86fbb09a8235ddc43129b763d4f7facccf8b2c1deb81c4
-size 5709185
+oid sha256:25e990b0be71c86218c052fd96d52e84fc543525670ee97a9419c3c00374452f
+size 5971189

report.txt

@@ -900,3 +900,35 @@ Epoch... (4/30 | Step: 8390 | Loss: 1.7176601886749268, Learning Rate: 2.6363675
 Epoch... (4/30 | Step: 8400 | Loss: 1.7720857858657837, Learning Rate: 2.635934106365312e-05)
 Epoch... (4/30 | Step: 8400 | Loss: 1.7720857858657837, Learning Rate: 2.635934106365312e-05)
 Epoch... (4/30 | Step: 8400 | Eval Loss: 1.899088978767395 | Eval rouge1: 41.3427 | Eval rouge2: 15.713 | Eval rougeL: 37.6044 | Eval rougeLsum: 37.602 | Eval gen_len: 11.2508 |)
+Epoch... (4/30 | Step: 8410 | Loss: 1.7903679609298706, Learning Rate: 2.635500641190447e-05)
+Epoch... (4/30 | Step: 8420 | Loss: 1.7643471956253052, Learning Rate: 2.635067176015582e-05)
+Epoch... (4/30 | Step: 8430 | Loss: 1.7884368896484375, Learning Rate: 2.634633710840717e-05)
+Epoch... (4/30 | Step: 8440 | Loss: 1.7901930809020996, Learning Rate: 2.634200245665852e-05)
+Epoch... (4/30 | Step: 8450 | Loss: 1.8174161911010742, Learning Rate: 2.6337665985920466e-05)
+Epoch... (4/30 | Step: 8460 | Loss: 1.7797125577926636, Learning Rate: 2.6333331334171817e-05)
+Epoch... (4/30 | Step: 8470 | Loss: 1.743789553642273, Learning Rate: 2.6328996682423167e-05)
+Epoch... (4/30 | Step: 8480 | Loss: 1.7208518981933594, Learning Rate: 2.632466384966392e-05)
+Epoch... (4/30 | Step: 8490 | Loss: 1.7644871473312378, Learning Rate: 2.632032919791527e-05)
+Epoch... (4/30 | Step: 8500 | Loss: 1.8212189674377441, Learning Rate: 2.631599454616662e-05)
+Epoch... (4/30 | Step: 8510 | Loss: 1.7835339307785034, Learning Rate: 2.631165989441797e-05)
+Epoch... (4/30 | Step: 8520 | Loss: 1.768432378768921, Learning Rate: 2.630732524266932e-05)
+Epoch... (4/30 | Step: 8530 | Loss: 1.7398850917816162, Learning Rate: 2.6302990590920672e-05)
+Epoch... (4/30 | Step: 8540 | Loss: 1.7920219898223877, Learning Rate: 2.629865412018262e-05)
+Epoch... (4/30 | Step: 8550 | Loss: 1.8058758974075317, Learning Rate: 2.629431946843397e-05)
+Epoch... (4/30 | Step: 8560 | Loss: 1.8054993152618408, Learning Rate: 2.628998481668532e-05)
+Epoch... (4/30 | Step: 8570 | Loss: 1.7596275806427002, Learning Rate: 2.6285651983926073e-05)
+Epoch... (4/30 | Step: 8580 | Loss: 1.7128454446792603, Learning Rate: 2.6281317332177423e-05)
+Epoch... (4/30 | Step: 8590 | Loss: 1.8160572052001953, Learning Rate: 2.6276982680428773e-05)
+Epoch... (4/30 | Step: 8600 | Loss: 1.7876338958740234, Learning Rate: 2.6272648028680123e-05)
+Epoch... (4/30 | Step: 8610 | Loss: 1.7162377834320068, Learning Rate: 2.6268313376931474e-05)
+Epoch... (4/30 | Step: 8620 | Loss: 1.7962429523468018, Learning Rate: 2.6263978725182824e-05)
+Epoch... (4/30 | Step: 8630 | Loss: 1.7868194580078125, Learning Rate: 2.6259644073434174e-05)
+Epoch... (4/30 | Step: 8640 | Loss: 1.778346061706543, Learning Rate: 2.6255309421685524e-05)
+Epoch... (4/30 | Step: 8650 | Loss: 1.7848930358886719, Learning Rate: 2.6250974769936875e-05)
+Epoch... (4/30 | Step: 8660 | Loss: 1.7496588230133057, Learning Rate: 2.6246640118188225e-05)
+Epoch... (4/30 | Step: 8670 | Loss: 1.7488641738891602, Learning Rate: 2.6242305466439575e-05)
+Epoch... (4/30 | Step: 8680 | Loss: 1.7910881042480469, Learning Rate: 2.6237970814690925e-05)
+Epoch... (4/30 | Step: 8690 | Loss: 1.7799428701400757, Learning Rate: 2.6233636162942275e-05)
+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 |)