Saving weights and logs of epoch 4 - step 8400

ckpt_epoch_4_step_8400/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_8400/flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d445cd14d0a1eaac96e8289e4d0f71b67c93d87935b8a79494ca63890a18917
+size 956799284

ckpt_epoch_4_step_8400/special_tokens_map.json

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

ckpt_epoch_4_step_8400/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:cede2fb89d00b5f76fd199469489cf6c6c76d9c8c25099f83f7a4819fdee41f6
-size 5491281
+oid sha256:41bffc48241daedd8d86fbb09a8235ddc43129b763d4f7facccf8b2c1deb81c4
+size 5709185

report.txt

@@ -868,3 +868,35 @@ Epoch... (4/30 | Step: 8090 | Loss: 1.736276626586914, Learning Rate: 2.64937134
 Epoch... (4/30 | Step: 8100 | Loss: 1.7609823942184448, Learning Rate: 2.648937879712321e-05)
 Epoch... (4/30 | Step: 8100 | Loss: 1.7609823942184448, Learning Rate: 2.648937879712321e-05)
 Epoch... (4/30 | Step: 8100 | Eval Loss: 1.9074890613555908 | Eval rouge1: 41.3555 | Eval rouge2: 15.7164 | Eval rougeL: 37.6243 | Eval rougeLsum: 37.6188 | Eval gen_len: 11.1658 |)
+Epoch... (4/30 | Step: 8110 | Loss: 1.7898554801940918, Learning Rate: 2.648504414537456e-05)
+Epoch... (4/30 | Step: 8120 | Loss: 1.901104211807251, Learning Rate: 2.6480711312615313e-05)
+Epoch... (4/30 | Step: 8130 | Loss: 1.707322359085083, Learning Rate: 2.6476376660866663e-05)
+Epoch... (4/30 | Step: 8140 | Loss: 1.9236220121383667, Learning Rate: 2.6472042009118013e-05)
+Epoch... (4/30 | Step: 8150 | Loss: 1.7018535137176514, Learning Rate: 2.646770553837996e-05)
+Epoch... (4/30 | Step: 8160 | Loss: 1.811523675918579, Learning Rate: 2.646337088663131e-05)
+Epoch... (4/30 | Step: 8170 | Loss: 1.7439903020858765, Learning Rate: 2.645903623488266e-05)
+Epoch... (4/30 | Step: 8180 | Loss: 1.7460384368896484, Learning Rate: 2.645470158313401e-05)
+Epoch... (4/30 | Step: 8190 | Loss: 1.6671082973480225, Learning Rate: 2.645036693138536e-05)
+Epoch... (4/30 | Step: 8200 | Loss: 1.8321022987365723, Learning Rate: 2.644603227963671e-05)
+Epoch... (4/30 | Step: 8210 | Loss: 1.721744418144226, Learning Rate: 2.6441699446877465e-05)
+Epoch... (4/30 | Step: 8220 | Loss: 1.7297766208648682, Learning Rate: 2.6437364795128815e-05)
+Epoch... (4/30 | Step: 8230 | Loss: 1.7734706401824951, Learning Rate: 2.6433030143380165e-05)
+Epoch... (4/30 | Step: 8240 | Loss: 1.7746353149414062, Learning Rate: 2.6428695491631515e-05)
+Epoch... (4/30 | Step: 8250 | Loss: 1.7374098300933838, Learning Rate: 2.6424360839882866e-05)
+Epoch... (4/30 | Step: 8260 | Loss: 1.7754874229431152, Learning Rate: 2.6420024369144812e-05)
+Epoch... (4/30 | Step: 8270 | Loss: 1.8101651668548584, Learning Rate: 2.6415689717396162e-05)
+Epoch... (4/30 | Step: 8280 | Loss: 1.7362170219421387, Learning Rate: 2.6411355065647513e-05)
+Epoch... (4/30 | Step: 8290 | Loss: 1.7455593347549438, Learning Rate: 2.6407020413898863e-05)
+Epoch... (4/30 | Step: 8300 | Loss: 1.7678217887878418, Learning Rate: 2.6402687581139617e-05)
+Epoch... (4/30 | Step: 8310 | Loss: 1.7820069789886475, Learning Rate: 2.6398352929390967e-05)
+Epoch... (4/30 | Step: 8320 | Loss: 1.7654781341552734, Learning Rate: 2.6394018277642317e-05)
+Epoch... (4/30 | Step: 8330 | Loss: 1.7164040803909302, Learning Rate: 2.6389683625893667e-05)
+Epoch... (4/30 | Step: 8340 | Loss: 1.778324842453003, Learning Rate: 2.6385347155155614e-05)
+Epoch... (4/30 | Step: 8350 | Loss: 1.7316615581512451, Learning Rate: 2.6381012503406964e-05)
+Epoch... (4/30 | Step: 8360 | Loss: 1.6872611045837402, Learning Rate: 2.6376677851658314e-05)
+Epoch... (4/30 | Step: 8370 | Loss: 1.7629599571228027, Learning Rate: 2.6372343199909665e-05)
+Epoch... (4/30 | Step: 8380 | Loss: 1.6997967958450317, Learning Rate: 2.6368008548161015e-05)
+Epoch... (4/30 | Step: 8390 | Loss: 1.7176601886749268, Learning Rate: 2.636367571540177e-05)
+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 |)