Saving weights and logs of epoch 3 - step 6600

ckpt_epoch_3_step_6600/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_6600/flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b3112920889ca6b2f080496ed5eaee0f60d811769cca6b668023d9f26665373
+size 956799284

ckpt_epoch_3_step_6600/special_tokens_map.json

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

ckpt_epoch_3_step_6600/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 sha256:67a547018b7633703cf8dcc2c10148f6a6c0cad5086b7bec89b417804e442b18
-size 4092079
+oid sha256:7393001306606ab94de4948649f7ed5a5b0fe88163d515b69fd6185ce019d4ed
+size 4384512

report.txt

@@ -674,3 +674,35 @@ Epoch... (3/30 | Step: 6290 | Loss: 1.821446180343628, Learning Rate: 2.72739489
 Epoch... (3/30 | Step: 6300 | Loss: 1.8445713520050049, Learning Rate: 2.7269614292890765e-05)
 Epoch... (3/30 | Step: 6300 | Loss: 1.8445713520050049, Learning Rate: 2.7269614292890765e-05)
 Epoch... (3/30 | Step: 6300 | Eval Loss: 1.9208292961120605 | Eval rouge1: 41.3445 | Eval rouge2: 15.639 | Eval rougeL: 37.5483 | Eval rougeLsum: 37.5456 | Eval gen_len: 11.2487 |)
+Epoch... (3/30 | Step: 6310 | Loss: 1.8458572626113892, Learning Rate: 2.7265279641142115e-05)
+Epoch... (3/30 | Step: 6320 | Loss: 1.7985508441925049, Learning Rate: 2.726094317040406e-05)
+Epoch... (3/30 | Step: 6330 | Loss: 1.751726508140564, Learning Rate: 2.7256608518655412e-05)
+Epoch... (3/30 | Step: 6340 | Loss: 1.8094416856765747, Learning Rate: 2.7252273866906762e-05)
+Epoch... (3/30 | Step: 6350 | Loss: 1.853166937828064, Learning Rate: 2.7247941034147516e-05)
+Epoch... (3/30 | Step: 6360 | Loss: 1.8393105268478394, Learning Rate: 2.7243606382398866e-05)
+Epoch... (3/30 | Step: 6370 | Loss: 1.8263094425201416, Learning Rate: 2.7239271730650216e-05)
+Epoch... (3/30 | Step: 6380 | Loss: 1.804229974746704, Learning Rate: 2.7234937078901567e-05)
+Epoch... (3/30 | Step: 6390 | Loss: 1.820934772491455, Learning Rate: 2.7230602427152917e-05)
+Epoch... (3/30 | Step: 6400 | Loss: 1.9347383975982666, Learning Rate: 2.7226265956414863e-05)
+Epoch... (3/30 | Step: 6410 | Loss: 1.873093605041504, Learning Rate: 2.7221931304666214e-05)
+Epoch... (3/30 | Step: 6420 | Loss: 1.8458762168884277, Learning Rate: 2.7217596652917564e-05)
+Epoch... (3/30 | Step: 6430 | Loss: 1.8492844104766846, Learning Rate: 2.7213262001168914e-05)
+Epoch... (3/30 | Step: 6440 | Loss: 1.794797420501709, Learning Rate: 2.7208929168409668e-05)
+Epoch... (3/30 | Step: 6450 | Loss: 1.7921502590179443, Learning Rate: 2.7204594516661018e-05)
+Epoch... (3/30 | Step: 6460 | Loss: 1.7883315086364746, Learning Rate: 2.720025986491237e-05)
+Epoch... (3/30 | Step: 6470 | Loss: 1.8689000606536865, Learning Rate: 2.719592521316372e-05)
+Epoch... (3/30 | Step: 6480 | Loss: 1.8820496797561646, Learning Rate: 2.719159056141507e-05)
+Epoch... (3/30 | Step: 6490 | Loss: 1.8595609664916992, Learning Rate: 2.718725590966642e-05)
+Epoch... (3/30 | Step: 6500 | Loss: 1.7791099548339844, Learning Rate: 2.718292125791777e-05)
+Epoch... (3/30 | Step: 6510 | Loss: 1.7369716167449951, Learning Rate: 2.7178584787179716e-05)
+Epoch... (3/30 | Step: 6520 | Loss: 1.907957673072815, Learning Rate: 2.7174250135431066e-05)
+Epoch... (3/30 | Step: 6530 | Loss: 1.8726749420166016, Learning Rate: 2.716991730267182e-05)
+Epoch... (3/30 | Step: 6540 | Loss: 1.8146827220916748, Learning Rate: 2.716558265092317e-05)
+Epoch... (3/30 | Step: 6550 | Loss: 1.8158860206604004, Learning Rate: 2.716124799917452e-05)
+Epoch... (3/30 | Step: 6560 | Loss: 1.8074976205825806, Learning Rate: 2.715691334742587e-05)
+Epoch... (3/30 | Step: 6570 | Loss: 1.8178911209106445, Learning Rate: 2.715257869567722e-05)
+Epoch... (3/30 | Step: 6580 | Loss: 1.8084090948104858, Learning Rate: 2.714824404392857e-05)
+Epoch... (3/30 | Step: 6590 | Loss: 1.836090326309204, Learning Rate: 2.714390939217992e-05)
+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 |)