Saving weights and logs of epoch 1 - step 2307

ckpt_epoch_1_step_2307/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_2307/flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dde06ed03ab4322bd3608f6f4f4f3423330306239b35882cc56019e977bb962
+size 956799284

ckpt_epoch_1_step_2307/special_tokens_map.json

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

ckpt_epoch_1_step_2307/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 sha256:9af925175aac37fd8a08fcb838c389c9f9afd0453bacf7a4475e8cbf8e0126ad
-size 1236499
+oid sha256:ff4efbdcba1dbd6214d2af848719e66b6c8b1d25362fc6704362fb5bf660d749
+size 1575865

report.txt

@@ -222,3 +222,25 @@ Epoch... (1/30 | Step: 2090 | Loss: 2.1344692707061768, Learning Rate: 2.9094493
 Epoch... (1/30 | Step: 2100 | Loss: 2.0788259506225586, Learning Rate: 2.9090160751366057e-05)
 Epoch... (1/30 | Step: 2100 | Loss: 2.0788259506225586, Learning Rate: 2.9090160751366057e-05)
 Epoch... (1/30 | Step: 2100 | Eval Loss: 2.037459373474121 | Eval rouge1: 40.5198 | Eval rouge2: 15.162 | Eval rougeL: 36.9107 | Eval rougeLsum: 36.9123 | Eval gen_len: 10.8398 |)
+Epoch... (1/30 | Step: 2110 | Loss: 2.0843522548675537, Learning Rate: 2.9085826099617407e-05)
+Epoch... (1/30 | Step: 2120 | Loss: 2.0523273944854736, Learning Rate: 2.9081491447868757e-05)
+Epoch... (1/30 | Step: 2130 | Loss: 2.0692148208618164, Learning Rate: 2.9077154977130704e-05)
+Epoch... (1/30 | Step: 2140 | Loss: 2.0720198154449463, Learning Rate: 2.9072820325382054e-05)
+Epoch... (1/30 | Step: 2150 | Loss: 2.018003463745117, Learning Rate: 2.9068485673633404e-05)
+Epoch... (1/30 | Step: 2160 | Loss: 2.0908870697021484, Learning Rate: 2.9064151021884754e-05)
+Epoch... (1/30 | Step: 2170 | Loss: 1.9835797548294067, Learning Rate: 2.9059816370136105e-05)
+Epoch... (1/30 | Step: 2180 | Loss: 2.033381462097168, Learning Rate: 2.9055481718387455e-05)
+Epoch... (1/30 | Step: 2190 | Loss: 2.0725207328796387, Learning Rate: 2.905114888562821e-05)
+Epoch... (1/30 | Step: 2200 | Loss: 2.0173754692077637, Learning Rate: 2.904681423387956e-05)
+Epoch... (1/30 | Step: 2210 | Loss: 2.1233925819396973, Learning Rate: 2.904247958213091e-05)
+Epoch... (1/30 | Step: 2220 | Loss: 2.0552401542663574, Learning Rate: 2.903814493038226e-05)
+Epoch... (1/30 | Step: 2230 | Loss: 2.046525001525879, Learning Rate: 2.9033808459644206e-05)
+Epoch... (1/30 | Step: 2240 | Loss: 2.064979076385498, Learning Rate: 2.9029473807895556e-05)
+Epoch... (1/30 | Step: 2250 | Loss: 2.0798213481903076, Learning Rate: 2.9025139156146906e-05)
+Epoch... (1/30 | Step: 2260 | Loss: 2.0388433933258057, Learning Rate: 2.9020804504398257e-05)
+Epoch... (1/30 | Step: 2270 | Loss: 2.0377979278564453, Learning Rate: 2.901647167163901e-05)
+Epoch... (1/30 | Step: 2280 | Loss: 2.0889925956726074, Learning Rate: 2.901213701989036e-05)
+Epoch... (1/30 | Step: 2290 | Loss: 2.05222749710083, Learning Rate: 2.900780236814171e-05)
+Epoch... (1/30 | Step: 2300 | Loss: 2.033143997192383, Learning Rate: 2.900346771639306e-05)
+Epoch... (1/30 | Step: 2307 | Loss: 2.164933443069458, Learning Rate: 2.9000433642067946e-05)
+Epoch... (1/30 | Step: 2307 | Eval Loss: 2.0284838676452637 | Eval rouge1: 40.5299 | Eval rouge2: 15.057 | Eval rougeL: 36.9003 | Eval rougeLsum: 36.8978 | Eval gen_len: 10.9925 |)