Saving weights and logs of epoch 2 - step 2400

ckpt_epoch_2_step_2400/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_2_step_2400/flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4feb497b73eb7978ca6794711496428734919819ebc09184e422df0fb49ccfce
+size 956799284

ckpt_epoch_2_step_2400/special_tokens_map.json

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

ckpt_epoch_2_step_2400/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:ff4efbdcba1dbd6214d2af848719e66b6c8b1d25362fc6704362fb5bf660d749
-size 1575865
+oid sha256:3f0ee1dffb1fc6d1b8f2c3b81442f8965e1ee6fd6a641dccba47b50fcd601d6a
+size 1590027

report.txt

@@ -244,3 +244,15 @@ Epoch... (1/30 | Step: 2290 | Loss: 2.05222749710083, Learning Rate: 2.900780236
 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 |)
+Epoch... (2/30 | Step: 2310 | Loss: 1.9816746711730957, Learning Rate: 2.899913306464441e-05)
+Epoch... (2/30 | Step: 2320 | Loss: 1.9637086391448975, Learning Rate: 2.8994796593906358e-05)
+Epoch... (2/30 | Step: 2330 | Loss: 1.9946067333221436, Learning Rate: 2.8990461942157708e-05)
+Epoch... (2/30 | Step: 2340 | Loss: 1.9579181671142578, Learning Rate: 2.898612729040906e-05)
+Epoch... (2/30 | Step: 2350 | Loss: 2.0120954513549805, Learning Rate: 2.898179263866041e-05)
+Epoch... (2/30 | Step: 2360 | Loss: 1.933640480041504, Learning Rate: 2.8977459805901162e-05)
+Epoch... (2/30 | Step: 2370 | Loss: 2.001372814178467, Learning Rate: 2.8973125154152513e-05)
+Epoch... (2/30 | Step: 2380 | Loss: 1.9272139072418213, Learning Rate: 2.8968790502403863e-05)
+Epoch... (2/30 | Step: 2390 | Loss: 2.0162031650543213, Learning Rate: 2.8964455850655213e-05)
+Epoch... (2/30 | Step: 2400 | Loss: 1.9704089164733887, Learning Rate: 2.8960121198906563e-05)
+Epoch... (2/30 | Step: 2400 | Loss: 1.9704089164733887, Learning Rate: 2.8960121198906563e-05)
+Epoch... (2/30 | Step: 2400 | Eval Loss: 2.024594306945801 | Eval rouge1: 40.4764 | Eval rouge2: 14.9051 | Eval rougeL: 36.8785 | Eval rougeLsum: 36.8769 | Eval gen_len: 10.8998 |)