Saving weights and logs of epoch 3 - step 5400

ckpt_epoch_3_step_5400/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_5400/flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:660244ef7e6d396e5c786e7b7c5dca3178f78680f8c69a70319f581a17974a39
+size 956799284

ckpt_epoch_3_step_5400/special_tokens_map.json

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

ckpt_epoch_3_step_5400/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:d4d4abc3763d83debcc6e98d5ee056178a208d1dc41bbbdbe8305e3adec2e176
-size 3363347
+oid sha256:2fcc96e6a18db97b02f87c56f17652b31c0ebb268663955bf39d2920c116f332
+size 3479380

report.txt

@@ -546,3 +546,35 @@ Epoch... (3/30 | Step: 5090 | Loss: 1.8129793405532837, Learning Rate: 2.7794103
 Epoch... (3/30 | Step: 5100 | Loss: 1.9016380310058594, Learning Rate: 2.778976886474993e-05)
 Epoch... (3/30 | Step: 5100 | Loss: 1.9016380310058594, Learning Rate: 2.778976886474993e-05)
 Epoch... (3/30 | Step: 5100 | Eval Loss: 1.9427725076675415 | Eval rouge1: 41.2198 | Eval rouge2: 15.6318 | Eval rougeL: 37.4398 | Eval rougeLsum: 37.4436 | Eval gen_len: 11.1195 |)
+Epoch... (3/30 | Step: 5110 | Loss: 1.8517467975616455, Learning Rate: 2.7785436031990685e-05)
+Epoch... (3/30 | Step: 5120 | Loss: 1.8552989959716797, Learning Rate: 2.7781101380242035e-05)
+Epoch... (3/30 | Step: 5130 | Loss: 1.8470796346664429, Learning Rate: 2.7776766728493385e-05)
+Epoch... (3/30 | Step: 5140 | Loss: 1.9408626556396484, Learning Rate: 2.7772432076744735e-05)
+Epoch... (3/30 | Step: 5150 | Loss: 1.9104987382888794, Learning Rate: 2.7768095606006682e-05)
+Epoch... (3/30 | Step: 5160 | Loss: 1.8002305030822754, Learning Rate: 2.7763760954258032e-05)
+Epoch... (3/30 | Step: 5170 | Loss: 1.7606427669525146, Learning Rate: 2.7759426302509382e-05)
+Epoch... (3/30 | Step: 5180 | Loss: 1.8362019062042236, Learning Rate: 2.7755091650760733e-05)
+Epoch... (3/30 | Step: 5190 | Loss: 1.8140841722488403, Learning Rate: 2.7750756999012083e-05)
+Epoch... (3/30 | Step: 5200 | Loss: 1.8190215826034546, Learning Rate: 2.7746424166252837e-05)
+Epoch... (3/30 | Step: 5210 | Loss: 1.8725632429122925, Learning Rate: 2.7742089514504187e-05)
+Epoch... (3/30 | Step: 5220 | Loss: 1.871530532836914, Learning Rate: 2.7737754862755537e-05)
+Epoch... (3/30 | Step: 5230 | Loss: 1.8738446235656738, Learning Rate: 2.7733420211006887e-05)
+Epoch... (3/30 | Step: 5240 | Loss: 1.726067304611206, Learning Rate: 2.7729083740268834e-05)
+Epoch... (3/30 | Step: 5250 | Loss: 1.7526288032531738, Learning Rate: 2.7724749088520184e-05)
+Epoch... (3/30 | Step: 5260 | Loss: 1.7957985401153564, Learning Rate: 2.7720414436771534e-05)
+Epoch... (3/30 | Step: 5270 | Loss: 1.8102589845657349, Learning Rate: 2.7716079785022885e-05)
+Epoch... (3/30 | Step: 5280 | Loss: 1.9033677577972412, Learning Rate: 2.7711745133274235e-05)
+Epoch... (3/30 | Step: 5290 | Loss: 1.87894868850708, Learning Rate: 2.770741230051499e-05)
+Epoch... (3/30 | Step: 5300 | Loss: 1.8765783309936523, Learning Rate: 2.770307764876634e-05)
+Epoch... (3/30 | Step: 5310 | Loss: 1.9336323738098145, Learning Rate: 2.769874299701769e-05)
+Epoch... (3/30 | Step: 5320 | Loss: 1.883346676826477, Learning Rate: 2.769440834526904e-05)
+Epoch... (3/30 | Step: 5330 | Loss: 1.8765766620635986, Learning Rate: 2.769007369352039e-05)
+Epoch... (3/30 | Step: 5340 | Loss: 1.8111586570739746, Learning Rate: 2.768573904177174e-05)
+Epoch... (3/30 | Step: 5350 | Loss: 1.8051023483276367, Learning Rate: 2.7681402571033686e-05)
+Epoch... (3/30 | Step: 5360 | Loss: 1.7918339967727661, Learning Rate: 2.7677067919285037e-05)
+Epoch... (3/30 | Step: 5370 | Loss: 1.8722422122955322, Learning Rate: 2.7672733267536387e-05)
+Epoch... (3/30 | Step: 5380 | Loss: 1.848788857460022, Learning Rate: 2.766840043477714e-05)
+Epoch... (3/30 | Step: 5390 | Loss: 1.830802321434021, Learning Rate: 2.766406578302849e-05)
+Epoch... (3/30 | Step: 5400 | Loss: 1.8050287961959839, Learning Rate: 2.765973113127984e-05)
+Epoch... (3/30 | Step: 5400 | Loss: 1.8050287961959839, Learning Rate: 2.765973113127984e-05)
+Epoch... (3/30 | Step: 5400 | Eval Loss: 1.9341686964035034 | Eval rouge1: 40.9793 | Eval rouge2: 15.5931 | Eval rougeL: 37.2943 | Eval rougeLsum: 37.2958 | Eval gen_len: 11.0549 |)