Saving weights and logs of epoch 1 - step 1800

ckpt_epoch_1_step_1800/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_1800/flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:490604c6d7dc47a49da3af020942b703f4c19999bb638959ed1dc922217101a1
+size 956799284

ckpt_epoch_1_step_1800/special_tokens_map.json

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

ckpt_epoch_1_step_1800/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 sha256:5059fd33bdcf121e2b03cce6b6fd061897ef62b373ea63b626874f096ed8b33d
-size 662725
+oid sha256:326ee83ea915748ed2b1582fb2065fbd468a2655dd06cb763e3e27c1402e8552
+size 927562

report.txt

@@ -158,3 +158,35 @@ Epoch... (1/30 | Step: 1490 | Loss: 2.1194841861724854, Learning Rate: 2.9354572
 Epoch... (1/30 | Step: 1500 | Loss: 2.0982208251953125, Learning Rate: 2.935023803729564e-05)
 Epoch... (1/30 | Step: 1500 | Loss: 2.0982208251953125, Learning Rate: 2.935023803729564e-05)
 Epoch... (1/30 | Step: 1500 | Eval Loss: 2.087283134460449 | Eval rouge1: 39.7247 | Eval rouge2: 14.3773 | Eval rougeL: 36.2126 | Eval rougeLsum: 36.2124 | Eval gen_len: 10.922 |)
+Epoch... (1/30 | Step: 1510 | Loss: 2.0628573894500732, Learning Rate: 2.934590338554699e-05)
+Epoch... (1/30 | Step: 1520 | Loss: 2.0424842834472656, Learning Rate: 2.934156873379834e-05)
+Epoch... (1/30 | Step: 1530 | Loss: 2.157275676727295, Learning Rate: 2.933723408204969e-05)
+Epoch... (1/30 | Step: 1540 | Loss: 2.1352427005767822, Learning Rate: 2.933289943030104e-05)
+Epoch... (1/30 | Step: 1550 | Loss: 2.1653575897216797, Learning Rate: 2.9328562959562987e-05)
+Epoch... (1/30 | Step: 1560 | Loss: 2.0672290325164795, Learning Rate: 2.9324228307814337e-05)
+Epoch... (1/30 | Step: 1570 | Loss: 2.097109794616699, Learning Rate: 2.931989547505509e-05)
+Epoch... (1/30 | Step: 1580 | Loss: 2.087357997894287, Learning Rate: 2.931556082330644e-05)
+Epoch... (1/30 | Step: 1590 | Loss: 2.1381149291992188, Learning Rate: 2.931122617155779e-05)
+Epoch... (1/30 | Step: 1600 | Loss: 2.1855034828186035, Learning Rate: 2.9306891519809142e-05)
+Epoch... (1/30 | Step: 1610 | Loss: 2.183502674102783, Learning Rate: 2.9302556868060492e-05)
+Epoch... (1/30 | Step: 1620 | Loss: 2.1278882026672363, Learning Rate: 2.9298222216311842e-05)
+Epoch... (1/30 | Step: 1630 | Loss: 2.086331605911255, Learning Rate: 2.9293887564563192e-05)
+Epoch... (1/30 | Step: 1640 | Loss: 2.0485429763793945, Learning Rate: 2.9289552912814543e-05)
+Epoch... (1/30 | Step: 1650 | Loss: 2.0960192680358887, Learning Rate: 2.9285218261065893e-05)
+Epoch... (1/30 | Step: 1660 | Loss: 2.078531265258789, Learning Rate: 2.9280883609317243e-05)
+Epoch... (1/30 | Step: 1670 | Loss: 2.1528992652893066, Learning Rate: 2.9276548957568593e-05)
+Epoch... (1/30 | Step: 1680 | Loss: 2.044875144958496, Learning Rate: 2.9272214305819944e-05)
+Epoch... (1/30 | Step: 1690 | Loss: 2.1002728939056396, Learning Rate: 2.9267879654071294e-05)
+Epoch... (1/30 | Step: 1700 | Loss: 2.0666818618774414, Learning Rate: 2.9263545002322644e-05)
+Epoch... (1/30 | Step: 1710 | Loss: 2.076720714569092, Learning Rate: 2.9259210350573994e-05)
+Epoch... (1/30 | Step: 1720 | Loss: 2.0573716163635254, Learning Rate: 2.9254875698825344e-05)
+Epoch... (1/30 | Step: 1730 | Loss: 2.0897603034973145, Learning Rate: 2.9250541047076695e-05)
+Epoch... (1/30 | Step: 1740 | Loss: 2.141058921813965, Learning Rate: 2.9246206395328045e-05)
+Epoch... (1/30 | Step: 1750 | Loss: 2.1023364067077637, Learning Rate: 2.9241871743579395e-05)
+Epoch... (1/30 | Step: 1760 | Loss: 2.1418118476867676, Learning Rate: 2.9237537091830745e-05)
+Epoch... (1/30 | Step: 1770 | Loss: 2.246041774749756, Learning Rate: 2.9233202440082096e-05)
+Epoch... (1/30 | Step: 1780 | Loss: 2.1305742263793945, Learning Rate: 2.9228867788333446e-05)
+Epoch... (1/30 | Step: 1790 | Loss: 2.1510705947875977, Learning Rate: 2.9224533136584796e-05)
+Epoch... (1/30 | Step: 1800 | Loss: 2.2788705825805664, Learning Rate: 2.9220198484836146e-05)
+Epoch... (1/30 | Step: 1800 | Loss: 2.2788705825805664, Learning Rate: 2.9220198484836146e-05)
+Epoch... (1/30 | Step: 1800 | Eval Loss: 2.0597662925720215 | Eval rouge1: 40.5653 | Eval rouge2: 15.0792 | Eval rougeL: 36.9261 | Eval rougeLsum: 36.9178 | Eval gen_len: 10.8504 |)