Saving weights and logs of epoch 1 - step 1500

ckpt_epoch_1_step_1500/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_1500/flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6205f82b78ca8b64ccdbeee07d61c460150faa8facd4bebaba1397a13f2fec4
+size 956799284

ckpt_epoch_1_step_1500/special_tokens_map.json

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

ckpt_epoch_1_step_1500/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 sha256:1f6609a739499790b8ecbe0c08614464524e23dda62c2ed6c436c21973cfe6e9
-size 441988
+oid sha256:5059fd33bdcf121e2b03cce6b6fd061897ef62b373ea63b626874f096ed8b33d
+size 662725

report.txt

@@ -126,3 +126,35 @@ Epoch... (1/30 | Step: 1190 | Loss: 2.19675350189209, Learning Rate: 2.948461042
 Epoch... (1/30 | Step: 1200 | Loss: 2.069185972213745, Learning Rate: 2.948027577076573e-05)
 Epoch... (1/30 | Step: 1200 | Loss: 2.069185972213745, Learning Rate: 2.948027577076573e-05)
 Epoch... (1/30 | Step: 1200 | Eval Loss: 2.118244171142578 | Eval rouge1: 39.626 | Eval rouge2: 14.2226 | Eval rougeL: 36.0901 | Eval rougeLsum: 36.0902 | Eval gen_len: 10.9209 |)
+Epoch... (1/30 | Step: 1210 | Loss: 2.143256664276123, Learning Rate: 2.9475942938006483e-05)
+Epoch... (1/30 | Step: 1220 | Loss: 2.1436400413513184, Learning Rate: 2.9471608286257833e-05)
+Epoch... (1/30 | Step: 1230 | Loss: 2.2154154777526855, Learning Rate: 2.9467273634509183e-05)
+Epoch... (1/30 | Step: 1240 | Loss: 2.1441659927368164, Learning Rate: 2.9462938982760534e-05)
+Epoch... (1/30 | Step: 1250 | Loss: 2.174199104309082, Learning Rate: 2.9458604331011884e-05)
+Epoch... (1/30 | Step: 1260 | Loss: 2.1268279552459717, Learning Rate: 2.945426786027383e-05)
+Epoch... (1/30 | Step: 1270 | Loss: 2.126941204071045, Learning Rate: 2.944993320852518e-05)
+Epoch... (1/30 | Step: 1280 | Loss: 2.119166612625122, Learning Rate: 2.944559855677653e-05)
+Epoch... (1/30 | Step: 1290 | Loss: 2.2846920490264893, Learning Rate: 2.944126390502788e-05)
+Epoch... (1/30 | Step: 1300 | Loss: 2.1685166358947754, Learning Rate: 2.9436931072268635e-05)
+Epoch... (1/30 | Step: 1310 | Loss: 2.151987314224243, Learning Rate: 2.9432596420519985e-05)
+Epoch... (1/30 | Step: 1320 | Loss: 2.103717565536499, Learning Rate: 2.9428261768771335e-05)
+Epoch... (1/30 | Step: 1330 | Loss: 2.155966281890869, Learning Rate: 2.9423927117022686e-05)
+Epoch... (1/30 | Step: 1340 | Loss: 2.1677801609039307, Learning Rate: 2.9419592465274036e-05)
+Epoch... (1/30 | Step: 1350 | Loss: 2.143979549407959, Learning Rate: 2.9415255994535983e-05)
+Epoch... (1/30 | Step: 1360 | Loss: 2.229569911956787, Learning Rate: 2.9410921342787333e-05)
+Epoch... (1/30 | Step: 1370 | Loss: 2.0859322547912598, Learning Rate: 2.9406586691038683e-05)
+Epoch... (1/30 | Step: 1380 | Loss: 2.2380738258361816, Learning Rate: 2.9402252039290033e-05)
+Epoch... (1/30 | Step: 1390 | Loss: 2.10669207572937, Learning Rate: 2.9397919206530787e-05)
+Epoch... (1/30 | Step: 1400 | Loss: 2.1286675930023193, Learning Rate: 2.9393584554782137e-05)
+Epoch... (1/30 | Step: 1410 | Loss: 2.140237331390381, Learning Rate: 2.9389249903033487e-05)
+Epoch... (1/30 | Step: 1420 | Loss: 2.081178665161133, Learning Rate: 2.9384915251284838e-05)
+Epoch... (1/30 | Step: 1430 | Loss: 2.0578155517578125, Learning Rate: 2.9380580599536188e-05)
+Epoch... (1/30 | Step: 1440 | Loss: 2.082831859588623, Learning Rate: 2.9376245947787538e-05)
+Epoch... (1/30 | Step: 1450 | Loss: 2.1357812881469727, Learning Rate: 2.937191129603889e-05)
+Epoch... (1/30 | Step: 1460 | Loss: 2.164750576019287, Learning Rate: 2.9367574825300835e-05)
+Epoch... (1/30 | Step: 1470 | Loss: 2.0534393787384033, Learning Rate: 2.9363240173552185e-05)
+Epoch... (1/30 | Step: 1480 | Loss: 2.1811447143554688, Learning Rate: 2.935890734079294e-05)
+Epoch... (1/30 | Step: 1490 | Loss: 2.1194841861724854, Learning Rate: 2.935457268904429e-05)
+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 |)