Saving weights and logs of epoch 2 - step 4500

ckpt_epoch_2_step_4500/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_4500/flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:026e1f3dc06be0249c2308d21b9a4e8d3b0b874d59152d93b1506e6a45a317ef
+size 956799284

ckpt_epoch_2_step_4500/special_tokens_map.json

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

ckpt_epoch_2_step_4500/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 sha256:3dd85c5c40a998050e0097c1cdb924a1c39dac446c23c3e110ff1ee112228b04
-size 2601099
+oid sha256:7dcef2c1cf7105edc9d303fb6948c27bf83038daeab2f1420ea0449b4b80f390
+size 2923961

report.txt

@@ -448,3 +448,35 @@ Epoch... (2/30 | Step: 4190 | Loss: 1.893964171409607, Learning Rate: 2.81842203
 Epoch... (2/30 | Step: 4200 | Loss: 1.8666478395462036, Learning Rate: 2.8179885703139007e-05)
 Epoch... (2/30 | Step: 4200 | Loss: 1.8666478395462036, Learning Rate: 2.8179885703139007e-05)
 Epoch... (2/30 | Step: 4200 | Eval Loss: 1.9555346965789795 | Eval rouge1: 40.9762 | Eval rouge2: 15.5911 | Eval rougeL: 37.3749 | Eval rougeLsum: 37.3706 | Eval gen_len: 10.9797 |)
+Epoch... (2/30 | Step: 4210 | Loss: 1.9187740087509155, Learning Rate: 2.8175551051390357e-05)
+Epoch... (2/30 | Step: 4220 | Loss: 1.9928175210952759, Learning Rate: 2.817121821863111e-05)
+Epoch... (2/30 | Step: 4230 | Loss: 1.9062347412109375, Learning Rate: 2.816688356688246e-05)
+Epoch... (2/30 | Step: 4240 | Loss: 1.9475587606430054, Learning Rate: 2.816254891513381e-05)
+Epoch... (2/30 | Step: 4250 | Loss: 1.9387705326080322, Learning Rate: 2.8158214263385162e-05)
+Epoch... (2/30 | Step: 4260 | Loss: 1.930619239807129, Learning Rate: 2.8153879611636512e-05)
+Epoch... (2/30 | Step: 4270 | Loss: 1.9640536308288574, Learning Rate: 2.814954314089846e-05)
+Epoch... (2/30 | Step: 4280 | Loss: 1.9580998420715332, Learning Rate: 2.814520848914981e-05)
+Epoch... (2/30 | Step: 4290 | Loss: 1.9430346488952637, Learning Rate: 2.814087383740116e-05)
+Epoch... (2/30 | Step: 4300 | Loss: 1.9957571029663086, Learning Rate: 2.813653918565251e-05)
+Epoch... (2/30 | Step: 4310 | Loss: 1.9378894567489624, Learning Rate: 2.8132206352893263e-05)
+Epoch... (2/30 | Step: 4320 | Loss: 1.9086257219314575, Learning Rate: 2.8127871701144613e-05)
+Epoch... (2/30 | Step: 4330 | Loss: 1.9071044921875, Learning Rate: 2.8123537049395964e-05)
+Epoch... (2/30 | Step: 4340 | Loss: 1.9538824558258057, Learning Rate: 2.8119202397647314e-05)
+Epoch... (2/30 | Step: 4350 | Loss: 1.8882595300674438, Learning Rate: 2.8114867745898664e-05)
+Epoch... (2/30 | Step: 4360 | Loss: 1.939955472946167, Learning Rate: 2.8110533094150014e-05)
+Epoch... (2/30 | Step: 4370 | Loss: 1.9267652034759521, Learning Rate: 2.810619662341196e-05)
+Epoch... (2/30 | Step: 4380 | Loss: 1.8608458042144775, Learning Rate: 2.810186197166331e-05)
+Epoch... (2/30 | Step: 4390 | Loss: 1.9454424381256104, Learning Rate: 2.809752731991466e-05)
+Epoch... (2/30 | Step: 4400 | Loss: 1.9094369411468506, Learning Rate: 2.8093194487155415e-05)
+Epoch... (2/30 | Step: 4410 | Loss: 1.8965256214141846, Learning Rate: 2.8088859835406765e-05)
+Epoch... (2/30 | Step: 4420 | Loss: 1.980330467224121, Learning Rate: 2.8084525183658116e-05)
+Epoch... (2/30 | Step: 4430 | Loss: 1.9047348499298096, Learning Rate: 2.8080190531909466e-05)
+Epoch... (2/30 | Step: 4440 | Loss: 1.856551170349121, Learning Rate: 2.8075855880160816e-05)
+Epoch... (2/30 | Step: 4450 | Loss: 1.9115313291549683, Learning Rate: 2.8071521228412166e-05)
+Epoch... (2/30 | Step: 4460 | Loss: 1.8422142267227173, Learning Rate: 2.8067184757674113e-05)
+Epoch... (2/30 | Step: 4470 | Loss: 1.9501553773880005, Learning Rate: 2.8062850105925463e-05)
+Epoch... (2/30 | Step: 4480 | Loss: 1.99320650100708, Learning Rate: 2.8058515454176813e-05)
+Epoch... (2/30 | Step: 4490 | Loss: 1.8857262134552002, Learning Rate: 2.8054182621417567e-05)
+Epoch... (2/30 | Step: 4500 | Loss: 1.8706979751586914, Learning Rate: 2.8049847969668917e-05)
+Epoch... (2/30 | Step: 4500 | Loss: 1.8706979751586914, Learning Rate: 2.8049847969668917e-05)
+Epoch... (2/30 | Step: 4500 | Eval Loss: 1.9466681480407715 | Eval rouge1: 40.7165 | Eval rouge2: 15.3635 | Eval rougeL: 37.0299 | Eval rougeLsum: 37.031 | Eval gen_len: 11.2565 |)