Saving weights and logs of epoch 1 - step 300

ckpt_epoch_1_step_300/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_300/flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2048662323313d2a6f0c9fbe5ea7b40a6810b771811a64b11cd00d36f050642
+size 956799284

ckpt_epoch_1_step_300/special_tokens_map.json

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

ckpt_epoch_1_step_300/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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f49258f80d1097f4612202635e31b54f675d42a84c46c211f742f988f6405aa4
+size 44377

report.txt

@@ -0,0 +1,32 @@
+Epoch... (1/30 | Step: 10 | Loss: 3.4405534267425537, Learning Rate: 2.999609750986565e-05)
+Epoch... (1/30 | Step: 20 | Loss: 3.218325614929199, Learning Rate: 2.9991762858117e-05)
+Epoch... (1/30 | Step: 30 | Loss: 3.1018149852752686, Learning Rate: 2.998742820636835e-05)
+Epoch... (1/30 | Step: 40 | Loss: 3.022020101547241, Learning Rate: 2.99830935546197e-05)
+Epoch... (1/30 | Step: 50 | Loss: 2.981201648712158, Learning Rate: 2.997875890287105e-05)
+Epoch... (1/30 | Step: 60 | Loss: 2.8424253463745117, Learning Rate: 2.9974426070111804e-05)
+Epoch... (1/30 | Step: 70 | Loss: 2.907778263092041, Learning Rate: 2.9970091418363154e-05)
+Epoch... (1/30 | Step: 80 | Loss: 2.7866015434265137, Learning Rate: 2.9965756766614504e-05)
+Epoch... (1/30 | Step: 90 | Loss: 2.8242785930633545, Learning Rate: 2.996142029587645e-05)
+Epoch... (1/30 | Step: 100 | Loss: 2.706552028656006, Learning Rate: 2.99570856441278e-05)
+Epoch... (1/30 | Step: 110 | Loss: 2.611888885498047, Learning Rate: 2.995275099237915e-05)
+Epoch... (1/30 | Step: 120 | Loss: 2.595040798187256, Learning Rate: 2.99484163406305e-05)
+Epoch... (1/30 | Step: 130 | Loss: 2.6346092224121094, Learning Rate: 2.9944081688881852e-05)
+Epoch... (1/30 | Step: 140 | Loss: 2.608229160308838, Learning Rate: 2.9939747037133202e-05)
+Epoch... (1/30 | Step: 150 | Loss: 2.628932476043701, Learning Rate: 2.9935414204373956e-05)
+Epoch... (1/30 | Step: 160 | Loss: 2.4869046211242676, Learning Rate: 2.9931079552625306e-05)
+Epoch... (1/30 | Step: 170 | Loss: 2.5518672466278076, Learning Rate: 2.9926744900876656e-05)
+Epoch... (1/30 | Step: 180 | Loss: 2.475501298904419, Learning Rate: 2.9922410249128006e-05)
+Epoch... (1/30 | Step: 190 | Loss: 2.7231974601745605, Learning Rate: 2.9918073778389953e-05)
+Epoch... (1/30 | Step: 200 | Loss: 2.500187873840332, Learning Rate: 2.9913739126641303e-05)
+Epoch... (1/30 | Step: 210 | Loss: 2.5470097064971924, Learning Rate: 2.9909404474892654e-05)
+Epoch... (1/30 | Step: 220 | Loss: 2.3819117546081543, Learning Rate: 2.9905069823144004e-05)
+Epoch... (1/30 | Step: 230 | Loss: 2.5723557472229004, Learning Rate: 2.9900735171395354e-05)
+Epoch... (1/30 | Step: 240 | Loss: 2.440537929534912, Learning Rate: 2.9896402338636108e-05)
+Epoch... (1/30 | Step: 250 | Loss: 2.559695243835449, Learning Rate: 2.9892067686887458e-05)
+Epoch... (1/30 | Step: 260 | Loss: 2.5182833671569824, Learning Rate: 2.9887733035138808e-05)
+Epoch... (1/30 | Step: 270 | Loss: 2.405858039855957, Learning Rate: 2.988339838339016e-05)
+Epoch... (1/30 | Step: 280 | Loss: 2.4234917163848877, Learning Rate: 2.987906373164151e-05)
+Epoch... (1/30 | Step: 290 | Loss: 2.36462140083313, Learning Rate: 2.9874727260903455e-05)
+Epoch... (1/30 | Step: 300 | Loss: 2.4654769897460938, Learning Rate: 2.9870392609154806e-05)
+Epoch... (1/30 | Step: 300 | Loss: 2.4654769897460938, Learning Rate: 2.9870392609154806e-05)
+Epoch... (1/30 | Step: 300 | Eval Loss: 2.3369832038879395 | Eval rouge1: 36.6481 | Eval rouge2: 12.0172 | Eval rougeL: 33.4031 | Eval rougeLsum: 33.4031 | Eval gen_len: 10.6758 |)