Saving weights and logs of epoch 2 - step 3300

ckpt_epoch_2_step_3300/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_3300/flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9625b16b6fa5d76a48cbd78b299293299cb7700b2e3edc1ad7c6d7676458451
+size 956799284

ckpt_epoch_2_step_3300/special_tokens_map.json

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

ckpt_epoch_2_step_3300/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 sha256:34d511f9ba292d071293ec42b1b0234544a3433795b853f55a2f74b28ba9af32
-size 1750651
+oid sha256:7836f3dff26370c0f8c5f4ddb03616e71cf76c51a9fb2fd9f34a86d57e219dc8
+size 1897113

report.txt

@@ -320,3 +320,35 @@ Epoch... (2/30 | Step: 2990 | Loss: 2.039159059524536, Learning Rate: 2.87043785
 Epoch... (2/30 | Step: 3000 | Loss: 1.9609485864639282, Learning Rate: 2.870004391297698e-05)
 Epoch... (2/30 | Step: 3000 | Loss: 1.9609485864639282, Learning Rate: 2.870004391297698e-05)
 Epoch... (2/30 | Step: 3000 | Eval Loss: 1.9941604137420654 | Eval rouge1: 40.6226 | Eval rouge2: 15.1062 | Eval rougeL: 36.9129 | Eval rougeLsum: 36.9145 | Eval gen_len: 11.0414 |)
+Epoch... (2/30 | Step: 3010 | Loss: 1.9202957153320312, Learning Rate: 2.8695707442238927e-05)
+Epoch... (2/30 | Step: 3020 | Loss: 1.959960699081421, Learning Rate: 2.8691372790490277e-05)
+Epoch... (2/30 | Step: 3030 | Loss: 2.0083134174346924, Learning Rate: 2.8687038138741627e-05)
+Epoch... (2/30 | Step: 3040 | Loss: 1.9896552562713623, Learning Rate: 2.8682703486992978e-05)
+Epoch... (2/30 | Step: 3050 | Loss: 2.0054593086242676, Learning Rate: 2.8678368835244328e-05)
+Epoch... (2/30 | Step: 3060 | Loss: 1.9596562385559082, Learning Rate: 2.8674034183495678e-05)
+Epoch... (2/30 | Step: 3070 | Loss: 1.9955945014953613, Learning Rate: 2.8669701350736432e-05)
+Epoch... (2/30 | Step: 3080 | Loss: 1.9095125198364258, Learning Rate: 2.8665366698987782e-05)
+Epoch... (2/30 | Step: 3090 | Loss: 1.9675850868225098, Learning Rate: 2.8661032047239132e-05)
+Epoch... (2/30 | Step: 3100 | Loss: 1.9429959058761597, Learning Rate: 2.865669557650108e-05)
+Epoch... (2/30 | Step: 3110 | Loss: 1.9753589630126953, Learning Rate: 2.865236092475243e-05)
+Epoch... (2/30 | Step: 3120 | Loss: 1.9604036808013916, Learning Rate: 2.864802627300378e-05)
+Epoch... (2/30 | Step: 3130 | Loss: 1.9368562698364258, Learning Rate: 2.864369162125513e-05)
+Epoch... (2/30 | Step: 3140 | Loss: 1.9978103637695312, Learning Rate: 2.863935696950648e-05)
+Epoch... (2/30 | Step: 3150 | Loss: 2.0798728466033936, Learning Rate: 2.863502231775783e-05)
+Epoch... (2/30 | Step: 3160 | Loss: 1.9111906290054321, Learning Rate: 2.8630689484998584e-05)
+Epoch... (2/30 | Step: 3170 | Loss: 2.041853427886963, Learning Rate: 2.8626354833249934e-05)
+Epoch... (2/30 | Step: 3180 | Loss: 2.0397024154663086, Learning Rate: 2.8622020181501284e-05)
+Epoch... (2/30 | Step: 3190 | Loss: 1.8796460628509521, Learning Rate: 2.8617685529752634e-05)
+Epoch... (2/30 | Step: 3200 | Loss: 2.0037131309509277, Learning Rate: 2.8613350878003985e-05)
+Epoch... (2/30 | Step: 3210 | Loss: 1.9178547859191895, Learning Rate: 2.860901440726593e-05)
+Epoch... (2/30 | Step: 3220 | Loss: 1.958061933517456, Learning Rate: 2.860467975551728e-05)
+Epoch... (2/30 | Step: 3230 | Loss: 1.9921672344207764, Learning Rate: 2.8600345103768632e-05)
+Epoch... (2/30 | Step: 3240 | Loss: 1.9145488739013672, Learning Rate: 2.8596010452019982e-05)
+Epoch... (2/30 | Step: 3250 | Loss: 1.974982738494873, Learning Rate: 2.8591677619260736e-05)
+Epoch... (2/30 | Step: 3260 | Loss: 1.9515241384506226, Learning Rate: 2.8587342967512086e-05)
+Epoch... (2/30 | Step: 3270 | Loss: 1.94496488571167, Learning Rate: 2.8583008315763436e-05)
+Epoch... (2/30 | Step: 3280 | Loss: 1.9740091562271118, Learning Rate: 2.8578673664014786e-05)
+Epoch... (2/30 | Step: 3290 | Loss: 2.032979726791382, Learning Rate: 2.8574339012266137e-05)
+Epoch... (2/30 | Step: 3300 | Loss: 1.9422719478607178, Learning Rate: 2.8570002541528083e-05)
+Epoch... (2/30 | Step: 3300 | Loss: 1.9422719478607178, Learning Rate: 2.8570002541528083e-05)
+Epoch... (2/30 | Step: 3300 | Eval Loss: 1.9856388568878174 | Eval rouge1: 40.961 | Eval rouge2: 15.427 | Eval rougeL: 37.1983 | Eval rougeLsum: 37.1916 | Eval gen_len: 10.9743 |)