Saving weights and logs of epoch 1 - step 2100

ckpt_epoch_1_step_2100/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_2100/flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6ecc1d4c2b09a179d4daf54b604729dd2c27993d65762d6cbb4d042aa191df7
+size 956799284

ckpt_epoch_1_step_2100/special_tokens_map.json

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

ckpt_epoch_1_step_2100/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 sha256:326ee83ea915748ed2b1582fb2065fbd468a2655dd06cb763e3e27c1402e8552
-size 927562
+oid sha256:9af925175aac37fd8a08fcb838c389c9f9afd0453bacf7a4475e8cbf8e0126ad
+size 1236499

report.txt

@@ -190,3 +190,35 @@ Epoch... (1/30 | Step: 1790 | Loss: 2.1510705947875977, Learning Rate: 2.9224533
 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 |)
+Epoch... (1/30 | Step: 1810 | Loss: 2.1530094146728516, Learning Rate: 2.9215863833087496e-05)
+Epoch... (1/30 | Step: 1820 | Loss: 2.216090679168701, Learning Rate: 2.9211529181338847e-05)
+Epoch... (1/30 | Step: 1830 | Loss: 2.138352155685425, Learning Rate: 2.92071963485796e-05)
+Epoch... (1/30 | Step: 1840 | Loss: 2.0977377891540527, Learning Rate: 2.9202859877841547e-05)
+Epoch... (1/30 | Step: 1850 | Loss: 2.1130166053771973, Learning Rate: 2.9198525226092897e-05)
+Epoch... (1/30 | Step: 1860 | Loss: 1.9936583042144775, Learning Rate: 2.9194190574344248e-05)
+Epoch... (1/30 | Step: 1870 | Loss: 2.0906026363372803, Learning Rate: 2.9189855922595598e-05)
+Epoch... (1/30 | Step: 1880 | Loss: 2.1219160556793213, Learning Rate: 2.9185521270846948e-05)
+Epoch... (1/30 | Step: 1890 | Loss: 2.136955738067627, Learning Rate: 2.9181186619098298e-05)
+Epoch... (1/30 | Step: 1900 | Loss: 2.098308563232422, Learning Rate: 2.917685196734965e-05)
+Epoch... (1/30 | Step: 1910 | Loss: 2.095719337463379, Learning Rate: 2.9172517315601e-05)
+Epoch... (1/30 | Step: 1920 | Loss: 2.089087724685669, Learning Rate: 2.9168184482841752e-05)
+Epoch... (1/30 | Step: 1930 | Loss: 2.167004346847534, Learning Rate: 2.9163849831093103e-05)
+Epoch... (1/30 | Step: 1940 | Loss: 1.9983344078063965, Learning Rate: 2.915951336035505e-05)
+Epoch... (1/30 | Step: 1950 | Loss: 2.1173758506774902, Learning Rate: 2.91551787086064e-05)
+Epoch... (1/30 | Step: 1960 | Loss: 2.0237390995025635, Learning Rate: 2.915084405685775e-05)
+Epoch... (1/30 | Step: 1970 | Loss: 2.0724878311157227, Learning Rate: 2.91465094051091e-05)
+Epoch... (1/30 | Step: 1980 | Loss: 2.0563502311706543, Learning Rate: 2.914217475336045e-05)
+Epoch... (1/30 | Step: 1990 | Loss: 2.088345527648926, Learning Rate: 2.91378401016118e-05)
+Epoch... (1/30 | Step: 2000 | Loss: 2.14585542678833, Learning Rate: 2.913350544986315e-05)
+Epoch... (1/30 | Step: 2010 | Loss: 2.0599942207336426, Learning Rate: 2.9129172617103904e-05)
+Epoch... (1/30 | Step: 2020 | Loss: 2.049421787261963, Learning Rate: 2.9124837965355255e-05)
+Epoch... (1/30 | Step: 2030 | Loss: 2.032505989074707, Learning Rate: 2.9120503313606605e-05)
+Epoch... (1/30 | Step: 2040 | Loss: 2.1009111404418945, Learning Rate: 2.911616684286855e-05)
+Epoch... (1/30 | Step: 2050 | Loss: 2.0961179733276367, Learning Rate: 2.9111832191119902e-05)
+Epoch... (1/30 | Step: 2060 | Loss: 2.0474748611450195, Learning Rate: 2.9107497539371252e-05)
+Epoch... (1/30 | Step: 2070 | Loss: 2.1285176277160645, Learning Rate: 2.9103162887622602e-05)
+Epoch... (1/30 | Step: 2080 | Loss: 2.0173821449279785, Learning Rate: 2.9098828235873953e-05)
+Epoch... (1/30 | Step: 2090 | Loss: 2.1344692707061768, Learning Rate: 2.9094493584125303e-05)
+Epoch... (1/30 | Step: 2100 | Loss: 2.0788259506225586, Learning Rate: 2.9090160751366057e-05)
+Epoch... (1/30 | Step: 2100 | Loss: 2.0788259506225586, Learning Rate: 2.9090160751366057e-05)
+Epoch... (1/30 | Step: 2100 | Eval Loss: 2.037459373474121 | Eval rouge1: 40.5198 | Eval rouge2: 15.162 | Eval rougeL: 36.9107 | Eval rougeLsum: 36.9123 | Eval gen_len: 10.8398 |)