Saving weights and logs of epoch 1 - step 1200

ckpt_epoch_1_step_1200/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_1200/flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83f68c25e86ba57002d1a5d9164ddb22c494fcd142c291c67a88d85eea637365
+size 956799284

ckpt_epoch_1_step_1200/special_tokens_map.json

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

ckpt_epoch_1_step_1200/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 sha256:590ece01b6ce062357e7d3d3c9886190e92b2b3ebcc1ec9dde0ffea6bf971bd1
-size 265351
+oid sha256:1f6609a739499790b8ecbe0c08614464524e23dda62c2ed6c436c21973cfe6e9
+size 441988

report.txt

@@ -94,3 +94,35 @@ Epoch... (1/30 | Step: 890 | Loss: 2.254265785217285, Learning Rate: 2.961464997
 Epoch... (1/30 | Step: 900 | Loss: 2.2401223182678223, Learning Rate: 2.9610315323225223e-05)
 Epoch... (1/30 | Step: 900 | Loss: 2.2401223182678223, Learning Rate: 2.9610315323225223e-05)
 Epoch... (1/30 | Step: 900 | Eval Loss: 2.152062177658081 | Eval rouge1: 39.5335 | Eval rouge2: 14.3557 | Eval rougeL: 35.8974 | Eval rougeLsum: 35.9057 | Eval gen_len: 10.8698 |)
+Epoch... (1/30 | Step: 910 | Loss: 2.145946979522705, Learning Rate: 2.9605980671476573e-05)
+Epoch... (1/30 | Step: 920 | Loss: 2.0916032791137695, Learning Rate: 2.9601646019727923e-05)
+Epoch... (1/30 | Step: 930 | Loss: 2.1092920303344727, Learning Rate: 2.9597311367979273e-05)
+Epoch... (1/30 | Step: 940 | Loss: 2.2093448638916016, Learning Rate: 2.9592976716230623e-05)
+Epoch... (1/30 | Step: 950 | Loss: 2.1340670585632324, Learning Rate: 2.9588643883471377e-05)
+Epoch... (1/30 | Step: 960 | Loss: 2.104341506958008, Learning Rate: 2.9584309231722727e-05)
+Epoch... (1/30 | Step: 970 | Loss: 2.1689233779907227, Learning Rate: 2.9579972760984674e-05)
+Epoch... (1/30 | Step: 980 | Loss: 2.1623427867889404, Learning Rate: 2.9575638109236024e-05)
+Epoch... (1/30 | Step: 990 | Loss: 2.050921678543091, Learning Rate: 2.9571303457487375e-05)
+Epoch... (1/30 | Step: 1000 | Loss: 2.2413523197174072, Learning Rate: 2.9566968805738725e-05)
+Epoch... (1/30 | Step: 1010 | Loss: 2.143608570098877, Learning Rate: 2.9562634153990075e-05)
+Epoch... (1/30 | Step: 1020 | Loss: 2.1761255264282227, Learning Rate: 2.9558299502241425e-05)
+Epoch... (1/30 | Step: 1030 | Loss: 2.2119503021240234, Learning Rate: 2.955396666948218e-05)
+Epoch... (1/30 | Step: 1040 | Loss: 2.071683645248413, Learning Rate: 2.954963201773353e-05)
+Epoch... (1/30 | Step: 1050 | Loss: 2.2042810916900635, Learning Rate: 2.954529736598488e-05)
+Epoch... (1/30 | Step: 1060 | Loss: 2.1775331497192383, Learning Rate: 2.954096271423623e-05)
+Epoch... (1/30 | Step: 1070 | Loss: 2.0984702110290527, Learning Rate: 2.9536626243498176e-05)
+Epoch... (1/30 | Step: 1080 | Loss: 2.1763856410980225, Learning Rate: 2.9532291591749527e-05)
+Epoch... (1/30 | Step: 1090 | Loss: 2.2860050201416016, Learning Rate: 2.9527956940000877e-05)
+Epoch... (1/30 | Step: 1100 | Loss: 2.125678062438965, Learning Rate: 2.9523622288252227e-05)
+Epoch... (1/30 | Step: 1110 | Loss: 2.127748727798462, Learning Rate: 2.9519287636503577e-05)
+Epoch... (1/30 | Step: 1120 | Loss: 2.092984199523926, Learning Rate: 2.951495480374433e-05)
+Epoch... (1/30 | Step: 1130 | Loss: 2.1310806274414062, Learning Rate: 2.951062015199568e-05)
+Epoch... (1/30 | Step: 1140 | Loss: 2.1979918479919434, Learning Rate: 2.950628550024703e-05)
+Epoch... (1/30 | Step: 1150 | Loss: 2.229048013687134, Learning Rate: 2.950195084849838e-05)
+Epoch... (1/30 | Step: 1160 | Loss: 2.143617630004883, Learning Rate: 2.949761437776033e-05)
+Epoch... (1/30 | Step: 1170 | Loss: 2.162456750869751, Learning Rate: 2.949327972601168e-05)
+Epoch... (1/30 | Step: 1180 | Loss: 2.1484286785125732, Learning Rate: 2.948894507426303e-05)
+Epoch... (1/30 | Step: 1190 | Loss: 2.19675350189209, Learning Rate: 2.948461042251438e-05)
+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 |)