Saving weights and logs of epoch 3 - step 6300

ckpt_epoch_3_step_6300/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_3_step_6300/flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a435b66504368f0a898055d7a478672dfc205d0c844eec0ae0cfd3fb8a0858c6
+size 956799284

ckpt_epoch_3_step_6300/special_tokens_map.json

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

ckpt_epoch_3_step_6300/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:dd1863fba015ebcf435f120b60ad86fde74e528f1c432128d6846e426d57ae18
-size 3843746
+oid sha256:67a547018b7633703cf8dcc2c10148f6a6c0cad5086b7bec89b417804e442b18
+size 4092079

report.txt

@@ -642,3 +642,35 @@ Epoch... (3/30 | Step: 5990 | Loss: 1.862635612487793, Learning Rate: 2.74039866
 Epoch... (3/30 | Step: 6000 | Loss: 1.9368724822998047, Learning Rate: 2.7399653845350258e-05)
 Epoch... (3/30 | Step: 6000 | Loss: 1.9368724822998047, Learning Rate: 2.7399653845350258e-05)
 Epoch... (3/30 | Step: 6000 | Eval Loss: 1.9258944988250732 | Eval rouge1: 41.086 | Eval rouge2: 15.536 | Eval rougeL: 37.351 | Eval rougeLsum: 37.3528 | Eval gen_len: 11.2105 |)
+Epoch... (3/30 | Step: 6010 | Loss: 1.9061357975006104, Learning Rate: 2.7395317374612205e-05)
+Epoch... (3/30 | Step: 6020 | Loss: 1.8703413009643555, Learning Rate: 2.7390982722863555e-05)
+Epoch... (3/30 | Step: 6030 | Loss: 1.9126508235931396, Learning Rate: 2.7386648071114905e-05)
+Epoch... (3/30 | Step: 6040 | Loss: 1.8640691041946411, Learning Rate: 2.7382313419366255e-05)
+Epoch... (3/30 | Step: 6050 | Loss: 1.8807706832885742, Learning Rate: 2.7377978767617606e-05)
+Epoch... (3/30 | Step: 6060 | Loss: 1.9057433605194092, Learning Rate: 2.7373644115868956e-05)
+Epoch... (3/30 | Step: 6070 | Loss: 1.8330992460250854, Learning Rate: 2.7369309464120306e-05)
+Epoch... (3/30 | Step: 6080 | Loss: 1.9661799669265747, Learning Rate: 2.7364974812371656e-05)
+Epoch... (3/30 | Step: 6090 | Loss: 1.7911491394042969, Learning Rate: 2.736064197961241e-05)
+Epoch... (3/30 | Step: 6100 | Loss: 1.7153382301330566, Learning Rate: 2.735630732786376e-05)
+Epoch... (3/30 | Step: 6110 | Loss: 1.8614788055419922, Learning Rate: 2.735197267611511e-05)
+Epoch... (3/30 | Step: 6120 | Loss: 1.7746303081512451, Learning Rate: 2.7347636205377057e-05)
+Epoch... (3/30 | Step: 6130 | Loss: 1.8193302154541016, Learning Rate: 2.7343301553628407e-05)
+Epoch... (3/30 | Step: 6140 | Loss: 1.8340637683868408, Learning Rate: 2.7338966901879758e-05)
+Epoch... (3/30 | Step: 6150 | Loss: 1.8399102687835693, Learning Rate: 2.7334632250131108e-05)
+Epoch... (3/30 | Step: 6160 | Loss: 1.8006336688995361, Learning Rate: 2.7330297598382458e-05)
+Epoch... (3/30 | Step: 6170 | Loss: 1.7936418056488037, Learning Rate: 2.7325964765623212e-05)
+Epoch... (3/30 | Step: 6180 | Loss: 1.7291109561920166, Learning Rate: 2.7321630113874562e-05)
+Epoch... (3/30 | Step: 6190 | Loss: 1.9827232360839844, Learning Rate: 2.7317295462125912e-05)
+Epoch... (3/30 | Step: 6200 | Loss: 1.862128496170044, Learning Rate: 2.7312960810377263e-05)
+Epoch... (3/30 | Step: 6210 | Loss: 1.775388240814209, Learning Rate: 2.730862433963921e-05)
+Epoch... (3/30 | Step: 6220 | Loss: 1.7971916198730469, Learning Rate: 2.730428968789056e-05)
+Epoch... (3/30 | Step: 6230 | Loss: 1.8290495872497559, Learning Rate: 2.729995503614191e-05)
+Epoch... (3/30 | Step: 6240 | Loss: 1.844942331314087, Learning Rate: 2.729562038439326e-05)
+Epoch... (3/30 | Step: 6250 | Loss: 1.816731333732605, Learning Rate: 2.729128573264461e-05)
+Epoch... (3/30 | Step: 6260 | Loss: 1.8273515701293945, Learning Rate: 2.7286952899885364e-05)
+Epoch... (3/30 | Step: 6270 | Loss: 1.8184173107147217, Learning Rate: 2.7282618248136714e-05)
+Epoch... (3/30 | Step: 6280 | Loss: 1.796694040298462, Learning Rate: 2.7278283596388064e-05)
+Epoch... (3/30 | Step: 6290 | Loss: 1.821446180343628, Learning Rate: 2.7273948944639415e-05)
+Epoch... (3/30 | Step: 6300 | Loss: 1.8445713520050049, Learning Rate: 2.7269614292890765e-05)
+Epoch... (3/30 | Step: 6300 | Loss: 1.8445713520050049, Learning Rate: 2.7269614292890765e-05)
+Epoch... (3/30 | Step: 6300 | Eval Loss: 1.9208292961120605 | Eval rouge1: 41.3445 | Eval rouge2: 15.639 | Eval rougeL: 37.5483 | Eval rougeLsum: 37.5456 | Eval gen_len: 11.2487 |)