Saving weights and logs of epoch 3 - step 4800

ckpt_epoch_3_step_4800/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_4800/flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:580e8e62e197cd9cfb737eb02875f70651c94e2e660368f13b33a9205b55a25f
+size 956799284

ckpt_epoch_3_step_4800/special_tokens_map.json

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

ckpt_epoch_3_step_4800/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:a4acc41049a37953f2a9aa48cff87e23a61778cf0563520969f46ee62ed4781f
-size 3263581
+oid sha256:bb55a3d78724c9a55c802522a5ae121712bd605e3f3f200abb43aa69285ec829
+size 3291414

report.txt

@@ -493,3 +493,24 @@ Epoch... (2/30 | Step: 4600 | Loss: 1.8623323440551758, Learning Rate: 2.8006501
 Epoch... (2/30 | Step: 4610 | Loss: 1.8202744722366333, Learning Rate: 2.800216680043377e-05)
 Epoch... (2/30 | Step: 4614 | Loss: 1.9217591285705566, Learning Rate: 2.8000431484542787e-05)
 Epoch... (2/30 | Step: 4614 | Eval Loss: 1.9446606636047363 | Eval rouge1: 41.3801 | Eval rouge2: 15.8404 | Eval rougeL: 37.7066 | Eval rougeLsum: 37.6976 | Eval gen_len: 11.1192 |)
+Epoch... (3/30 | Step: 4620 | Loss: 1.9006057977676392, Learning Rate: 2.799783214868512e-05)
+Epoch... (3/30 | Step: 4630 | Loss: 1.9258897304534912, Learning Rate: 2.799349749693647e-05)
+Epoch... (3/30 | Step: 4640 | Loss: 1.8611785173416138, Learning Rate: 2.798916284518782e-05)
+Epoch... (3/30 | Step: 4650 | Loss: 1.7929704189300537, Learning Rate: 2.7984826374449767e-05)
+Epoch... (3/30 | Step: 4660 | Loss: 1.888678789138794, Learning Rate: 2.7980491722701117e-05)
+Epoch... (3/30 | Step: 4670 | Loss: 1.8310635089874268, Learning Rate: 2.797615888994187e-05)
+Epoch... (3/30 | Step: 4680 | Loss: 1.7876863479614258, Learning Rate: 2.797182423819322e-05)
+Epoch... (3/30 | Step: 4690 | Loss: 1.8022078275680542, Learning Rate: 2.796748958644457e-05)
+Epoch... (3/30 | Step: 4700 | Loss: 1.8882899284362793, Learning Rate: 2.7963154934695922e-05)
+Epoch... (3/30 | Step: 4710 | Loss: 1.8650214672088623, Learning Rate: 2.7958820282947272e-05)
+Epoch... (3/30 | Step: 4720 | Loss: 1.8108880519866943, Learning Rate: 2.7954485631198622e-05)
+Epoch... (3/30 | Step: 4730 | Loss: 1.8337535858154297, Learning Rate: 2.7950150979449973e-05)
+Epoch... (3/30 | Step: 4740 | Loss: 1.8705109357833862, Learning Rate: 2.7945816327701323e-05)
+Epoch... (3/30 | Step: 4750 | Loss: 1.8093873262405396, Learning Rate: 2.7941481675952673e-05)
+Epoch... (3/30 | Step: 4760 | Loss: 1.8352653980255127, Learning Rate: 2.7937147024204023e-05)
+Epoch... (3/30 | Step: 4770 | Loss: 1.8993232250213623, Learning Rate: 2.7932812372455373e-05)
+Epoch... (3/30 | Step: 4780 | Loss: 1.866384506225586, Learning Rate: 2.7928477720706724e-05)
+Epoch... (3/30 | Step: 4790 | Loss: 1.8843146562576294, Learning Rate: 2.7924143068958074e-05)
+Epoch... (3/30 | Step: 4800 | Loss: 1.8721106052398682, Learning Rate: 2.7919808417209424e-05)
+Epoch... (3/30 | Step: 4800 | Loss: 1.8721106052398682, Learning Rate: 2.7919808417209424e-05)
+Epoch... (3/30 | Step: 4800 | Eval Loss: 1.945229411125183 | Eval rouge1: 41.4206 | Eval rouge2: 15.7017 | Eval rougeL: 37.6112 | Eval rougeLsum: 37.6064 | Eval gen_len: 11.2409 |)