Saving weights and logs of epoch 2 - step 4614

ckpt_epoch_2_step_4614/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_4614/flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d44000cfaf8f501bf6c78a8d3c73c8e369d723098c68e44d1f655d5d60189d2
+size 956799284

ckpt_epoch_2_step_4614/special_tokens_map.json

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

ckpt_epoch_2_step_4614/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 sha256:7dcef2c1cf7105edc9d303fb6948c27bf83038daeab2f1420ea0449b4b80f390
-size 2923961
+oid sha256:a4acc41049a37953f2a9aa48cff87e23a61778cf0563520969f46ee62ed4781f
+size 3263581

report.txt

@@ -480,3 +480,16 @@ Epoch... (2/30 | Step: 4490 | Loss: 1.8857262134552002, Learning Rate: 2.8054182
 Epoch... (2/30 | Step: 4500 | Loss: 1.8706979751586914, Learning Rate: 2.8049847969668917e-05)
 Epoch... (2/30 | Step: 4500 | Loss: 1.8706979751586914, Learning Rate: 2.8049847969668917e-05)
 Epoch... (2/30 | Step: 4500 | Eval Loss: 1.9466681480407715 | Eval rouge1: 40.7165 | Eval rouge2: 15.3635 | Eval rougeL: 37.0299 | Eval rougeLsum: 37.031 | Eval gen_len: 11.2565 |)
+Epoch... (2/30 | Step: 4510 | Loss: 1.9182460308074951, Learning Rate: 2.8045513317920268e-05)
+Epoch... (2/30 | Step: 4520 | Loss: 1.937203288078308, Learning Rate: 2.8041178666171618e-05)
+Epoch... (2/30 | Step: 4530 | Loss: 1.91261625289917, Learning Rate: 2.8036844014422968e-05)
+Epoch... (2/30 | Step: 4540 | Loss: 1.9567575454711914, Learning Rate: 2.8032509362674318e-05)
+Epoch... (2/30 | Step: 4550 | Loss: 1.9147999286651611, Learning Rate: 2.802817471092567e-05)
+Epoch... (2/30 | Step: 4560 | Loss: 1.9001394510269165, Learning Rate: 2.802384005917702e-05)
+Epoch... (2/30 | Step: 4570 | Loss: 1.9326331615447998, Learning Rate: 2.8019503588438965e-05)
+Epoch... (2/30 | Step: 4580 | Loss: 1.9304759502410889, Learning Rate: 2.801517075567972e-05)
+Epoch... (2/30 | Step: 4590 | Loss: 1.8214722871780396, Learning Rate: 2.801083610393107e-05)
+Epoch... (2/30 | Step: 4600 | Loss: 1.8623323440551758, Learning Rate: 2.800650145218242e-05)
+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 |)