Saving weights and logs of epoch 2 - step 4200

ckpt_epoch_2_step_4200/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_4200/flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:333b49d8f993208c4ab7333478b3c3622b65fb8c07a017184f564c89c944a2ea
+size 956799284

ckpt_epoch_2_step_4200/special_tokens_map.json

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

ckpt_epoch_2_step_4200/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 sha256:07b76c9c1f2e7c24294f98dcc031ffc0b2f703a21056085a673734a060758f0f
-size 2322337
+oid sha256:3dd85c5c40a998050e0097c1cdb924a1c39dac446c23c3e110ff1ee112228b04
+size 2601099

report.txt

@@ -416,3 +416,35 @@ Epoch... (2/30 | Step: 3890 | Loss: 2.0305581092834473, Learning Rate: 2.8314259
 Epoch... (2/30 | Step: 3900 | Loss: 1.985913872718811, Learning Rate: 2.83099252555985e-05)
 Epoch... (2/30 | Step: 3900 | Loss: 1.985913872718811, Learning Rate: 2.83099252555985e-05)
 Epoch... (2/30 | Step: 3900 | Eval Loss: 1.9652690887451172 | Eval rouge1: 41.1961 | Eval rouge2: 15.6232 | Eval rougeL: 37.4628 | Eval rougeLsum: 37.4635 | Eval gen_len: 10.8986 |)
+Epoch... (2/30 | Step: 3910 | Loss: 1.9935262203216553, Learning Rate: 2.830559060384985e-05)
+Epoch... (2/30 | Step: 3920 | Loss: 1.9875662326812744, Learning Rate: 2.83012559521012e-05)
+Epoch... (2/30 | Step: 3930 | Loss: 1.9753940105438232, Learning Rate: 2.829692130035255e-05)
+Epoch... (2/30 | Step: 3940 | Loss: 1.9695476293563843, Learning Rate: 2.82925866486039e-05)
+Epoch... (2/30 | Step: 3950 | Loss: 1.9616758823394775, Learning Rate: 2.828825199685525e-05)
+Epoch... (2/30 | Step: 3960 | Loss: 2.000000476837158, Learning Rate: 2.8283919164096005e-05)
+Epoch... (2/30 | Step: 3970 | Loss: 1.941230297088623, Learning Rate: 2.8279584512347355e-05)
+Epoch... (2/30 | Step: 3980 | Loss: 1.913987159729004, Learning Rate: 2.8275248041609302e-05)
+Epoch... (2/30 | Step: 3990 | Loss: 2.0030932426452637, Learning Rate: 2.8270913389860652e-05)
+Epoch... (2/30 | Step: 4000 | Loss: 1.9450314044952393, Learning Rate: 2.8266578738112003e-05)
+Epoch... (2/30 | Step: 4010 | Loss: 2.0085952281951904, Learning Rate: 2.8262244086363353e-05)
+Epoch... (2/30 | Step: 4020 | Loss: 1.9368841648101807, Learning Rate: 2.8257909434614703e-05)
+Epoch... (2/30 | Step: 4030 | Loss: 1.9371402263641357, Learning Rate: 2.8253574782866053e-05)
+Epoch... (2/30 | Step: 4040 | Loss: 1.8853888511657715, Learning Rate: 2.8249240131117404e-05)
+Epoch... (2/30 | Step: 4050 | Loss: 1.949146032333374, Learning Rate: 2.8244907298358157e-05)
+Epoch... (2/30 | Step: 4060 | Loss: 1.930593490600586, Learning Rate: 2.8240572646609508e-05)
+Epoch... (2/30 | Step: 4070 | Loss: 1.9453805685043335, Learning Rate: 2.8236236175871454e-05)
+Epoch... (2/30 | Step: 4080 | Loss: 2.0240161418914795, Learning Rate: 2.8231901524122804e-05)
+Epoch... (2/30 | Step: 4090 | Loss: 1.8439011573791504, Learning Rate: 2.8227566872374155e-05)
+Epoch... (2/30 | Step: 4100 | Loss: 1.9838228225708008, Learning Rate: 2.8223232220625505e-05)
+Epoch... (2/30 | Step: 4110 | Loss: 1.9583349227905273, Learning Rate: 2.8218897568876855e-05)
+Epoch... (2/30 | Step: 4120 | Loss: 1.9604921340942383, Learning Rate: 2.8214562917128205e-05)
+Epoch... (2/30 | Step: 4130 | Loss: 1.9949344396591187, Learning Rate: 2.8210228265379556e-05)
+Epoch... (2/30 | Step: 4140 | Loss: 1.9361615180969238, Learning Rate: 2.820589543262031e-05)
+Epoch... (2/30 | Step: 4150 | Loss: 1.8858580589294434, Learning Rate: 2.820156078087166e-05)
+Epoch... (2/30 | Step: 4160 | Loss: 1.939874529838562, Learning Rate: 2.819722612912301e-05)
+Epoch... (2/30 | Step: 4170 | Loss: 1.8935625553131104, Learning Rate: 2.819289147737436e-05)
+Epoch... (2/30 | Step: 4180 | Loss: 1.8785367012023926, Learning Rate: 2.8188555006636307e-05)
+Epoch... (2/30 | Step: 4190 | Loss: 1.893964171409607, Learning Rate: 2.8184220354887657e-05)
+Epoch... (2/30 | Step: 4200 | Loss: 1.8666478395462036, Learning Rate: 2.8179885703139007e-05)
+Epoch... (2/30 | Step: 4200 | Loss: 1.8666478395462036, Learning Rate: 2.8179885703139007e-05)
+Epoch... (2/30 | Step: 4200 | Eval Loss: 1.9555346965789795 | Eval rouge1: 40.9762 | Eval rouge2: 15.5911 | Eval rougeL: 37.3749 | Eval rougeLsum: 37.3706 | Eval gen_len: 10.9797 |)