Saving weights and logs of epoch 4 - step 7800

ckpt_epoch_4_step_7800/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_4_step_7800/flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f032f7141ae7653dc0e3a6cfeacd7efeefdf72e70070a8eaf277d970913e0ab
+size 956799284

ckpt_epoch_4_step_7800/special_tokens_map.json

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

ckpt_epoch_4_step_7800/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:ad94b88b17bd15ad5d81b1558c45c8c4f51154f981ad863531e69c7694729dac
-size 5187773
+oid sha256:74bc7342c72747fe21ded57fede817605996d502c59119e05deea76f00cd3922
+size 5317477

report.txt

@@ -804,3 +804,35 @@ Epoch... (4/30 | Step: 7490 | Loss: 1.799612283706665, Learning Rate: 2.67537907
 Epoch... (4/30 | Step: 7500 | Loss: 1.8033530712127686, Learning Rate: 2.6749457902042195e-05)
 Epoch... (4/30 | Step: 7500 | Loss: 1.8033530712127686, Learning Rate: 2.6749457902042195e-05)
 Epoch... (4/30 | Step: 7500 | Eval Loss: 1.9142653942108154 | Eval rouge1: 41.2043 | Eval rouge2: 15.5504 | Eval rougeL: 37.4412 | Eval rougeLsum: 37.4419 | Eval gen_len: 11.239 |)
+Epoch... (4/30 | Step: 7510 | Loss: 1.843985915184021, Learning Rate: 2.6745123250293545e-05)
+Epoch... (4/30 | Step: 7520 | Loss: 1.7345409393310547, Learning Rate: 2.6740788598544896e-05)
+Epoch... (4/30 | Step: 7530 | Loss: 1.7642332315444946, Learning Rate: 2.6736453946796246e-05)
+Epoch... (4/30 | Step: 7540 | Loss: 1.7493267059326172, Learning Rate: 2.6732119295047596e-05)
+Epoch... (4/30 | Step: 7550 | Loss: 1.8050358295440674, Learning Rate: 2.6727784643298946e-05)
+Epoch... (4/30 | Step: 7560 | Loss: 1.714761734008789, Learning Rate: 2.6723449991550297e-05)
+Epoch... (4/30 | Step: 7570 | Loss: 1.7845580577850342, Learning Rate: 2.6719113520812243e-05)
+Epoch... (4/30 | Step: 7580 | Loss: 1.7691221237182617, Learning Rate: 2.6714778869063593e-05)
+Epoch... (4/30 | Step: 7590 | Loss: 1.7299931049346924, Learning Rate: 2.6710446036304347e-05)
+Epoch... (4/30 | Step: 7600 | Loss: 1.7709275484085083, Learning Rate: 2.6706111384555697e-05)
+Epoch... (4/30 | Step: 7610 | Loss: 1.7494062185287476, Learning Rate: 2.6701776732807048e-05)
+Epoch... (4/30 | Step: 7620 | Loss: 1.825223445892334, Learning Rate: 2.6697442081058398e-05)
+Epoch... (4/30 | Step: 7630 | Loss: 1.7665493488311768, Learning Rate: 2.6693107429309748e-05)
+Epoch... (4/30 | Step: 7640 | Loss: 1.7820301055908203, Learning Rate: 2.66887727775611e-05)
+Epoch... (4/30 | Step: 7650 | Loss: 1.7157957553863525, Learning Rate: 2.668443812581245e-05)
+Epoch... (4/30 | Step: 7660 | Loss: 1.7743289470672607, Learning Rate: 2.66801034740638e-05)
+Epoch... (4/30 | Step: 7670 | Loss: 1.8115360736846924, Learning Rate: 2.667576882231515e-05)
+Epoch... (4/30 | Step: 7680 | Loss: 1.761516809463501, Learning Rate: 2.66714341705665e-05)
+Epoch... (4/30 | Step: 7690 | Loss: 1.8202887773513794, Learning Rate: 2.666709951881785e-05)
+Epoch... (4/30 | Step: 7700 | Loss: 1.754068374633789, Learning Rate: 2.66627648670692e-05)
+Epoch... (4/30 | Step: 7710 | Loss: 1.8063127994537354, Learning Rate: 2.665843021532055e-05)
+Epoch... (4/30 | Step: 7720 | Loss: 1.757204294204712, Learning Rate: 2.66540955635719e-05)
+Epoch... (4/30 | Step: 7730 | Loss: 1.8072246313095093, Learning Rate: 2.664976091182325e-05)
+Epoch... (4/30 | Step: 7740 | Loss: 1.7353928089141846, Learning Rate: 2.66454262600746e-05)
+Epoch... (4/30 | Step: 7750 | Loss: 1.7102036476135254, Learning Rate: 2.664109160832595e-05)
+Epoch... (4/30 | Step: 7760 | Loss: 1.7107794284820557, Learning Rate: 2.6636755137587897e-05)
+Epoch... (4/30 | Step: 7770 | Loss: 1.8361232280731201, Learning Rate: 2.663242230482865e-05)
+Epoch... (4/30 | Step: 7780 | Loss: 1.748347282409668, Learning Rate: 2.662808765308e-05)
+Epoch... (4/30 | Step: 7790 | Loss: 1.7465569972991943, Learning Rate: 2.6623753001331352e-05)
+Epoch... (4/30 | Step: 7800 | Loss: 1.8418853282928467, Learning Rate: 2.6619418349582702e-05)
+Epoch... (4/30 | Step: 7800 | Loss: 1.8418853282928467, Learning Rate: 2.6619418349582702e-05)
+Epoch... (4/30 | Step: 7800 | Eval Loss: 1.9070324897766113 | Eval rouge1: 41.41 | Eval rouge2: 15.682 | Eval rougeL: 37.6374 | Eval rougeLsum: 37.6387 | Eval gen_len: 11.2008 |)