Saving weights and logs of epoch 1 - step 500

ckpt_epoch_1_step_500/config.json

@@ -0,0 +1,174 @@
+{
+  "architectures": [
+    "VisionEncoderDecoderModel"
+  ],
+  "bos_token_id": 50256,
+  "decoder": {
+    "_name_or_path": "gpt2",
+    "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,
+    "cross_attention_hidden_size": null,
+    "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,
+    "reorder_and_upcast_attn": false,
+    "repetition_penalty": 1.0,
+    "resid_pdrop": 0.1,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "scale_attn_by_inverse_layer_idx": 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": "4.15.0.dev0",
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 50257
+  },
+  "decoder_start_token_id": 50256,
+  "encoder": {
+    "_name_or_path": "google/vit-base-patch16-224-in21k",
+    "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,
+    "cross_attention_hidden_size": null,
+    "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": {},
+    "qkv_bias": true,
+    "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": "4.15.0.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_1_step_500/eval_results.json

@@ -0,0 +1,8 @@
+{
+    "eval_gen_len": 12.159915,
+    "eval_loss": 2.153403,
+    "eval_rouge1": 38.644711,
+    "eval_rouge2": 13.35726,
+    "eval_rougeL": 34.996203,
+    "eval_rougeLsum": 35.002078
+}

ckpt_epoch_1_step_500/flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3c736848423b3246c224d3486dcc93b09fea07814d16d2ba3fcb5484c009171
+size 956799284

ckpt_epoch_1_step_500/special_tokens_map.json

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

ckpt_epoch_1_step_500/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.1640096976.t1v-n-ca5bb87c-w-0.29764.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc028f19a081516e321ed3157e5a245f0e0d044cdc4113f9367cb0d30106ddc3
+size 1866938

log

@@ -0,0 +1,51 @@
+Epoch... (1/1 | Step: 10 | Loss: 3.152461051940918 | Learning Rate: 2.988296364492271e-05 | Time per step: 15.587736415863038)
+Epoch... (1/1 | Step: 20 | Loss: 2.984159469604492 | Learning Rate: 2.9752924092463218e-05 | Time per step: 7.810857331752777)
+Epoch... (1/1 | Step: 30 | Loss: 2.966938018798828 | Learning Rate: 2.9622886358993128e-05 | Time per step: 5.218205340703329)
+Epoch... (1/1 | Step: 40 | Loss: 2.7915446758270264 | Learning Rate: 2.9492846806533635e-05 | Time per step: 3.923228472471237)
+Epoch... (1/1 | Step: 50 | Loss: 2.8086533546447754 | Learning Rate: 2.9362809073063545e-05 | Time per step: 3.1455979251861574)
+Epoch... (1/1 | Step: 60 | Loss: 2.7164440155029297 | Learning Rate: 2.923276952060405e-05 | Time per step: 2.6309441407521565)
+Epoch... (1/1 | Step: 70 | Loss: 2.620852470397949 | Learning Rate: 2.910272996814456e-05 | Time per step: 2.2604179041726247)
+Epoch... (1/1 | Step: 80 | Loss: 2.6376171112060547 | Learning Rate: 2.897269223467447e-05 | Time per step: 1.9821367621421815)
+Epoch... (1/1 | Step: 90 | Loss: 2.5884041786193848 | Learning Rate: 2.8842652682214975e-05 | Time per step: 1.7655608786476984)
+Epoch... (1/1 | Step: 100 | Loss: 2.605238914489746 | Learning Rate: 2.8712613129755482e-05 | Time per step: 1.592444236278534)
+Epoch... (1/1 | Step: 110 | Loss: 2.5857369899749756 | Learning Rate: 2.858257357729599e-05 | Time per step: 1.4507770885120739)
+Epoch... (1/1 | Step: 120 | Loss: 2.462893009185791 | Learning Rate: 2.8452534024836496e-05 | Time per step: 1.3327178955078125)
+Epoch... (1/1 | Step: 130 | Loss: 2.5480122566223145 | Learning Rate: 2.8322496291366406e-05 | Time per step: 1.2347213745117187)
+Epoch... (1/1 | Step: 140 | Loss: 2.5385568141937256 | Learning Rate: 2.8192456738906913e-05 | Time per step: 1.1489436558314732)
+Epoch... (1/1 | Step: 150 | Loss: 2.5392045974731445 | Learning Rate: 2.806241718644742e-05 | Time per step: 1.0746502176920574)
+Epoch... (1/1 | Step: 160 | Loss: 2.5710103511810303 | Learning Rate: 2.793237945297733e-05 | Time per step: 1.0096801206469537)
+Epoch... (1/1 | Step: 170 | Loss: 2.4399685859680176 | Learning Rate: 2.7802339900517836e-05 | Time per step: 0.9523633339825799)
+Epoch... (1/1 | Step: 180 | Loss: 2.457218885421753 | Learning Rate: 2.7672302167047746e-05 | Time per step: 0.9013986693488227)
+Epoch... (1/1 | Step: 190 | Loss: 2.5539286136627197 | Learning Rate: 2.7542262614588253e-05 | Time per step: 0.8558672904968262)
+Epoch... (1/1 | Step: 200 | Loss: 2.4565377235412598 | Learning Rate: 2.741222306212876e-05 | Time per step: 0.8160686993598938)
+Epoch... (1/1 | Step: 210 | Loss: 2.4070143699645996 | Learning Rate: 2.728218532865867e-05 | Time per step: 0.7789805684770856)
+Epoch... (1/1 | Step: 220 | Loss: 2.3925132751464844 | Learning Rate: 2.7152143957209773e-05 | Time per step: 0.7452002211050553)
+Epoch... (1/1 | Step: 230 | Loss: 2.375119209289551 | Learning Rate: 2.7022106223739684e-05 | Time per step: 0.714317157994146)
+Epoch... (1/1 | Step: 240 | Loss: 2.4307475090026855 | Learning Rate: 2.689206667128019e-05 | Time per step: 0.6860215455293656)
+Epoch... (1/1 | Step: 250 | Loss: 2.3495891094207764 | Learning Rate: 2.6762027118820697e-05 | Time per step: 0.6600858697891235)
+Epoch... (1/1 | Step: 260 | Loss: 2.323152780532837 | Learning Rate: 2.6631989385350607e-05 | Time per step: 0.6362197930996235)
+Epoch... (1/1 | Step: 270 | Loss: 2.3550381660461426 | Learning Rate: 2.6501949832891114e-05 | Time per step: 0.6149519796724673)
+Epoch... (1/1 | Step: 280 | Loss: 2.418388843536377 | Learning Rate: 2.637191028043162e-05 | Time per step: 0.5942821894373213)
+Epoch... (1/1 | Step: 290 | Loss: 2.304417133331299 | Learning Rate: 2.624187254696153e-05 | Time per step: 0.5750318412123056)
+Epoch... (1/1 | Step: 300 | Loss: 2.292708396911621 | Learning Rate: 2.6111832994502038e-05 | Time per step: 0.5570862245559692)
+Epoch... (1/1 | Step: 310 | Loss: 2.2911200523376465 | Learning Rate: 2.5981795261031948e-05 | Time per step: 0.5402729565097439)
+Epoch... (1/1 | Step: 320 | Loss: 2.3142271041870117 | Learning Rate: 2.5851755708572455e-05 | Time per step: 0.5245530068874359)
+Epoch... (1/1 | Step: 330 | Loss: 2.2752268314361572 | Learning Rate: 2.5721714337123558e-05 | Time per step: 0.5098378614945845)
+Epoch... (1/1 | Step: 340 | Loss: 2.3485875129699707 | Learning Rate: 2.5591678422642872e-05 | Time per step: 0.4959293926463408)
+Epoch... (1/1 | Step: 350 | Loss: 2.2506933212280273 | Learning Rate: 2.5461637051193975e-05 | Time per step: 0.4828984478541783)
+Epoch... (1/1 | Step: 360 | Loss: 2.309922695159912 | Learning Rate: 2.5331599317723885e-05 | Time per step: 0.4705710119671292)
+Epoch... (1/1 | Step: 370 | Loss: 2.345146656036377 | Learning Rate: 2.5201559765264392e-05 | Time per step: 0.45886457804087044)
+Epoch... (1/1 | Step: 380 | Loss: 2.2607898712158203 | Learning Rate: 2.50715202128049e-05 | Time per step: 0.4477769217993084)
+Epoch... (1/1 | Step: 390 | Loss: 2.2573559284210205 | Learning Rate: 2.494148247933481e-05 | Time per step: 0.437354511481065)
+Epoch... (1/1 | Step: 400 | Loss: 2.306978464126587 | Learning Rate: 2.4811442926875316e-05 | Time per step: 0.42739131927490237)
+Epoch... (1/1 | Step: 410 | Loss: 2.194396495819092 | Learning Rate: 2.4681403374415822e-05 | Time per step: 0.41849243408296166)
+Epoch... (1/1 | Step: 420 | Loss: 2.246137857437134 | Learning Rate: 2.4551365640945733e-05 | Time per step: 0.40944125141416277)
+Epoch... (1/1 | Step: 430 | Loss: 2.2333340644836426 | Learning Rate: 2.442132608848624e-05 | Time per step: 0.400786896639092)
+Epoch... (1/1 | Step: 440 | Loss: 2.240902900695801 | Learning Rate: 2.4291286536026746e-05 | Time per step: 0.39255606640468943)
+Epoch... (1/1 | Step: 450 | Loss: 2.208949565887451 | Learning Rate: 2.4161248802556656e-05 | Time per step: 0.3847881078720093)
+Epoch... (1/1 | Step: 460 | Loss: 2.1334152221679688 | Learning Rate: 2.403120743110776e-05 | Time per step: 0.37723992026370506)
+Epoch... (1/1 | Step: 470 | Loss: 2.126279354095459 | Learning Rate: 2.390116969763767e-05 | Time per step: 0.3700234945784224)
+Epoch... (1/1 | Step: 480 | Loss: 2.2395260334014893 | Learning Rate: 2.3771130145178176e-05 | Time per step: 0.3634992683927218)
+Epoch... (1/1 | Step: 490 | Loss: 2.204587936401367 | Learning Rate: 2.3641092411708087e-05 | Time per step: 0.3568650634921327)
+Epoch... (1/1 | Step: 500 | Loss: 2.204573154449463 | Learning Rate: 2.3511052859248593e-05 | Time per step: 0.35050120973587034)
+Epoch... (1/1 | Step: 500 | Eval Loss: 2.153402805328369 | Eval rouge1: 38.644711 | Eval rouge2: 13.35726 | Eval rougeL: 34.996203 | Eval rougeLsum: 35.002078 | Eval gen_len: 12.159915 |)