Saving weights and logs of epoch 1 - step 1500

ckpt_epoch_1_step_1500/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_1500/eval_results.json

@@ -0,0 +1,8 @@
+{
+    "eval_gen_len": 12.283868,
+    "eval_loss": 2.034754,
+    "eval_rouge1": 39.720462,
+    "eval_rouge2": 14.404286,
+    "eval_rougeL": 35.987809,
+    "eval_rougeLsum": 35.987896
+}

ckpt_epoch_1_step_1500/flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b119f09f52328f2822d2f115e9de4c1c1229c91e025e98dd7218097f871935e
+size 956799284

ckpt_epoch_1_step_1500/special_tokens_map.json

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

ckpt_epoch_1_step_1500/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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d9e4a7bd8f55385ffabcc2227ff8d471926ed964b9579c0304910890c0c9da6
-size 7407360
+oid sha256:219fa39bf6ea9cbc1e845c3ad236a19bf3911b73fadb8ed0a061a20408c66266
+size 16622782

log

@@ -100,3 +100,54 @@ Epoch... (1/1 | Step: 980 | Loss: 2.1486573219299316 | Learning Rate: 1.72691798
 Epoch... (1/1 | Step: 990 | Loss: 2.1983158588409424 | Learning Rate: 1.7139142073574476e-05 | Time per step: 0.19692125440847993)
 Epoch... (1/1 | Step: 1000 | Loss: 2.1434619426727295 | Learning Rate: 1.7009102521114983e-05 | Time per step: 0.195358873128891)
 Epoch... (1/1 | Step: 1000 | Eval Loss: 2.071117639541626 | Eval rouge1: 39.652538 | Eval rouge2: 14.177532 | Eval rougeL: 35.850527 | Eval rougeLsum: 35.848975 | Eval gen_len: 12.273961 |)
+Epoch... (1/1 | Step: 1010 | Loss: 2.1113176345825195 | Learning Rate: 1.687906296865549e-05 | Time per step: 0.19387355157644443)
+Epoch... (1/1 | Step: 1020 | Loss: 2.125403881072998 | Learning Rate: 1.67490252351854e-05 | Time per step: 0.19240601436764587)
+Epoch... (1/1 | Step: 1030 | Loss: 2.109292984008789 | Learning Rate: 1.6618983863736503e-05 | Time per step: 0.1909887906417106)
+Epoch... (1/1 | Step: 1040 | Loss: 2.0393459796905518 | Learning Rate: 1.6488947949255817e-05 | Time per step: 0.18951574976627644)
+Epoch... (1/1 | Step: 1050 | Loss: 2.0851333141326904 | Learning Rate: 1.635890657780692e-05 | Time per step: 0.18808958825610933)
+Epoch... (1/1 | Step: 1060 | Loss: 2.032742738723755 | Learning Rate: 1.622886884433683e-05 | Time per step: 0.1866728407032085)
+Epoch... (1/1 | Step: 1070 | Loss: 2.090559959411621 | Learning Rate: 1.6098829291877337e-05 | Time per step: 0.185282122754605)
+Epoch... (1/1 | Step: 1080 | Loss: 2.0871057510375977 | Learning Rate: 1.5968789739417844e-05 | Time per step: 0.18392574345624005)
+Epoch... (1/1 | Step: 1090 | Loss: 2.0560994148254395 | Learning Rate: 1.5838752005947754e-05 | Time per step: 0.18262962201319705)
+Epoch... (1/1 | Step: 1100 | Loss: 2.1433119773864746 | Learning Rate: 1.570871245348826e-05 | Time per step: 0.18134411139921708)
+Epoch... (1/1 | Step: 1110 | Loss: 2.1094539165496826 | Learning Rate: 1.5578672901028767e-05 | Time per step: 0.18005623065673554)
+Epoch... (1/1 | Step: 1120 | Loss: 2.0397915840148926 | Learning Rate: 1.5448633348569274e-05 | Time per step: 0.17881171469177518)
+Epoch... (1/1 | Step: 1130 | Loss: 2.0928614139556885 | Learning Rate: 1.5318595615099184e-05 | Time per step: 0.1775794653765923)
+Epoch... (1/1 | Step: 1140 | Loss: 2.071333408355713 | Learning Rate: 1.518855515314499e-05 | Time per step: 0.17638430909106606)
+Epoch... (1/1 | Step: 1150 | Loss: 2.141636371612549 | Learning Rate: 1.5058518329169601e-05 | Time per step: 0.17520383834838868)
+Epoch... (1/1 | Step: 1160 | Loss: 1.9951622486114502 | Learning Rate: 1.4928477867215406e-05 | Time per step: 0.17405129814970083)
+Epoch... (1/1 | Step: 1170 | Loss: 2.0520851612091064 | Learning Rate: 1.4798439224250615e-05 | Time per step: 0.17289256825406327)
+Epoch... (1/1 | Step: 1180 | Loss: 2.053399085998535 | Learning Rate: 1.4668399671791121e-05 | Time per step: 0.17176148750014225)
+Epoch... (1/1 | Step: 1190 | Loss: 2.0979127883911133 | Learning Rate: 1.453836102882633e-05 | Time per step: 0.17067777028604716)
+Epoch... (1/1 | Step: 1200 | Loss: 2.037087917327881 | Learning Rate: 1.4408322385861538e-05 | Time per step: 0.1697588900725047)
+Epoch... (1/1 | Step: 1210 | Loss: 2.225379467010498 | Learning Rate: 1.4278283742896747e-05 | Time per step: 0.16866758992849304)
+Epoch... (1/1 | Step: 1220 | Loss: 2.072798728942871 | Learning Rate: 1.4148244190437254e-05 | Time per step: 0.16764525331434657)
+Epoch... (1/1 | Step: 1230 | Loss: 2.0676560401916504 | Learning Rate: 1.4018205547472462e-05 | Time per step: 0.1666269135668995)
+Epoch... (1/1 | Step: 1240 | Loss: 2.0550100803375244 | Learning Rate: 1.388816690450767e-05 | Time per step: 0.16559767165491657)
+Epoch... (1/1 | Step: 1250 | Loss: 2.090104579925537 | Learning Rate: 1.3758128261542879e-05 | Time per step: 0.16458576316833495)
+Epoch... (1/1 | Step: 1260 | Loss: 2.037855863571167 | Learning Rate: 1.3628086890093982e-05 | Time per step: 0.16380649502315217)
+Epoch... (1/1 | Step: 1270 | Loss: 2.069274663925171 | Learning Rate: 1.349804824712919e-05 | Time per step: 0.16282440039116566)
+Epoch... (1/1 | Step: 1280 | Loss: 2.139634370803833 | Learning Rate: 1.33680096041644e-05 | Time per step: 0.16187303308397533)
+Epoch... (1/1 | Step: 1290 | Loss: 2.0635054111480713 | Learning Rate: 1.3237970961199608e-05 | Time per step: 0.16094879715941673)
+Epoch... (1/1 | Step: 1300 | Loss: 2.115933418273926 | Learning Rate: 1.3107932318234816e-05 | Time per step: 0.16003306462214542)
+Epoch... (1/1 | Step: 1310 | Loss: 2.1170766353607178 | Learning Rate: 1.2977892765775323e-05 | Time per step: 0.15911450968443894)
+Epoch... (1/1 | Step: 1320 | Loss: 2.124302864074707 | Learning Rate: 1.2847854122810531e-05 | Time per step: 0.15840172821825202)
+Epoch... (1/1 | Step: 1330 | Loss: 2.0505247116088867 | Learning Rate: 1.271781547984574e-05 | Time per step: 0.15752380396190444)
+Epoch... (1/1 | Step: 1340 | Loss: 2.0901174545288086 | Learning Rate: 1.2587776836880948e-05 | Time per step: 0.15665231978715355)
+Epoch... (1/1 | Step: 1350 | Loss: 2.0725221633911133 | Learning Rate: 1.2457737284421455e-05 | Time per step: 0.15581043596620914)
+Epoch... (1/1 | Step: 1360 | Loss: 2.173769950866699 | Learning Rate: 1.2327698641456664e-05 | Time per step: 0.15497289966134464)
+Epoch... (1/1 | Step: 1370 | Loss: 1.9631630182266235 | Learning Rate: 1.2197659998491872e-05 | Time per step: 0.15411251478821691)
+Epoch... (1/1 | Step: 1380 | Loss: 2.0254154205322266 | Learning Rate: 1.2067619536537677e-05 | Time per step: 0.15345382293065388)
+Epoch... (1/1 | Step: 1390 | Loss: 2.0926127433776855 | Learning Rate: 1.1937579984078184e-05 | Time per step: 0.15263587742400683)
+Epoch... (1/1 | Step: 1400 | Loss: 2.1013355255126953 | Learning Rate: 1.1807541341113392e-05 | Time per step: 0.15183171289307731)
+Epoch... (1/1 | Step: 1410 | Loss: 2.127017021179199 | Learning Rate: 1.16775026981486e-05 | Time per step: 0.15108886035621588)
+Epoch... (1/1 | Step: 1420 | Loss: 2.107186794281006 | Learning Rate: 1.154746405518381e-05 | Time per step: 0.1503054445898029)
+Epoch... (1/1 | Step: 1430 | Loss: 2.0433754920959473 | Learning Rate: 1.1417425412219018e-05 | Time per step: 0.14954344509364842)
+Epoch... (1/1 | Step: 1440 | Loss: 2.196624279022217 | Learning Rate: 1.1287385859759524e-05 | Time per step: 0.1489259401957194)
+Epoch... (1/1 | Step: 1450 | Loss: 1.997576117515564 | Learning Rate: 1.1157347216794733e-05 | Time per step: 0.14815782185258536)
+Epoch... (1/1 | Step: 1460 | Loss: 2.0687851905822754 | Learning Rate: 1.1027308573829941e-05 | Time per step: 0.14740191845044698)
+Epoch... (1/1 | Step: 1470 | Loss: 2.0500588417053223 | Learning Rate: 1.089726993086515e-05 | Time per step: 0.14666985038186417)
+Epoch... (1/1 | Step: 1480 | Loss: 2.0253396034240723 | Learning Rate: 1.0767230378405657e-05 | Time per step: 0.14596247012550767)
+Epoch... (1/1 | Step: 1490 | Loss: 2.109578847885132 | Learning Rate: 1.0637191735440865e-05 | Time per step: 0.14524603322048316)
+Epoch... (1/1 | Step: 1500 | Loss: 1.9973983764648438 | Learning Rate: 1.050715127348667e-05 | Time per step: 0.14455435609817505)
+Epoch... (1/1 | Step: 1500 | Eval Loss: 2.0347542762756348 | Eval rouge1: 39.720462 | Eval rouge2: 14.404286 | Eval rougeL: 35.987809 | Eval rougeLsum: 35.987896 | Eval gen_len: 12.283868 |)