Upload model checkpoint

config.json

@@ -0,0 +1,60 @@
+{
+  "_name_or_path": "t5-large",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 4096,
+  "d_kv": 64,
+  "d_model": 1024,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "relu",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": false,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 24,
+  "num_heads": 16,
+  "num_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0",
+  "use_cache": true,
+  "vocab_size": 32128
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.31.0"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fda15d26f36b89853dffd2a4d4b7cc91af363f7be3ca26e7e127a91dc673feb4
+size 5901652619

over_range.csv

@@ -0,0 +1,104 @@
+,1,2,3,4,5,6,7,8
+overall,"Empty DataFrame
+Columns: [overall, content, word choice, organization, sentence fluency, conventions]
+Index: []","Empty DataFrame
+Columns: [overall, content, word choice, organization, sentence fluency, conventions]
+Index: []","Empty DataFrame
+Columns: [overall, content, prompt adherence, language, narrativity]
+Index: []","Empty DataFrame
+Columns: [overall, content, prompt adherence, language, narrativity]
+Index: []","Empty DataFrame
+Columns: [overall, content, prompt adherence, language, narrativity]
+Index: []","Empty DataFrame
+Columns: [overall, content, prompt adherence, language, narrativity]
+Index: []","Empty DataFrame
+Columns: [overall, content, organization, conventions, style]
+Index: []","Empty DataFrame
+Columns: [overall, content, word choice, organization, sentence fluency, conventions, voice]
+Index: []"
+content,"Empty DataFrame
+Columns: [overall, content, word choice, organization, sentence fluency, conventions]
+Index: []","Empty DataFrame
+Columns: [overall, content, word choice, organization, sentence fluency, conventions]
+Index: []","Empty DataFrame
+Columns: [overall, content, prompt adherence, language, narrativity]
+Index: []","Empty DataFrame
+Columns: [overall, content, prompt adherence, language, narrativity]
+Index: []","Empty DataFrame
+Columns: [overall, content, prompt adherence, language, narrativity]
+Index: []","Empty DataFrame
+Columns: [overall, content, prompt adherence, language, narrativity]
+Index: []","Empty DataFrame
+Columns: [overall, content, organization, conventions, style]
+Index: []","     overall  content  word choice  ...  sentence fluency  conventions  voice
+117      8.0      1.0          1.0  ...               2.0          2.0    1.0
+
+[1 rows x 7 columns]"
+word choice,"Empty DataFrame
+Columns: [overall, content, word choice, organization, sentence fluency, conventions]
+Index: []","Empty DataFrame
+Columns: [overall, content, word choice, organization, sentence fluency, conventions]
+Index: []",,,,,,"     overall  content  word choice  ...  sentence fluency  conventions  voice
+117      8.0      1.0          1.0  ...               2.0          2.0    1.0
+
+[1 rows x 7 columns]"
+organization,"Empty DataFrame
+Columns: [overall, content, word choice, organization, sentence fluency, conventions]
+Index: []","Empty DataFrame
+Columns: [overall, content, word choice, organization, sentence fluency, conventions]
+Index: []",,,,,"Empty DataFrame
+Columns: [overall, content, organization, conventions, style]
+Index: []","     overall  content  word choice  ...  sentence fluency  conventions  voice
+117      8.0      1.0          1.0  ...               2.0          2.0    1.0
+
+[1 rows x 7 columns]"
+sentence fluency,"Empty DataFrame
+Columns: [overall, content, word choice, organization, sentence fluency, conventions]
+Index: []","Empty DataFrame
+Columns: [overall, content, word choice, organization, sentence fluency, conventions]
+Index: []",,,,,,"Empty DataFrame
+Columns: [overall, content, word choice, organization, sentence fluency, conventions, voice]
+Index: []"
+conventions,"Empty DataFrame
+Columns: [overall, content, word choice, organization, sentence fluency, conventions]
+Index: []","Empty DataFrame
+Columns: [overall, content, word choice, organization, sentence fluency, conventions]
+Index: []",,,,,"Empty DataFrame
+Columns: [overall, content, organization, conventions, style]
+Index: []","Empty DataFrame
+Columns: [overall, content, word choice, organization, sentence fluency, conventions, voice]
+Index: []"
+prompt adherence,,,"Empty DataFrame
+Columns: [overall, content, prompt adherence, language, narrativity]
+Index: []","Empty DataFrame
+Columns: [overall, content, prompt adherence, language, narrativity]
+Index: []","Empty DataFrame
+Columns: [overall, content, prompt adherence, language, narrativity]
+Index: []","Empty DataFrame
+Columns: [overall, content, prompt adherence, language, narrativity]
+Index: []",,
+language,,,"Empty DataFrame
+Columns: [overall, content, prompt adherence, language, narrativity]
+Index: []","Empty DataFrame
+Columns: [overall, content, prompt adherence, language, narrativity]
+Index: []","Empty DataFrame
+Columns: [overall, content, prompt adherence, language, narrativity]
+Index: []","Empty DataFrame
+Columns: [overall, content, prompt adherence, language, narrativity]
+Index: []",,
+narrativity,,,"Empty DataFrame
+Columns: [overall, content, prompt adherence, language, narrativity]
+Index: []","Empty DataFrame
+Columns: [overall, content, prompt adherence, language, narrativity]
+Index: []","Empty DataFrame
+Columns: [overall, content, prompt adherence, language, narrativity]
+Index: []","Empty DataFrame
+Columns: [overall, content, prompt adherence, language, narrativity]
+Index: []",,
+style,,,,,,,"Empty DataFrame
+Columns: [overall, content, organization, conventions, style]
+Index: []",
+voice,,,,,,,,"     overall  content  word choice  ...  sentence fluency  conventions  voice
+117      8.0      1.0          1.0  ...               2.0          2.0    1.0
+
+[1 rows x 7 columns]"

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e668d5d6eb22e4ae8f2610e3ec6a4db85cf47e9fd5a2e7ed9c4938274fc90c7b
+size 2950848513

qwk_results.csv

@@ -0,0 +1,9 @@
+,overall,content,word choice,organization,sentence fluency,conventions,prompt adherence,language,narrativity,style,voice
+0,0.7882358030744383,0.7224408792235082,0.6867107266375085,0.6944918760011969,0.6929368290162699,0.6777347286091899,,,,,
+1,0.6077981651376146,0.7127554202281816,0.730915810139739,0.7142399897577058,0.7353018641538146,0.7416495799986772,,,,,
+2,0.6578881685903359,0.6751647714927211,,,,,0.6889805313129376,0.6573551412443583,0.692497658179341,,
+3,0.7774712902499437,0.7935640403524453,,,,,0.7954026008143964,0.7160884342295656,0.7873158539809185,,
+4,0.8005118808713608,0.7015240737508384,,,,,0.666681048616744,0.602433382338218,0.6337069584463209,,
+5,0.8262346368715083,0.8075515563783527,,,,,0.7911200807265388,0.7152016546018614,0.7390001728475677,,
+6,0.8172503038592347,0.7919180917983687,,0.7419367771162828,,0.6817016997534708,,,,0.7221037152686376,
+7,0.6649163232696997,0.5437933207309389,0.6232831916285154,0.5108695652173914,0.6555740432612311,0.5841239109390126,,,,,0.5254782189358624

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6773c7d4129261a3e4ce3b88ca747d43b130df52ba74a4df5391bc5cb58e102
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcc2b6538cea87c6208096fd7d0d88f00a38709d20f410a6c362f712955eefae
+size 627

special_tokens_map.json

@@ -0,0 +1,107 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
+size 791656

tokenizer_config.json

@@ -0,0 +1,113 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 100,
+  "legacy": true,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,220 @@
+{
+  "best_metric": 0.02520456165075302,
+  "best_model_checkpoint": "./results_pnum/results_cvrev_pnum_f3_large_b4e15_5000/checkpoint-5000",
+  "epoch": 7.704160246533128,
+  "global_step": 15000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.914903088829532e-05,
+      "loss": 0.5561,
+      "step": 500
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 4.8292925142113556e-05,
+      "loss": 0.0339,
+      "step": 1000
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 4.743681939593179e-05,
+      "loss": 0.0311,
+      "step": 1500
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 4.658071364975002e-05,
+      "loss": 0.0297,
+      "step": 2000
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 4.572460790356825e-05,
+      "loss": 0.0287,
+      "step": 2500
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 4.4868502157386485e-05,
+      "loss": 0.0285,
+      "step": 3000
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 4.4012396411204716e-05,
+      "loss": 0.0278,
+      "step": 3500
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 4.3156290665022946e-05,
+      "loss": 0.0272,
+      "step": 4000
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 4.2300184918841177e-05,
+      "loss": 0.026,
+      "step": 4500
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 4.1444079172659414e-05,
+      "loss": 0.0259,
+      "step": 5000
+    },
+    {
+      "epoch": 2.57,
+      "eval_loss": 0.02520456165075302,
+      "eval_runtime": 103.0087,
+      "eval_samples_per_second": 25.192,
+      "eval_steps_per_second": 6.3,
+      "step": 5000
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 4.058797342647764e-05,
+      "loss": 0.0259,
+      "step": 5500
+    },
+    {
+      "epoch": 3.08,
+      "learning_rate": 3.973186768029587e-05,
+      "loss": 0.0251,
+      "step": 6000
+    },
+    {
+      "epoch": 3.34,
+      "learning_rate": 3.8875761934114105e-05,
+      "loss": 0.0247,
+      "step": 6500
+    },
+    {
+      "epoch": 3.6,
+      "learning_rate": 3.8019656187932336e-05,
+      "loss": 0.0243,
+      "step": 7000
+    },
+    {
+      "epoch": 3.85,
+      "learning_rate": 3.7163550441750566e-05,
+      "loss": 0.0242,
+      "step": 7500
+    },
+    {
+      "epoch": 4.11,
+      "learning_rate": 3.63074446955688e-05,
+      "loss": 0.023,
+      "step": 8000
+    },
+    {
+      "epoch": 4.37,
+      "learning_rate": 3.545133894938703e-05,
+      "loss": 0.0227,
+      "step": 8500
+    },
+    {
+      "epoch": 4.62,
+      "learning_rate": 3.4595233203205265e-05,
+      "loss": 0.0226,
+      "step": 9000
+    },
+    {
+      "epoch": 4.88,
+      "learning_rate": 3.3739127457023495e-05,
+      "loss": 0.0228,
+      "step": 9500
+    },
+    {
+      "epoch": 5.14,
+      "learning_rate": 3.2883021710841726e-05,
+      "loss": 0.021,
+      "step": 10000
+    },
+    {
+      "epoch": 5.14,
+      "eval_loss": 0.026348939165472984,
+      "eval_runtime": 102.8144,
+      "eval_samples_per_second": 25.24,
+      "eval_steps_per_second": 6.312,
+      "step": 10000
+    },
+    {
+      "epoch": 5.39,
+      "learning_rate": 3.2026915964659956e-05,
+      "loss": 0.0206,
+      "step": 10500
+    },
+    {
+      "epoch": 5.65,
+      "learning_rate": 3.117081021847819e-05,
+      "loss": 0.0208,
+      "step": 11000
+    },
+    {
+      "epoch": 5.91,
+      "learning_rate": 3.0314704472296417e-05,
+      "loss": 0.0204,
+      "step": 11500
+    },
+    {
+      "epoch": 6.16,
+      "learning_rate": 2.945859872611465e-05,
+      "loss": 0.0191,
+      "step": 12000
+    },
+    {
+      "epoch": 6.42,
+      "learning_rate": 2.860249297993288e-05,
+      "loss": 0.019,
+      "step": 12500
+    },
+    {
+      "epoch": 6.68,
+      "learning_rate": 2.7746387233751116e-05,
+      "loss": 0.0191,
+      "step": 13000
+    },
+    {
+      "epoch": 6.93,
+      "learning_rate": 2.6890281487569346e-05,
+      "loss": 0.0179,
+      "step": 13500
+    },
+    {
+      "epoch": 7.19,
+      "learning_rate": 2.603417574138758e-05,
+      "loss": 0.0165,
+      "step": 14000
+    },
+    {
+      "epoch": 7.45,
+      "learning_rate": 2.517806999520581e-05,
+      "loss": 0.0172,
+      "step": 14500
+    },
+    {
+      "epoch": 7.7,
+      "learning_rate": 2.432196424902404e-05,
+      "loss": 0.0164,
+      "step": 15000
+    },
+    {
+      "epoch": 7.7,
+      "eval_loss": 0.029481180012226105,
+      "eval_runtime": 102.7986,
+      "eval_samples_per_second": 25.244,
+      "eval_steps_per_second": 6.313,
+      "step": 15000
+    }
+  ],
+  "max_steps": 29205,
+  "num_train_epochs": 15,
+  "total_flos": 1.29872527097856e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68e1993aee22ac51d886a0ae0ac2fe476ee74ea029346bbd158a1955ac2f11bb
+size 4091

val_qwk_results.csv

@@ -0,0 +1,9 @@
+,overall,content,word choice,organization,sentence fluency,conventions,prompt adherence,language,narrativity,style,voice
+0,0.7664640745982849,0.7260191696488901,0.728222861640495,0.6831091116143531,0.7113127630837017,0.7084964187767926,,,,,
+1,0.6385943939346274,0.6795389272684933,0.7136752690960966,0.6770601336302895,0.7202820400070973,0.7300356939912279,,,,,
+2,0.7106974224011147,0.7076546464551361,,,,,0.7113929908455008,0.7272382277600329,0.735724936409087,,
+3,0.7761037465162438,0.7658311581506776,,,,,0.7805996439788624,0.720881245899375,0.7810652351384113,,
+4,0.7973124719269351,0.6885886812760671,,,,,0.6642306670209939,0.6577171127362166,0.6805129962809304,,
+5,0.8124205171682917,0.80755873340143,,,,,0.767334771333705,0.6967006356573504,0.6807225450152448,,
+6,0.8133444853874663,0.8010320081410613,,0.7343387184427647,,0.7329616850523801,,,,0.7025229375830431,
+7,0.6914997658079627,0.5880614171935298,0.5608600161831001,0.608868279081045,0.6624338624338624,0.608656537385046,,,,,0.5904805415957137