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:f7d59d2d8c20fbb9e25e93358a43cf93d24729ad9d23b0c9c0fc9640d0e2df3c
+size 5901652619

over_range.csv

@@ -0,0 +1,100 @@
+,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: []","Empty DataFrame
+Columns: [overall, content, word choice, organization, sentence fluency, conventions, voice]
+Index: []"
+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: []",,,,,,"Empty DataFrame
+Columns: [overall, content, word choice, organization, sentence fluency, conventions, voice]
+Index: []"
+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: []","Empty DataFrame
+Columns: [overall, content, word choice, organization, sentence fluency, conventions, voice]
+Index: []"
+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,,,,,,,,"Empty DataFrame
+Columns: [overall, content, word choice, organization, sentence fluency, conventions, voice]
+Index: []"

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:090d4ddb619a1230b796e80bb3832fe08919a034fa05ec2415fee321c88a01cd
+size 2950848513

qwk_results.csv

@@ -0,0 +1,9 @@
+,overall,content,word choice,organization,sentence fluency,conventions,prompt adherence,language,narrativity,style,voice
+0,0.7402882722712554,0.7049043415693379,0.7096549320320669,0.6805162887405778,0.702025247479793,0.7022492625368733,,,,,
+1,0.640048909720807,0.691350688430076,0.6940098316462722,0.6666666666666666,0.693277457116679,0.7301946295997134,,,,,
+2,0.669036480235492,0.6630663260356369,,,,,0.6632075304252134,0.6675618717245753,0.7174447174447175,,
+3,0.7672283214935713,0.7191552224106801,,,,,0.7173652694610778,0.7055351028775665,0.7389313758088856,,
+4,0.8005657083508275,0.7068504422958239,,,,,0.6942336359940371,0.6828090160496281,0.694375186067282,,
+5,0.7881766578983802,0.78913491246138,,,,,0.731168650271617,0.652810447676935,0.6841252699784017,,
+6,0.8376963254606435,0.8193745367656007,,0.7404570285659862,,0.722254471072781,,,,0.7366060514091572,
+7,0.7105446802062441,0.5844338297274516,0.6287277839140476,0.5909207489099768,0.6335835927485808,0.6539945083682008,,,,,0.59552384041518

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3d52b779ee854e0ed7300e9760a806d45b38ed3731081785b46359c07757499
+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": 0.025496283546090126,
+  "best_model_checkpoint": "./results_pnum/results_cvrev_pnum_f2_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": 0.5836,
+      "step": 500
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 4.8292925142113556e-05,
+      "loss": 0.0329,
+      "step": 1000
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 4.743681939593179e-05,
+      "loss": 0.0314,
+      "step": 1500
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 4.658071364975002e-05,
+      "loss": 0.0309,
+      "step": 2000
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 4.572460790356825e-05,
+      "loss": 0.0287,
+      "step": 2500
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 4.4868502157386485e-05,
+      "loss": 0.0279,
+      "step": 3000
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 4.4012396411204716e-05,
+      "loss": 0.0278,
+      "step": 3500
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 4.3156290665022946e-05,
+      "loss": 0.0267,
+      "step": 4000
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 4.2300184918841177e-05,
+      "loss": 0.0257,
+      "step": 4500
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 4.1444079172659414e-05,
+      "loss": 0.0259,
+      "step": 5000
+    },
+    {
+      "epoch": 2.57,
+      "eval_loss": 0.025496283546090126,
+      "eval_runtime": 103.1414,
+      "eval_samples_per_second": 25.16,
+      "eval_steps_per_second": 6.292,
+      "step": 5000
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 4.058797342647764e-05,
+      "loss": 0.0258,
+      "step": 5500
+    },
+    {
+      "epoch": 3.08,
+      "learning_rate": 3.973186768029587e-05,
+      "loss": 0.0252,
+      "step": 6000
+    },
+    {
+      "epoch": 3.34,
+      "learning_rate": 3.8875761934114105e-05,
+      "loss": 0.024,
+      "step": 6500
+    },
+    {
+      "epoch": 3.6,
+      "learning_rate": 3.8019656187932336e-05,
+      "loss": 0.0241,
+      "step": 7000
+    },
+    {
+      "epoch": 3.85,
+      "learning_rate": 3.7163550441750566e-05,
+      "loss": 0.0239,
+      "step": 7500
+    },
+    {
+      "epoch": 4.11,
+      "learning_rate": 3.63074446955688e-05,
+      "loss": 0.0229,
+      "step": 8000
+    },
+    {
+      "epoch": 4.37,
+      "learning_rate": 3.545133894938703e-05,
+      "loss": 0.0226,
+      "step": 8500
+    },
+    {
+      "epoch": 4.62,
+      "learning_rate": 3.4595233203205265e-05,
+      "loss": 0.0218,
+      "step": 9000
+    },
+    {
+      "epoch": 4.88,
+      "learning_rate": 3.3739127457023495e-05,
+      "loss": 0.0223,
+      "step": 9500
+    },
+    {
+      "epoch": 5.14,
+      "learning_rate": 3.2883021710841726e-05,
+      "loss": 0.0209,
+      "step": 10000
+    },
+    {
+      "epoch": 5.14,
+      "eval_loss": 0.026023680344223976,
+      "eval_runtime": 102.9909,
+      "eval_samples_per_second": 25.196,
+      "eval_steps_per_second": 6.302,
+      "step": 10000
+    },
+    {
+      "epoch": 5.39,
+      "learning_rate": 3.2026915964659956e-05,
+      "loss": 0.02,
+      "step": 10500
+    },
+    {
+      "epoch": 5.65,
+      "learning_rate": 3.117081021847819e-05,
+      "loss": 0.0201,
+      "step": 11000
+    },
+    {
+      "epoch": 5.91,
+      "learning_rate": 3.0314704472296417e-05,
+      "loss": 0.0199,
+      "step": 11500
+    },
+    {
+      "epoch": 6.16,
+      "learning_rate": 2.945859872611465e-05,
+      "loss": 0.0184,
+      "step": 12000
+    },
+    {
+      "epoch": 6.42,
+      "learning_rate": 2.860249297993288e-05,
+      "loss": 0.0179,
+      "step": 12500
+    },
+    {
+      "epoch": 6.68,
+      "learning_rate": 2.7746387233751116e-05,
+      "loss": 0.0183,
+      "step": 13000
+    },
+    {
+      "epoch": 6.93,
+      "learning_rate": 2.6890281487569346e-05,
+      "loss": 0.0184,
+      "step": 13500
+    },
+    {
+      "epoch": 7.19,
+      "learning_rate": 2.603417574138758e-05,
+      "loss": 0.0167,
+      "step": 14000
+    },
+    {
+      "epoch": 7.45,
+      "learning_rate": 2.517806999520581e-05,
+      "loss": 0.0166,
+      "step": 14500
+    },
+    {
+      "epoch": 7.7,
+      "learning_rate": 2.432196424902404e-05,
+      "loss": 0.0162,
+      "step": 15000
+    },
+    {
+      "epoch": 7.7,
+      "eval_loss": 0.030035318806767464,
+      "eval_runtime": 102.9735,
+      "eval_samples_per_second": 25.201,
+      "eval_steps_per_second": 6.303,
+      "step": 15000
+    }
+  ],
+  "max_steps": 29205,
+  "num_train_epochs": 15,
+  "total_flos": 1.29857371766784e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56bf04a344b24f6cfeb676c5ed86b9534d0f196e1587eac182977a93de07a702
+size 4091

val_qwk_results.csv

@@ -0,0 +1,9 @@
+,overall,content,word choice,organization,sentence fluency,conventions,prompt adherence,language,narrativity,style,voice
+0,0.7319376962157165,0.6510793756227168,0.6462127705163916,0.6743870135162671,0.6764420275781704,0.6687748648372949,,,,,
+1,0.6276752883497281,0.6842507791438022,0.7106623050301047,0.672439821496707,0.6965391680348522,0.6857875571339554,,,,,
+2,0.6403470424050846,0.6806406208391982,,,,,0.6723952113250415,0.6763720533593226,0.6971535283165504,,
+3,0.8262208199487174,0.7673786952179018,,,,,0.7726129516709791,0.6717940073327995,0.7658422477462086,,
+4,0.8224260245072855,0.7217141029740965,,,,,0.7299332194013768,0.6843074846963462,0.6989709715303578,,
+5,0.78653254159167,0.8017151384343437,,,,,0.7805809512787871,0.7052817186501974,0.7045943354668187,,
+6,0.7723164954739459,0.7622060555129402,,0.6520865974740961,,0.6711264274613149,,,,0.6848955100351748,
+7,0.7633936525054068,0.7111663727368461,0.7334073178407566,0.697567575185321,0.6750076757752533,0.6770910658269678,,,,,0.7114746849436215