Upload 21 files

README.md

@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # flan-t5-base-v3-edos_labelled_aggregated
 
-This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the edos_labelled_aggregated dataset.
+This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the None dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.0663
 - Rouge1: 95.8792

checkpoint-3500/config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "google/flan-t5-base",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "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: "
+    }
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "use_cache": true,
+  "vocab_size": 32128
+}

checkpoint-3500/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.28.1"
+}

checkpoint-3500/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87d76f223d8721eda626a3fa58094a04c865e7bf08356a009b63612e3829a9fb
+size 990408885

checkpoint-3500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f6840049ad02450cf7067d9046d905b794a36a950f4196d0466576c651ddd53
+size 14575

checkpoint-3500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1de04677ba3545f6935a7d0edc59f7e0b081085364220619d9ec4019da24cd6d
+size 627

checkpoint-3500/trainer_state.json

@@ -0,0 +1,84 @@
+{
+  "best_metric": 0.06633109599351883,
+  "best_model_checkpoint": "flan-t5-base-v3-edos_labelled_aggregated/checkpoint-3500",
+  "epoch": 2.0,
+  "global_step": 3500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.714285714285714e-05,
+      "loss": 0.1362,
+      "step": 500
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 4.428571428571428e-05,
+      "loss": 0.09,
+      "step": 1000
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 4.1428571428571437e-05,
+      "loss": 0.0822,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_gen_len": 4.805,
+      "eval_loss": 0.06878727674484253,
+      "eval_rouge1": 95.8375,
+      "eval_rouge2": 71.9,
+      "eval_rougeL": 95.8417,
+      "eval_rougeLsum": 95.8333,
+      "eval_runtime": 126.0351,
+      "eval_samples_per_second": 31.737,
+      "eval_steps_per_second": 3.967,
+      "step": 1750
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 3.857142857142858e-05,
+      "loss": 0.0751,
+      "step": 2000
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 3.571428571428572e-05,
+      "loss": 0.068,
+      "step": 2500
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 3.285714285714286e-05,
+      "loss": 0.073,
+      "step": 3000
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3e-05,
+      "loss": 0.0663,
+      "step": 3500
+    },
+    {
+      "epoch": 2.0,
+      "eval_gen_len": 4.79025,
+      "eval_loss": 0.06633109599351883,
+      "eval_rouge1": 95.8792,
+      "eval_rouge2": 71.25,
+      "eval_rougeL": 95.875,
+      "eval_rougeLsum": 95.8792,
+      "eval_runtime": 124.8268,
+      "eval_samples_per_second": 32.044,
+      "eval_steps_per_second": 4.006,
+      "step": 3500
+    }
+  ],
+  "max_steps": 8750,
+  "num_train_epochs": 5,
+  "total_flos": 4793301467136000.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:581c119e3527f4af0b25fea695de03109e935b7927b531ddaeeab2cfb7f64ac0
+size 3835

checkpoint-8750/config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "google/flan-t5-base",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "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: "
+    }
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "use_cache": true,
+  "vocab_size": 32128
+}

checkpoint-8750/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.28.1"
+}

checkpoint-8750/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d05db1aa0bf4b3c8fa51992efa3454de2ee6cd052840b6330399c36ca7cd39ff
+size 990408885

checkpoint-8750/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60aa8cadb9eef388673b821a5e3029dfeb80920b05980b74f7c967cbb2e6a007
+size 14575

checkpoint-8750/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b771940e016e1c16a81be6efaaaeac336f8cf4b60dc25c036092f77daa417829
+size 627

checkpoint-8750/trainer_state.json

@@ -0,0 +1,183 @@
+{
+  "best_metric": 0.06633109599351883,
+  "best_model_checkpoint": "flan-t5-base-v3-edos_labelled_aggregated/checkpoint-3500",
+  "epoch": 5.0,
+  "global_step": 8750,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.714285714285714e-05,
+      "loss": 0.1362,
+      "step": 500
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 4.428571428571428e-05,
+      "loss": 0.09,
+      "step": 1000
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 4.1428571428571437e-05,
+      "loss": 0.0822,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_gen_len": 4.805,
+      "eval_loss": 0.06878727674484253,
+      "eval_rouge1": 95.8375,
+      "eval_rouge2": 71.9,
+      "eval_rougeL": 95.8417,
+      "eval_rougeLsum": 95.8333,
+      "eval_runtime": 126.0351,
+      "eval_samples_per_second": 31.737,
+      "eval_steps_per_second": 3.967,
+      "step": 1750
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 3.857142857142858e-05,
+      "loss": 0.0751,
+      "step": 2000
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 3.571428571428572e-05,
+      "loss": 0.068,
+      "step": 2500
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 3.285714285714286e-05,
+      "loss": 0.073,
+      "step": 3000
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3e-05,
+      "loss": 0.0663,
+      "step": 3500
+    },
+    {
+      "epoch": 2.0,
+      "eval_gen_len": 4.79025,
+      "eval_loss": 0.06633109599351883,
+      "eval_rouge1": 95.8792,
+      "eval_rouge2": 71.25,
+      "eval_rougeL": 95.875,
+      "eval_rougeLsum": 95.8792,
+      "eval_runtime": 124.8268,
+      "eval_samples_per_second": 32.044,
+      "eval_steps_per_second": 4.006,
+      "step": 3500
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 2.714285714285714e-05,
+      "loss": 0.0571,
+      "step": 4000
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 2.4285714285714288e-05,
+      "loss": 0.058,
+      "step": 4500
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 2.1428571428571428e-05,
+      "loss": 0.0536,
+      "step": 5000
+    },
+    {
+      "epoch": 3.0,
+      "eval_gen_len": 4.758,
+      "eval_loss": 0.07638958841562271,
+      "eval_rouge1": 95.65,
+      "eval_rouge2": 69.3,
+      "eval_rougeL": 95.65,
+      "eval_rougeLsum": 95.6667,
+      "eval_runtime": 124.7009,
+      "eval_samples_per_second": 32.077,
+      "eval_steps_per_second": 4.01,
+      "step": 5250
+    },
+    {
+      "epoch": 3.14,
+      "learning_rate": 1.8571428571428572e-05,
+      "loss": 0.0552,
+      "step": 5500
+    },
+    {
+      "epoch": 3.43,
+      "learning_rate": 1.5714285714285715e-05,
+      "loss": 0.049,
+      "step": 6000
+    },
+    {
+      "epoch": 3.71,
+      "learning_rate": 1.2857142857142857e-05,
+      "loss": 0.0468,
+      "step": 6500
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1e-05,
+      "loss": 0.0486,
+      "step": 7000
+    },
+    {
+      "epoch": 4.0,
+      "eval_gen_len": 4.76575,
+      "eval_loss": 0.08493922650814056,
+      "eval_rouge1": 95.8333,
+      "eval_rouge2": 69.925,
+      "eval_rougeL": 95.8167,
+      "eval_rougeLsum": 95.8333,
+      "eval_runtime": 124.2728,
+      "eval_samples_per_second": 32.187,
+      "eval_steps_per_second": 4.023,
+      "step": 7000
+    },
+    {
+      "epoch": 4.29,
+      "learning_rate": 7.142857142857143e-06,
+      "loss": 0.0429,
+      "step": 7500
+    },
+    {
+      "epoch": 4.57,
+      "learning_rate": 4.285714285714286e-06,
+      "loss": 0.043,
+      "step": 8000
+    },
+    {
+      "epoch": 4.86,
+      "learning_rate": 1.4285714285714286e-06,
+      "loss": 0.0467,
+      "step": 8500
+    },
+    {
+      "epoch": 5.0,
+      "eval_gen_len": 4.7635,
+      "eval_loss": 0.09458264708518982,
+      "eval_rouge1": 95.825,
+      "eval_rouge2": 69.8,
+      "eval_rougeL": 95.8083,
+      "eval_rougeLsum": 95.825,
+      "eval_runtime": 124.9433,
+      "eval_samples_per_second": 32.015,
+      "eval_steps_per_second": 4.002,
+      "step": 8750
+    }
+  ],
+  "max_steps": 8750,
+  "num_train_epochs": 5,
+  "total_flos": 1.198325366784e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-8750/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:581c119e3527f4af0b25fea695de03109e935b7927b531ddaeeab2cfb7f64ac0
+size 3835

logs/1682836817.3577423/events.out.tfevents.1682836817.48ced680e174.463.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5de8cf4176e18ad74ad7540f54ce5a5348e857d38310de0ba2e8390184be47e0
+size 6237

logs/events.out.tfevents.1682836817.48ced680e174.463.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7476736490444de072527412574d1be147e73bcb7fdb2d2bdc1d4ad98f6e511
+size 10729

logs/events.out.tfevents.1682840403.48ced680e174.463.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a6a1b539fba93eb34be4ba522bd50a31c9db88d81cb5f29a3f9b0d1facde7bc
+size 613

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>"
+}

tokenizer_config.json

@@ -0,0 +1,112 @@
+{
+  "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,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}