End of training

README.md

@@ -3,6 +3,8 @@ license: apache-2.0
 base_model: google/flan-t5-small
 tags:
 - generated_from_trainer
+metrics:
+- rouge
 model-index:
 - name: results
   results: []
@@ -14,6 +16,12 @@ should probably proofread and complete it, then remove this comment. -->
 # results
 
 This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.5487
+- Rouge1: 0.3047
+- Rouge2: 0.1253
+- Rougel: 0.2752
+- Rougelsum: 0.2813
 
 ## Model description
 
@@ -32,22 +40,26 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0002
-- train_batch_size: 4
-- eval_batch_size: 8
+- learning_rate: 0.0003
+- train_batch_size: 8
+- eval_batch_size: 4
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: constant
-- lr_scheduler_warmup_ratio: 0.03
-- num_epochs: 1
+- lr_scheduler_type: linear
+- num_epochs: 3
 
 ### Training results
 
+| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
+| No log        | 1.0   | 4    | 2.8586          | 0.2445 | 0.0844 | 0.2195 | 0.2220    |
+| No log        | 2.0   | 8    | 2.6345          | 0.2824 | 0.1235 | 0.2586 | 0.2601    |
+| No log        | 3.0   | 12   | 2.5487          | 0.3047 | 0.1253 | 0.2752 | 0.2813    |
 
 
 ### Framework versions
 
 - Transformers 4.35.2
-- Pytorch 2.0.1
-- Datasets 2.14.7
+- Pytorch 2.1.0+cu121
+- Datasets 2.15.0
 - Tokenizers 0.15.0

added_tokens.json

@@ -0,0 +1,102 @@
+{
+  "<extra_id_0>": 32099,
+  "<extra_id_10>": 32089,
+  "<extra_id_11>": 32088,
+  "<extra_id_12>": 32087,
+  "<extra_id_13>": 32086,
+  "<extra_id_14>": 32085,
+  "<extra_id_15>": 32084,
+  "<extra_id_16>": 32083,
+  "<extra_id_17>": 32082,
+  "<extra_id_18>": 32081,
+  "<extra_id_19>": 32080,
+  "<extra_id_1>": 32098,
+  "<extra_id_20>": 32079,
+  "<extra_id_21>": 32078,
+  "<extra_id_22>": 32077,
+  "<extra_id_23>": 32076,
+  "<extra_id_24>": 32075,
+  "<extra_id_25>": 32074,
+  "<extra_id_26>": 32073,
+  "<extra_id_27>": 32072,
+  "<extra_id_28>": 32071,
+  "<extra_id_29>": 32070,
+  "<extra_id_2>": 32097,
+  "<extra_id_30>": 32069,
+  "<extra_id_31>": 32068,
+  "<extra_id_32>": 32067,
+  "<extra_id_33>": 32066,
+  "<extra_id_34>": 32065,
+  "<extra_id_35>": 32064,
+  "<extra_id_36>": 32063,
+  "<extra_id_37>": 32062,
+  "<extra_id_38>": 32061,
+  "<extra_id_39>": 32060,
+  "<extra_id_3>": 32096,
+  "<extra_id_40>": 32059,
+  "<extra_id_41>": 32058,
+  "<extra_id_42>": 32057,
+  "<extra_id_43>": 32056,
+  "<extra_id_44>": 32055,
+  "<extra_id_45>": 32054,
+  "<extra_id_46>": 32053,
+  "<extra_id_47>": 32052,
+  "<extra_id_48>": 32051,
+  "<extra_id_49>": 32050,
+  "<extra_id_4>": 32095,
+  "<extra_id_50>": 32049,
+  "<extra_id_51>": 32048,
+  "<extra_id_52>": 32047,
+  "<extra_id_53>": 32046,
+  "<extra_id_54>": 32045,
+  "<extra_id_55>": 32044,
+  "<extra_id_56>": 32043,
+  "<extra_id_57>": 32042,
+  "<extra_id_58>": 32041,
+  "<extra_id_59>": 32040,
+  "<extra_id_5>": 32094,
+  "<extra_id_60>": 32039,
+  "<extra_id_61>": 32038,
+  "<extra_id_62>": 32037,
+  "<extra_id_63>": 32036,
+  "<extra_id_64>": 32035,
+  "<extra_id_65>": 32034,
+  "<extra_id_66>": 32033,
+  "<extra_id_67>": 32032,
+  "<extra_id_68>": 32031,
+  "<extra_id_69>": 32030,
+  "<extra_id_6>": 32093,
+  "<extra_id_70>": 32029,
+  "<extra_id_71>": 32028,
+  "<extra_id_72>": 32027,
+  "<extra_id_73>": 32026,
+  "<extra_id_74>": 32025,
+  "<extra_id_75>": 32024,
+  "<extra_id_76>": 32023,
+  "<extra_id_77>": 32022,
+  "<extra_id_78>": 32021,
+  "<extra_id_79>": 32020,
+  "<extra_id_7>": 32092,
+  "<extra_id_80>": 32019,
+  "<extra_id_81>": 32018,
+  "<extra_id_82>": 32017,
+  "<extra_id_83>": 32016,
+  "<extra_id_84>": 32015,
+  "<extra_id_85>": 32014,
+  "<extra_id_86>": 32013,
+  "<extra_id_87>": 32012,
+  "<extra_id_88>": 32011,
+  "<extra_id_89>": 32010,
+  "<extra_id_8>": 32091,
+  "<extra_id_90>": 32009,
+  "<extra_id_91>": 32008,
+  "<extra_id_92>": 32007,
+  "<extra_id_93>": 32006,
+  "<extra_id_94>": 32005,
+  "<extra_id_95>": 32004,
+  "<extra_id_96>": 32003,
+  "<extra_id_97>": 32002,
+  "<extra_id_98>": 32001,
+  "<extra_id_99>": 32000,
+  "<extra_id_9>": 32090
+}

config.json

@@ -0,0 +1,62 @@
+{
+  "_name_or_path": "google/flan-t5-small",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 1024,
+  "d_kv": 64,
+  "d_model": 512,
+  "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": 8,
+  "num_heads": 6,
+  "num_layers": 8,
+  "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": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 32128
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.35.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:712f1f9532790051adcffdd8e10459af24d7a5cfeb0781706f468ee2466ef0b6
+size 307867048

runs/Dec18_06-17-07_9cab81f7dbfc/events.out.tfevents.1702880266.9cab81f7dbfc.7859.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b16f633922c8287212dbae3b5f30ecfbd2316a660176a9df1c7d45be3d873cc1
+size 5225

runs/Dec18_06-24-25_9cab81f7dbfc/events.out.tfevents.1702881234.9cab81f7dbfc.9906.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e453ffbba5e868c5215a7668d71d68e1f043d2a4a52c3ddb9815d1d699ccda1
+size 6968

runs/Dec18_06-24-25_9cab81f7dbfc/events.out.tfevents.1702882134.9cab81f7dbfc.9906.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b54eea59daba4c9346614b81679c4006a27dd9dc7d2b6cdbbe5294ac8be81a6e
+size 6968

runs/Dec18_07-03-47_9cab81f7dbfc/events.out.tfevents.1702883028.9cab81f7dbfc.19978.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a9518563d614974c5ea53783bced3b67046aaaa144f5d20e839b0a76bce75b6
+size 6968

special_tokens_map.json

@@ -101,7 +101,25 @@
     "<extra_id_98>",
     "<extra_id_99>"
   ],
-  "eos_token": "</s>",
-  "pad_token": "<pad>",
-  "unk_token": "<unk>"
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

spiece.model

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

tokenizer_config.json

@@ -930,6 +930,7 @@
   "clean_up_tokenization_spaces": true,
   "eos_token": "</s>",
   "extra_ids": 100,
+  "legacy": true,
   "model_max_length": 512,
   "pad_token": "<pad>",
   "sp_model_kwargs": {},

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73e425b966d0ca2472c8da2095a4bb20471ffc0eadd2b24adabc19a3f94eca5d
-size 4155
+oid sha256:cdb13061f50f5890c07462d0240bff4d41e9248346cecd86a92a966b742d4a22
+size 4728