Upload 12 files

README.md

@@ -0,0 +1,76 @@
+---
+tags:
+- generated_from_trainer
+datasets:
+- xsum
+metrics:
+- rouge
+model-index:
+- name: small-3-6-t
+  results:
+  - task:
+      name: Summarization
+      type: summarization
+    dataset:
+      name: xsum
+      type: xsum
+      config: default
+      split: validation
+      args: default
+    metrics:
+    - name: Rouge1
+      type: rouge
+      value: 31.7432
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# small-3-6-t
+
+This model is a fine-tuned version of [models/small-3-6](https://huggingface.co/models/small-3-6) on the xsum dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.1322
+- Rouge1: 31.7432
+- Rouge2: 10.077
+- Rougel: 24.8565
+- Rougelsum: 24.8444
+- Gen Len: 28.8587
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 32
+- eval_batch_size: 16
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: constant
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.27.0.dev0
+- Pytorch 1.12.1+cu113
+- Datasets 2.10.0
+- Tokenizers 0.13.2

all_results.json

@@ -0,0 +1,18 @@
+{
+    "epoch": 3.0,
+    "eval_gen_len": 28.858656307936787,
+    "eval_loss": 2.132248878479004,
+    "eval_rouge1": 31.7432,
+    "eval_rouge2": 10.077,
+    "eval_rougeL": 24.8565,
+    "eval_rougeLsum": 24.8444,
+    "eval_runtime": 553.66,
+    "eval_samples": 11327,
+    "eval_samples_per_second": 20.458,
+    "eval_steps_per_second": 1.279,
+    "train_loss": 2.37733912099011,
+    "train_runtime": 8397.5704,
+    "train_samples": 204017,
+    "train_samples_per_second": 72.884,
+    "train_steps_per_second": 1.139
+}

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "models/small-3-6",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "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": 4,
+  "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": "4.27.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32128
+}

eval_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 3.0,
+    "eval_gen_len": 28.858656307936787,
+    "eval_loss": 2.132248878479004,
+    "eval_rouge1": 31.7432,
+    "eval_rouge2": 10.077,
+    "eval_rougeL": 24.8565,
+    "eval_rougeLsum": 24.8444,
+    "eval_runtime": 553.66,
+    "eval_samples": 11327,
+    "eval_samples_per_second": 20.458,
+    "eval_steps_per_second": 1.279
+}

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": "4.27.0.dev0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:682d6e315377557db86cd39f41c08b2f2a3761cecb5e3b5441b3f7afa4bae9ea
+size 270131021

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>"
+  ],
+  "eos_token": "</s>",
+  "extra_ids": 100,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "/home/younes_huggingface_co/.cache/huggingface/hub/models--google--t5-v1_1-small/snapshots/fb7e6cba609f7bab11c614294bc04f82f613c7b1/special_tokens_map.json",
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 2.37733912099011,
+    "train_runtime": 8397.5704,
+    "train_samples": 204017,
+    "train_samples_per_second": 72.884,
+    "train_steps_per_second": 1.139
+}

trainer_state.json

@@ -0,0 +1,139 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 9564,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0001,
+      "loss": 2.5455,
+      "step": 500
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0001,
+      "loss": 2.4773,
+      "step": 1000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0001,
+      "loss": 2.4581,
+      "step": 1500
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0001,
+      "loss": 2.4289,
+      "step": 2000
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0001,
+      "loss": 2.4264,
+      "step": 2500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0001,
+      "loss": 2.4111,
+      "step": 3000
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0001,
+      "loss": 2.3918,
+      "step": 3500
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.0001,
+      "loss": 2.373,
+      "step": 4000
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.0001,
+      "loss": 2.3684,
+      "step": 4500
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 0.0001,
+      "loss": 2.364,
+      "step": 5000
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.0001,
+      "loss": 2.3606,
+      "step": 5500
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 0.0001,
+      "loss": 2.3512,
+      "step": 6000
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 0.0001,
+      "loss": 2.3383,
+      "step": 6500
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 0.0001,
+      "loss": 2.3184,
+      "step": 7000
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 0.0001,
+      "loss": 2.3238,
+      "step": 7500
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 0.0001,
+      "loss": 2.3079,
+      "step": 8000
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 0.0001,
+      "loss": 2.3105,
+      "step": 8500
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 0.0001,
+      "loss": 2.3148,
+      "step": 9000
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 0.0001,
+      "loss": 2.3072,
+      "step": 9500
+    },
+    {
+      "epoch": 3.0,
+      "step": 9564,
+      "total_flos": 1.916909651434537e+17,
+      "train_loss": 2.37733912099011,
+      "train_runtime": 8397.5704,
+      "train_samples_per_second": 72.884,
+      "train_steps_per_second": 1.139
+    }
+  ],
+  "max_steps": 9564,
+  "num_train_epochs": 3,
+  "total_flos": 1.916909651434537e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b06acb0c42c995c39614ca9c1505acc13befd60ef91232c34d33675a0e2843b
+size 3631