commit files to HF hub

README.md

@@ -0,0 +1,59 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+model-index:
+- name: T5-summarizer-simple-wiki-v2
+  results: []
+---
+
+<!-- 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. -->
+
+# T5-summarizer-simple-wiki-v2
+
+This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.0866
+
+## 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: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 2.2575        | 1.0   | 14719 | 2.1173          |
+| 2.2663        | 2.0   | 29438 | 2.0926          |
+| 2.2092        | 3.0   | 44157 | 2.0866          |
+
+
+### Framework versions
+
+- Transformers 4.19.4
+- Pytorch 1.11.0
+- Datasets 2.3.2
+- Tokenizers 0.12.1

checkpoint-44157/config.json

@@ -0,0 +1,58 @@
+{
+  "_name_or_path": "t5-small",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 512,
+  "decoder_start_token_id": 0,
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 6,
+  "num_heads": 8,
+  "num_layers": 6,
+  "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": "4.19.4",
+  "use_cache": true,
+  "vocab_size": 32128
+}

checkpoint-44157/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68236975bc40f15fb38db62b9605c70f244dd8379418c3a60b1abcb42334a498
+size 484129461

checkpoint-44157/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4bef3500b6c1bc07cbe61e7ee9dcfcbfb8fafa58569407cf92d710ecd195f76
+size 242070267

checkpoint-44157/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f962e4fa63ae56391ee77c540393187112e19b3eeba9c290efc0eccadaaa76a4
+size 14503

checkpoint-44157/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82f5ed4bbb2b39f09f1524e3a2a42c673003ef4cc95a9994334fd5cfdc5bee26
+size 559

checkpoint-44157/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24f2c79808aaac618cc62090db498fee204b96e3b2affe929402215c3c0a504b
+size 623

checkpoint-44157/special_tokens_map.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "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>"]}

checkpoint-44157/spiece.model

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

checkpoint-44157/tokenizer_config.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "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>"], "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "t5-small", "tokenizer_class": "T5Tokenizer"}

checkpoint-44157/trainer_state.json

@@ -0,0 +1,568 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 44157,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.9774441198450984e-05,
+      "loss": 2.4542,
+      "step": 500
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9547976538261206e-05,
+      "loss": 2.4106,
+      "step": 1000
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9321511878071427e-05,
+      "loss": 2.4207,
+      "step": 1500
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.909595307652241e-05,
+      "loss": 2.3664,
+      "step": 2000
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.8869488416332635e-05,
+      "loss": 2.3553,
+      "step": 2500
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8643023756142857e-05,
+      "loss": 2.3541,
+      "step": 3000
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.841655909595308e-05,
+      "loss": 2.3494,
+      "step": 3500
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.81900944357633e-05,
+      "loss": 2.3592,
+      "step": 4000
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.7963629775573522e-05,
+      "loss": 2.3452,
+      "step": 4500
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.7737165115383744e-05,
+      "loss": 2.32,
+      "step": 5000
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.7510700455193966e-05,
+      "loss": 2.2992,
+      "step": 5500
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.728423579500419e-05,
+      "loss": 2.3109,
+      "step": 6000
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.7057771134814413e-05,
+      "loss": 2.3008,
+      "step": 6500
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.6831306474624635e-05,
+      "loss": 2.3091,
+      "step": 7000
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.6604841814434857e-05,
+      "loss": 2.3252,
+      "step": 7500
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.6378377154245082e-05,
+      "loss": 2.2909,
+      "step": 8000
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.6151912494055304e-05,
+      "loss": 2.3015,
+      "step": 8500
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.5925900763185907e-05,
+      "loss": 2.2997,
+      "step": 9000
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.569943610299613e-05,
+      "loss": 2.283,
+      "step": 9500
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.547297144280635e-05,
+      "loss": 2.2826,
+      "step": 10000
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.5246506782616575e-05,
+      "loss": 2.2771,
+      "step": 10500
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.5020042122426796e-05,
+      "loss": 2.2991,
+      "step": 11000
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.4794030391557398e-05,
+      "loss": 2.3035,
+      "step": 11500
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.456756573136762e-05,
+      "loss": 2.2715,
+      "step": 12000
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.4341101071177844e-05,
+      "loss": 2.2736,
+      "step": 12500
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.4114636410988067e-05,
+      "loss": 2.2883,
+      "step": 13000
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.388862468011867e-05,
+      "loss": 2.2545,
+      "step": 13500
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.3662160019928891e-05,
+      "loss": 2.2956,
+      "step": 14000
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.3435695359739113e-05,
+      "loss": 2.2575,
+      "step": 14500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.1173367500305176,
+      "eval_runtime": 371.7904,
+      "eval_samples_per_second": 158.353,
+      "eval_steps_per_second": 9.898,
+      "step": 14719
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.3209230699549337e-05,
+      "loss": 2.2485,
+      "step": 15000
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 1.298276603935956e-05,
+      "loss": 2.2548,
+      "step": 15500
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1.2756301379169782e-05,
+      "loss": 2.242,
+      "step": 16000
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 1.2529836718980004e-05,
+      "loss": 2.2797,
+      "step": 16500
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.2303824988110606e-05,
+      "loss": 2.264,
+      "step": 17000
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.207781325724121e-05,
+      "loss": 2.2747,
+      "step": 17500
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.1851348597051431e-05,
+      "loss": 2.2776,
+      "step": 18000
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.1624883936861653e-05,
+      "loss": 2.2696,
+      "step": 18500
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.1398419276671877e-05,
+      "loss": 2.2436,
+      "step": 19000
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.1171954616482099e-05,
+      "loss": 2.2563,
+      "step": 19500
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.094548995629232e-05,
+      "loss": 2.266,
+      "step": 20000
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 1.0719478225422924e-05,
+      "loss": 2.2696,
+      "step": 20500
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.0493013565233146e-05,
+      "loss": 2.2423,
+      "step": 21000
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.026654890504337e-05,
+      "loss": 2.2411,
+      "step": 21500
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.0040084244853591e-05,
+      "loss": 2.2564,
+      "step": 22000
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 9.813619584663813e-06,
+      "loss": 2.2632,
+      "step": 22500
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 9.587154924474037e-06,
+      "loss": 2.2656,
+      "step": 23000
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 9.360690264284259e-06,
+      "loss": 2.2667,
+      "step": 23500
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 9.134225604094482e-06,
+      "loss": 2.2622,
+      "step": 24000
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 8.907760943904704e-06,
+      "loss": 2.2398,
+      "step": 24500
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 8.681296283714928e-06,
+      "loss": 2.2477,
+      "step": 25000
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 8.45528455284553e-06,
+      "loss": 2.2248,
+      "step": 25500
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 8.228819892655751e-06,
+      "loss": 2.2286,
+      "step": 26000
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 8.002355232465975e-06,
+      "loss": 2.2268,
+      "step": 26500
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 7.775890572276197e-06,
+      "loss": 2.239,
+      "step": 27000
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 7.5498788414067996e-06,
+      "loss": 2.2238,
+      "step": 27500
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 7.323414181217021e-06,
+      "loss": 2.2225,
+      "step": 28000
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 7.096949521027244e-06,
+      "loss": 2.2272,
+      "step": 28500
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 6.870484860837466e-06,
+      "loss": 2.2663,
+      "step": 29000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.092595100402832,
+      "eval_runtime": 372.6322,
+      "eval_samples_per_second": 157.995,
+      "eval_steps_per_second": 9.876,
+      "step": 29438
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 6.644473129968069e-06,
+      "loss": 2.2417,
+      "step": 29500
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 6.4180084697782915e-06,
+      "loss": 2.2355,
+      "step": 30000
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 6.191543809588514e-06,
+      "loss": 2.2285,
+      "step": 30500
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 5.965079149398737e-06,
+      "loss": 2.2392,
+      "step": 31000
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 5.738614489208959e-06,
+      "loss": 2.23,
+      "step": 31500
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 5.512149829019182e-06,
+      "loss": 2.2399,
+      "step": 32000
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 5.286138098149784e-06,
+      "loss": 2.2363,
+      "step": 32500
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 5.059673437960007e-06,
+      "loss": 2.2392,
+      "step": 33000
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 4.833208777770229e-06,
+      "loss": 2.2302,
+      "step": 33500
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 4.6067441175804515e-06,
+      "loss": 2.2257,
+      "step": 34000
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 4.380732386711054e-06,
+      "loss": 2.2527,
+      "step": 34500
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 4.154267726521277e-06,
+      "loss": 2.2505,
+      "step": 35000
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 3.927803066331499e-06,
+      "loss": 2.2063,
+      "step": 35500
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 3.701338406141722e-06,
+      "loss": 2.2317,
+      "step": 36000
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 3.4748737459519442e-06,
+      "loss": 2.2432,
+      "step": 36500
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 3.248409085762167e-06,
+      "loss": 2.2414,
+      "step": 37000
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 3.0219444255723896e-06,
+      "loss": 2.2523,
+      "step": 37500
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 2.795479765382612e-06,
+      "loss": 2.2264,
+      "step": 38000
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 2.5690151051928346e-06,
+      "loss": 2.229,
+      "step": 38500
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 2.343003374323437e-06,
+      "loss": 2.2231,
+      "step": 39000
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 2.1165387141336597e-06,
+      "loss": 2.2375,
+      "step": 39500
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 1.8900740539438822e-06,
+      "loss": 2.235,
+      "step": 40000
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 1.6636093937541049e-06,
+      "loss": 2.2294,
+      "step": 40500
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 1.4371447335643274e-06,
+      "loss": 2.2244,
+      "step": 41000
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 1.2106800733745499e-06,
+      "loss": 2.2468,
+      "step": 41500
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 9.842154131847726e-07,
+      "loss": 2.2278,
+      "step": 42000
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 7.577507529949953e-07,
+      "loss": 2.222,
+      "step": 42500
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 5.317390221255973e-07,
+      "loss": 2.2208,
+      "step": 43000
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 3.057272912561995e-07,
+      "loss": 2.211,
+      "step": 43500
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 7.926263106642208e-08,
+      "loss": 2.2092,
+      "step": 44000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.086573362350464,
+      "eval_runtime": 371.7326,
+      "eval_samples_per_second": 158.377,
+      "eval_steps_per_second": 9.9,
+      "step": 44157
+    }
+  ],
+  "max_steps": 44157,
+  "num_train_epochs": 3,
+  "total_flos": 6.916093810478285e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-44157/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:877743c33e306d19c3f70b013b001c6a7976c99a695b0ebd0072e22d2b6381b9
+size 3375

config.json

@@ -0,0 +1,58 @@
+{
+  "_name_or_path": "t5-small",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 512,
+  "decoder_start_token_id": 0,
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 6,
+  "num_heads": 8,
+  "num_layers": 6,
+  "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": "4.19.4",
+  "use_cache": true,
+  "vocab_size": 32128
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4bef3500b6c1bc07cbe61e7ee9dcfcbfb8fafa58569407cf92d710ecd195f76
+size 242070267

runs/Jun16_12-09-25_c34ff7159c16/1655381368.0660024/events.out.tfevents.1655381368.c34ff7159c16.10568.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd5234b3e1b7e2b32ccbb05750bb8d4e5635f5e8f49f2287c8145878762fc374
+size 5436

runs/Jun16_12-09-25_c34ff7159c16/events.out.tfevents.1655381368.c34ff7159c16.10568.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:877b8a87239da6f195646575c105fe30adf8bcb99cecffd96cf2529a699e079a
+size 19591

special_tokens_map.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "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>"]}

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 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "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>"], "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "t5-small", "tokenizer_class": "T5Tokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acb29a171fcab1e64030730ed74400cc1cf48894314cd0d84d7d74fc63231930
+size 3375