anantoj commited on Jun 16, 2022

Commit

8e211ba

•

1 Parent(s): 7045e1b

Initial commit

Browse files

Files changed (20) hide show

README.md +59 -0
checkpoint-44157/config.json +58 -0
checkpoint-44157/optimizer.pt +3 -0
checkpoint-44157/pytorch_model.bin +3 -0
checkpoint-44157/rng_state.pth +3 -0
checkpoint-44157/scaler.pt +3 -0
checkpoint-44157/scheduler.pt +3 -0
checkpoint-44157/special_tokens_map.json +1 -0
checkpoint-44157/spiece.model +3 -0
checkpoint-44157/tokenizer.json +0 -0
checkpoint-44157/tokenizer_config.json +1 -0
checkpoint-44157/trainer_state.json +568 -0
checkpoint-44157/training_args.bin +3 -0
config.json +58 -0
pytorch_model.bin +3 -0
special_tokens_map.json +1 -0
spiece.model +3 -0
tokenizer.json +0 -0
tokenizer_config.json +1 -0
training_args.bin +3 -0

README.md ADDED Viewed

	@@ -0,0 +1,59 @@

+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+model-index:
+- name: results
+  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. -->
+# results
+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: 2.0868
+## 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 |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 2.2583        | 1.0   | 14719 | 2.1164          |
+| 2.2649        | 2.0   | 29438 | 2.0925          |
+| 2.209         | 3.0   | 44157 | 2.0868          |
+### Framework versions
+- Transformers 4.19.4
+- Pytorch 1.11.0+cu113
+- Datasets 2.3.2
+- Tokenizers 0.12.1

checkpoint-44157/config.json ADDED Viewed

	@@ -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 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:15c46c37a1b327317e2d9ba045448b5c85be37f9b2581c8624114bcf64b521c0
+size 484129461

checkpoint-44157/pytorch_model.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:e2a080ed17900659a6f7c133c72c814002125f51c35ae6c7d423421367542a0e
+size 242070267

checkpoint-44157/rng_state.pth ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:bc3d0e710cabea991f3688f1b06042c351dcad4c6c31e7155a30be41084e42ec
+size 14503

checkpoint-44157/scaler.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:19ebcd5f457b4e963a47547930d77acbcf9f874a502751b8720fb128e1b3893a
+size 559

checkpoint-44157/scheduler.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d67dd30727a2b39ab56e811aa8b1718be5cf6a140eb779db146e24974f09c3e4
+size 623

checkpoint-44157/special_tokens_map.json ADDED Viewed

	@@ -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 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
+size 791656

checkpoint-44157/tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

checkpoint-44157/tokenizer_config.json ADDED Viewed

	@@ -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 ADDED Viewed

	@@ -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": 2.5305,
+      "step": 500
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9548429467581584e-05,
+      "loss": 2.4174,
+      "step": 1000
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9322417736712188e-05,
+      "loss": 2.4269,
+      "step": 1500
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.909595307652241e-05,
+      "loss": 2.3693,
+      "step": 2000
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.8869488416332635e-05,
+      "loss": 2.3566,
+      "step": 2500
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8643023756142857e-05,
+      "loss": 2.3586,
+      "step": 3000
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.841655909595308e-05,
+      "loss": 2.3499,
+      "step": 3500
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.81900944357633e-05,
+      "loss": 2.3594,
+      "step": 4000
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.7963629775573522e-05,
+      "loss": 2.345,
+      "step": 4500
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.7737165115383744e-05,
+      "loss": 2.321,
+      "step": 5000
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.7510700455193966e-05,
+      "loss": 2.3003,
+      "step": 5500
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.728423579500419e-05,
+      "loss": 2.3128,
+      "step": 6000
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.7058224064134795e-05,
+      "loss": 2.3011,
+      "step": 6500
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.6831759403945017e-05,
+      "loss": 2.3096,
+      "step": 7000
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.660529474375524e-05,
+      "loss": 2.3256,
+      "step": 7500
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.637883008356546e-05,
+      "loss": 2.2922,
+      "step": 8000
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.6152365423375686e-05,
+      "loss": 2.3021,
+      "step": 8500
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.5925900763185907e-05,
+      "loss": 2.3011,
+      "step": 9000
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.569943610299613e-05,
+      "loss": 2.2814,
+      "step": 9500
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.547297144280635e-05,
+      "loss": 2.2816,
+      "step": 10000
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.5246959711936953e-05,
+      "loss": 2.2801,
+      "step": 10500
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.5020947981067555e-05,
+      "loss": 2.2993,
+      "step": 11000
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.4794483320877777e-05,
+      "loss": 2.3057,
+      "step": 11500
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.4568018660688002e-05,
+      "loss": 2.2701,
+      "step": 12000
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.4341554000498224e-05,
+      "loss": 2.2742,
+      "step": 12500
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.4115089340308446e-05,
+      "loss": 2.2872,
+      "step": 13000
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.388862468011867e-05,
+      "loss": 2.256,
+      "step": 13500
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.3662160019928891e-05,
+      "loss": 2.2959,
+      "step": 14000
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.3435695359739113e-05,
+      "loss": 2.2583,
+      "step": 14500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.116374969482422,
+      "eval_runtime": 353.9363,
+      "eval_samples_per_second": 166.341,
+      "eval_steps_per_second": 10.397,
+      "step": 14719
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.3209230699549337e-05,
+      "loss": 2.2496,
+      "step": 15000
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 1.2983218968679939e-05,
+      "loss": 2.2561,
+      "step": 15500
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1.275675430849016e-05,
+      "loss": 2.2408,
+      "step": 16000
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 1.2530289648300384e-05,
+      "loss": 2.2835,
+      "step": 16500
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.2303824988110606e-05,
+      "loss": 2.2636,
+      "step": 17000
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.2077360327920828e-05,
+      "loss": 2.2751,
+      "step": 17500
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.1850895667731051e-05,
+      "loss": 2.279,
+      "step": 18000
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.1624431007541275e-05,
+      "loss": 2.27,
+      "step": 18500
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.1398419276671877e-05,
+      "loss": 2.2436,
+      "step": 19000
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.1171954616482099e-05,
+      "loss": 2.2575,
+      "step": 19500
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.094548995629232e-05,
+      "loss": 2.2669,
+      "step": 20000
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 1.0719025296102544e-05,
+      "loss": 2.269,
+      "step": 20500
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.0492560635912768e-05,
+      "loss": 2.2429,
+      "step": 21000
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.026609597572299e-05,
+      "loss": 2.2424,
+      "step": 21500
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.0039631315533211e-05,
+      "loss": 2.2549,
+      "step": 22000
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 9.813166655343435e-06,
+      "loss": 2.2623,
+      "step": 22500
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 9.587154924474037e-06,
+      "loss": 2.2634,
+      "step": 23000
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 9.360690264284259e-06,
+      "loss": 2.2674,
+      "step": 23500
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 9.134225604094482e-06,
+      "loss": 2.2611,
+      "step": 24000
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 8.907760943904704e-06,
+      "loss": 2.2418,
+      "step": 24500
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 8.681749213035306e-06,
+      "loss": 2.2493,
+      "step": 25000
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 8.45528455284553e-06,
+      "loss": 2.2259,
+      "step": 25500
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 8.229272821976131e-06,
+      "loss": 2.2296,
+      "step": 26000
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 8.002808161786353e-06,
+      "loss": 2.2258,
+      "step": 26500
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 7.776343501596577e-06,
+      "loss": 2.2407,
+      "step": 27000
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 7.5498788414067996e-06,
+      "loss": 2.2242,
+      "step": 27500
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 7.323414181217021e-06,
+      "loss": 2.2227,
+      "step": 28000
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 7.096949521027244e-06,
+      "loss": 2.2264,
+      "step": 28500
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 6.870484860837466e-06,
+      "loss": 2.2649,
+      "step": 29000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.092484951019287,
+      "eval_runtime": 353.9215,
+      "eval_samples_per_second": 166.348,
+      "eval_steps_per_second": 10.398,
+      "step": 29438
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 6.6440202006476895e-06,
+      "loss": 2.2415,
+      "step": 29500
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 6.417555540457911e-06,
+      "loss": 2.2354,
+      "step": 30000
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 6.191090880268135e-06,
+      "loss": 2.2296,
+      "step": 30500
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 5.965079149398737e-06,
+      "loss": 2.241,
+      "step": 31000
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 5.738614489208959e-06,
+      "loss": 2.2279,
+      "step": 31500
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 5.512149829019182e-06,
+      "loss": 2.2405,
+      "step": 32000
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 5.285685168829404e-06,
+      "loss": 2.2379,
+      "step": 32500
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 5.059673437960007e-06,
+      "loss": 2.2386,
+      "step": 33000
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 4.833208777770229e-06,
+      "loss": 2.2298,
+      "step": 33500
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 4.6067441175804515e-06,
+      "loss": 2.2259,
+      "step": 34000
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 4.380279457390674e-06,
+      "loss": 2.2537,
+      "step": 34500
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 4.153814797200897e-06,
+      "loss": 2.2521,
+      "step": 35000
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 3.927803066331499e-06,
+      "loss": 2.2049,
+      "step": 35500
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 3.701338406141722e-06,
+      "loss": 2.2317,
+      "step": 36000
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 3.4748737459519442e-06,
+      "loss": 2.2476,
+      "step": 36500
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 3.248409085762167e-06,
+      "loss": 2.2435,
+      "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": 2.5694680345132143e-06,
+      "loss": 2.2287,
+      "step": 38500
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 2.343003374323437e-06,
+      "loss": 2.2238,
+      "step": 39000
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 2.116991643454039e-06,
+      "loss": 2.2383,
+      "step": 39500
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 1.8905269832642617e-06,
+      "loss": 2.234,
+      "step": 40000
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 1.6640623230744844e-06,
+      "loss": 2.2298,
+      "step": 40500
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 1.4375976628847069e-06,
+      "loss": 2.2237,
+      "step": 41000
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 1.2111330026949296e-06,
+      "loss": 2.2489,
+      "step": 41500
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 9.846683425051522e-07,
+      "loss": 2.2263,
+      "step": 42000
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 7.582036823153747e-07,
+      "loss": 2.2223,
+      "step": 42500
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 5.317390221255973e-07,
+      "loss": 2.2229,
+      "step": 43000
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 3.0527436193581997e-07,
+      "loss": 2.2121,
+      "step": 43500
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 7.880970174604252e-08,
+      "loss": 2.209,
+      "step": 44000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.086761713027954,
+      "eval_runtime": 355.3374,
+      "eval_samples_per_second": 165.685,
+      "eval_steps_per_second": 10.356,
+      "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 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:19ba9d8516ad17e2c42a4b8c4e8c8f875bc32973b67b249cf10b10aaf8b8ab6e
+size 3311

config.json ADDED Viewed

	@@ -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 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:e2a080ed17900659a6f7c133c72c814002125f51c35ae6c7d423421367542a0e
+size 242070267

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1 @@

spiece.model ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
+size 791656

tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1 @@

training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:effd2643805aa0d145b33d51d879c48376bd40edd6a00105dad77efe1240a28b
+size 3375