Restore

.gitattributes

@@ -0,0 +1,39 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+spiece.model filter=lfs diff=lfs merge=lfs -text
+tokenizer filter=lfs diff=lfs merge=lfs -text
+training_args.bin filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,77 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- cstop_artificial
+model-index:
+- name: t5-base-pointer-adv-cstop_artificial
+  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-base-pointer-adv-cstop_artificial
+
+This model is a fine-tuned version of [google/mt5-base](https://huggingface.co/google/mt5-base) on the cstop_artificial dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0728
+- Exact Match: 0.7925
+
+## 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: 0.001
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 64
+- total_train_batch_size: 512
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- training_steps: 3000
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Exact Match |
+|:-------------:|:-----:|:----:|:---------------:|:-----------:|
+| 1.7423        | 12.5  | 200  | 0.1173          | 0.2397      |
+| 0.3678        | 25.0  | 400  | 0.0728          | 0.3363      |
+| 0.3202        | 37.5  | 600  | 0.0879          | 0.3381      |
+| 0.3452        | 50.0  | 800  | 0.0908          | 0.3363      |
+| 0.3099        | 62.5  | 1000 | 0.1056          | 0.3435      |
+| 0.3057        | 75.0  | 1200 | 0.1109          | 0.3470      |
+| 0.3045        | 87.5  | 1400 | 0.1273          | 0.3453      |
+| 0.3052        | 100.0 | 1600 | 0.1065          | 0.3417      |
+| 0.3037        | 112.5 | 1800 | 0.1387          | 0.3381      |
+| 0.3036        | 125.0 | 2000 | 0.1421          | 0.3453      |
+| 0.3023        | 137.5 | 2200 | 0.1649          | 0.3399      |
+| 0.3028        | 150.0 | 2400 | 0.1574          | 0.3399      |
+| 0.3025        | 162.5 | 2600 | 0.1563          | 0.3399      |
+| 0.3017        | 175.0 | 2800 | 0.1589          | 0.3399      |
+| 0.302         | 187.5 | 3000 | 0.1587          | 0.3417      |
+
+
+### Framework versions
+
+- Transformers 4.24.0
+- Pytorch 1.13.0+cu117
+- Datasets 2.7.0
+- Tokenizers 0.13.2

added_tokens.json

@@ -0,0 +1,60 @@
+{
+  "<pt-0>": 250131,
+  "<pt-10>": 250103,
+  "<pt-11>": 250108,
+  "<pt-12>": 250146,
+  "<pt-13>": 250135,
+  "<pt-14>": 250139,
+  "<pt-15>": 250147,
+  "<pt-16>": 250143,
+  "<pt-17>": 250155,
+  "<pt-18>": 250156,
+  "<pt-19>": 250157,
+  "<pt-1>": 250129,
+  "<pt-2>": 250114,
+  "<pt-3>": 250116,
+  "<pt-4>": 250106,
+  "<pt-5>": 250101,
+  "<pt-6>": 250100,
+  "<pt-7>": 250119,
+  "<pt-8>": 250117,
+  "<pt-9>": 250121,
+  "[IN:CAMERA_FOLLOW": 250104,
+  "[IN:CAMERA_STOP_FOLLOWING": 250107,
+  "[IN:CLOSE_RESOURCE": 250109,
+  "[IN:DECREASE_BRIGHTNESS": 250124,
+  "[IN:DECREASE_VOLUME": 250145,
+  "[IN:GET_INFO_CONTACT": 250152,
+  "[IN:GET_WEATHER": 250141,
+  "[IN:INCREASE_BRIGHTNESS": 250115,
+  "[IN:INCREASE_VOLUME": 250144,
+  "[IN:MAXIMIZE_VOLUME": 250136,
+  "[IN:MUTE_VOLUME": 250128,
+  "[IN:OPEN_HOMESCREEN": 250111,
+  "[IN:OPEN_RESOURCE": 250102,
+  "[IN:SET_BRIGHTNESS": 250127,
+  "[IN:SET_VOLUME": 250150,
+  "[IN:SLEEP": 250130,
+  "[IN:TURN_OFF": 250105,
+  "[IN:TURN_ON": 250110,
+  "[IN:UNMUTE_VOLUME": 250112,
+  "[IN:UNSUPPORTED_DEVICE": 250137,
+  "[IN:UNSUPPORTED_PEOPLE": 250149,
+  "[IN:UNSUPPORTED_WEATHER": 250142,
+  "[IN:WAKE_UP": 250133,
+  "[IN:ZOOM_IN": 250120,
+  "[IN:ZOOM_OUT": 250126,
+  "[SL:ABSTRACT_AMOUNT": 250132,
+  "[SL:COMPONENT": 250113,
+  "[SL:CONTACT": 250154,
+  "[SL:CONTACT_RELATED": 250148,
+  "[SL:DATE_TIME": 250151,
+  "[SL:LOCATION": 250138,
+  "[SL:PERCENT": 250125,
+  "[SL:PRECISE_AMOUNT": 250118,
+  "[SL:RESOURCE": 250123,
+  "[SL:RESOURCE_TYPE": 250122,
+  "[SL:TYPE_RELATION": 250153,
+  "[SL:WEATHER_ATTRIBUTE": 250140,
+  "[SL:WEATHER_TEMPERATURE_UNIT": 250134
+}

all_results.json

@@ -0,0 +1,20 @@
+{
+    "epoch": 187.5,
+    "eval_exact_match": 0.7924865831842576,
+    "eval_loss": 0.0727909728884697,
+    "eval_runtime": 45.8385,
+    "eval_samples": 559,
+    "eval_samples_per_second": 12.195,
+    "eval_steps_per_second": 1.527,
+    "predict_exact_match": 0.8063410454155956,
+    "predict_loss": 0.07482758909463882,
+    "predict_runtime": 97.1755,
+    "predict_samples": 1167,
+    "predict_samples_per_second": 12.009,
+    "predict_steps_per_second": 1.502,
+    "train_loss": 0.4079610900878906,
+    "train_runtime": 34544.7098,
+    "train_samples": 8224,
+    "train_samples_per_second": 44.464,
+    "train_steps_per_second": 0.087
+}

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "google/mt5-base",
+  "architectures": [
+    "AlignedMT5ForConditionalGeneration"
+  ],
+  "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": "mt5",
+  "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,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0",
+  "use_cache": true,
+  "vocab_size": 250158
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 187.5,
+    "eval_exact_match": 0.7924865831842576,
+    "eval_loss": 0.0727909728884697,
+    "eval_runtime": 45.8385,
+    "eval_samples": 559,
+    "eval_samples_per_second": 12.195,
+    "eval_steps_per_second": 1.527
+}

predict_results.json

@@ -0,0 +1,8 @@
+{
+    "predict_exact_match": 0.8063410454155956,
+    "predict_loss": 0.07482758909463882,
+    "predict_runtime": 97.1755,
+    "predict_samples": 1167,
+    "predict_samples_per_second": 12.009,
+    "predict_steps_per_second": 1.502
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b69347ce660a344f2233d6fca17edd3abaebdd3df1ddaf57c3cb5e6f1c028e7f
+size 2332353369

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
+size 4309802

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9929b4c5b9acf43dac7a509446035e5dd7ad4b416483deb07b3067e47a5b81e2
+size 16341505

tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": null,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "name_or_path": "google/mt5-base",
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "/home/patrick/.cache/torch/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276",
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 187.5,
+    "train_loss": 0.4079610900878906,
+    "train_runtime": 34544.7098,
+    "train_samples": 8224,
+    "train_samples_per_second": 44.464,
+    "train_steps_per_second": 0.087
+}

trainer_state.json

@@ -0,0 +1,250 @@
+{
+  "best_metric": 0.0727909728884697,
+  "best_model_checkpoint": "/data/wheld3/mt5-base-pointer-adv-cstop_artificial/checkpoint-400",
+  "epoch": 187.49805447470817,
+  "global_step": 3000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 12.5,
+      "learning_rate": 0.0009333333333333333,
+      "loss": 1.7423,
+      "step": 200
+    },
+    {
+      "epoch": 12.5,
+      "eval_exact_match": 0.23971377459749552,
+      "eval_loss": 0.11730749905109406,
+      "eval_runtime": 27.8131,
+      "eval_samples_per_second": 20.098,
+      "eval_steps_per_second": 2.517,
+      "step": 200
+    },
+    {
+      "epoch": 25.0,
+      "learning_rate": 0.0008666666666666667,
+      "loss": 0.3678,
+      "step": 400
+    },
+    {
+      "epoch": 25.0,
+      "eval_exact_match": 0.3363148479427549,
+      "eval_loss": 0.0727909728884697,
+      "eval_runtime": 29.0466,
+      "eval_samples_per_second": 19.245,
+      "eval_steps_per_second": 2.41,
+      "step": 400
+    },
+    {
+      "epoch": 37.5,
+      "learning_rate": 0.0008,
+      "loss": 0.3202,
+      "step": 600
+    },
+    {
+      "epoch": 37.5,
+      "eval_exact_match": 0.33810375670840787,
+      "eval_loss": 0.08794570714235306,
+      "eval_runtime": 29.1974,
+      "eval_samples_per_second": 19.146,
+      "eval_steps_per_second": 2.397,
+      "step": 600
+    },
+    {
+      "epoch": 50.0,
+      "learning_rate": 0.0007333333333333333,
+      "loss": 0.3452,
+      "step": 800
+    },
+    {
+      "epoch": 50.0,
+      "eval_exact_match": 0.3363148479427549,
+      "eval_loss": 0.09075574576854706,
+      "eval_runtime": 28.6647,
+      "eval_samples_per_second": 19.501,
+      "eval_steps_per_second": 2.442,
+      "step": 800
+    },
+    {
+      "epoch": 62.5,
+      "learning_rate": 0.0006666666666666666,
+      "loss": 0.3099,
+      "step": 1000
+    },
+    {
+      "epoch": 62.5,
+      "eval_exact_match": 0.3434704830053667,
+      "eval_loss": 0.10556001961231232,
+      "eval_runtime": 28.9715,
+      "eval_samples_per_second": 19.295,
+      "eval_steps_per_second": 2.416,
+      "step": 1000
+    },
+    {
+      "epoch": 75.0,
+      "learning_rate": 0.0006,
+      "loss": 0.3057,
+      "step": 1200
+    },
+    {
+      "epoch": 75.0,
+      "eval_exact_match": 0.3470483005366726,
+      "eval_loss": 0.11086518317461014,
+      "eval_runtime": 29.2047,
+      "eval_samples_per_second": 19.141,
+      "eval_steps_per_second": 2.397,
+      "step": 1200
+    },
+    {
+      "epoch": 87.5,
+      "learning_rate": 0.0005333333333333334,
+      "loss": 0.3045,
+      "step": 1400
+    },
+    {
+      "epoch": 87.5,
+      "eval_exact_match": 0.34525939177101966,
+      "eval_loss": 0.1273432970046997,
+      "eval_runtime": 29.0031,
+      "eval_samples_per_second": 19.274,
+      "eval_steps_per_second": 2.414,
+      "step": 1400
+    },
+    {
+      "epoch": 100.0,
+      "learning_rate": 0.00046666666666666666,
+      "loss": 0.3052,
+      "step": 1600
+    },
+    {
+      "epoch": 100.0,
+      "eval_exact_match": 0.3416815742397138,
+      "eval_loss": 0.10654404759407043,
+      "eval_runtime": 28.7998,
+      "eval_samples_per_second": 19.41,
+      "eval_steps_per_second": 2.431,
+      "step": 1600
+    },
+    {
+      "epoch": 112.5,
+      "learning_rate": 0.0004,
+      "loss": 0.3037,
+      "step": 1800
+    },
+    {
+      "epoch": 112.5,
+      "eval_exact_match": 0.33810375670840787,
+      "eval_loss": 0.13873372972011566,
+      "eval_runtime": 29.2765,
+      "eval_samples_per_second": 19.094,
+      "eval_steps_per_second": 2.391,
+      "step": 1800
+    },
+    {
+      "epoch": 125.0,
+      "learning_rate": 0.0003333333333333333,
+      "loss": 0.3036,
+      "step": 2000
+    },
+    {
+      "epoch": 125.0,
+      "eval_exact_match": 0.34525939177101966,
+      "eval_loss": 0.1421414017677307,
+      "eval_runtime": 28.8117,
+      "eval_samples_per_second": 19.402,
+      "eval_steps_per_second": 2.43,
+      "step": 2000
+    },
+    {
+      "epoch": 137.5,
+      "learning_rate": 0.0002666666666666667,
+      "loss": 0.3023,
+      "step": 2200
+    },
+    {
+      "epoch": 137.5,
+      "eval_exact_match": 0.33989266547406083,
+      "eval_loss": 0.16489343345165253,
+      "eval_runtime": 30.9662,
+      "eval_samples_per_second": 18.052,
+      "eval_steps_per_second": 2.261,
+      "step": 2200
+    },
+    {
+      "epoch": 150.0,
+      "learning_rate": 0.0002,
+      "loss": 0.3028,
+      "step": 2400
+    },
+    {
+      "epoch": 150.0,
+      "eval_exact_match": 0.33989266547406083,
+      "eval_loss": 0.1573849618434906,
+      "eval_runtime": 29.0042,
+      "eval_samples_per_second": 19.273,
+      "eval_steps_per_second": 2.413,
+      "step": 2400
+    },
+    {
+      "epoch": 162.5,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.3025,
+      "step": 2600
+    },
+    {
+      "epoch": 162.5,
+      "eval_exact_match": 0.33989266547406083,
+      "eval_loss": 0.15625949203968048,
+      "eval_runtime": 28.8424,
+      "eval_samples_per_second": 19.381,
+      "eval_steps_per_second": 2.427,
+      "step": 2600
+    },
+    {
+      "epoch": 175.0,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.3017,
+      "step": 2800
+    },
+    {
+      "epoch": 175.0,
+      "eval_exact_match": 0.33989266547406083,
+      "eval_loss": 0.1589040458202362,
+      "eval_runtime": 28.7706,
+      "eval_samples_per_second": 19.43,
+      "eval_steps_per_second": 2.433,
+      "step": 2800
+    },
+    {
+      "epoch": 187.5,
+      "learning_rate": 0.0,
+      "loss": 0.302,
+      "step": 3000
+    },
+    {
+      "epoch": 187.5,
+      "eval_exact_match": 0.3416815742397138,
+      "eval_loss": 0.15874968469142914,
+      "eval_runtime": 33.2641,
+      "eval_samples_per_second": 16.805,
+      "eval_steps_per_second": 2.104,
+      "step": 3000
+    },
+    {
+      "epoch": 187.5,
+      "step": 3000,
+      "total_flos": 6.474719775139762e+16,
+      "train_loss": 0.4079610900878906,
+      "train_runtime": 34544.7098,
+      "train_samples_per_second": 44.464,
+      "train_steps_per_second": 0.087
+    }
+  ],
+  "max_steps": 3000,
+  "num_train_epochs": 188,
+  "total_flos": 6.474719775139762e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f0f9fc79fe4d1b66c314882732d3b427b10b38f9fef2d225acf1c1a1db62712
+size 3643