End of training

.gitignore

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

README.md

@@ -0,0 +1,69 @@
+---
+language:
+- multilingual
+license: apache-2.0
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: canine_c
+  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. -->
+
+# canine_c
+
+This model is a fine-tuned version of [google/canine-c](https://huggingface.co/google/canine-c) on the Gwatk/10k_test3_xnli_subset dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0990
+- Accuracy: 0.3247
+- F1 Weighted: 0.1591
+- Precision Weighted: 0.1054
+- Recall Weighted: 0.3247
+
+## 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: 5e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 32
+- 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 | Accuracy | F1 Weighted | Precision Weighted | Recall Weighted |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:-----------:|:------------------:|:---------------:|
+| 1.1017        | 1.0   | 312  | 1.1029          | 0.3247   | 0.1591      | 0.1054             | 0.3247          |
+| 1.0999        | 2.0   | 625  | 1.0978          | 0.3533   | 0.1845      | 0.1248             | 0.3533          |
+| 1.099         | 3.0   | 936  | 1.0990          | 0.3247   | 0.1591      | 0.1054             | 0.3247          |
+
+
+### Framework versions
+
+- Transformers 4.27.2
+- Pytorch 2.0.0+cu117
+- Datasets 2.10.1
+- Tokenizers 0.13.2

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "google/canine-c",
+  "architectures": [
+    "CanineForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 57344,
+  "downsampling_rate": 4,
+  "eos_token_id": 57345,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "local_transformer_stride": 128,
+  "max_position_embeddings": 16384,
+  "model_type": "canine",
+  "num_attention_heads": 12,
+  "num_hash_buckets": 16384,
+  "num_hash_functions": 8,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.2",
+  "type_vocab_size": 16,
+  "upsampling_kernel_size": 4,
+  "use_cache": true
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80dc483a70efe3912f6fdf77393ad05a11d0e5538e9efd2c0b219b42566f6b99
+size 528557809

runs/Mar25_01-36-57_evening/1679704631.0029478/events.out.tfevents.1679704631.evening.174289.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:251ebe26f5c7180f1caa37653b00a0b4a610faaa9d94312edaa845685849a793
+size 5915

runs/Mar25_01-36-57_evening/events.out.tfevents.1679704631.evening.174289.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26eda968e989e2803abd1b97f9664d9f0a84fb8d01af580dc2f3f80caa167d56
+size 7715

special_tokens_map.json

@@ -0,0 +1,44 @@
+{
+  "bos_token": {
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "\u0000",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "__type": "AddedToken",
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 2048,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "\u0000",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "__type": "AddedToken",
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "special_tokens_map_file": "/home/gwatk/.cache/huggingface/hub/models--google--canine-c/snapshots/59de14c6de8e676db78de601ac4cb470b56d4d25/special_tokens_map.json",
+  "tokenizer_class": "CanineTokenizer"
+}

trainer_state.json

@@ -0,0 +1,121 @@
+{
+  "best_metric": 0.35333333333333333,
+  "best_model_checkpoint": "nli_results/10k_test3/models/canine_c/checkpoint-625",
+  "epoch": 2.9952,
+  "global_step": 936,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.99465811965812e-05,
+      "loss": 1.3267,
+      "step": 1
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.465811965811966e-05,
+      "loss": 1.1043,
+      "step": 100
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 3.931623931623932e-05,
+      "loss": 1.102,
+      "step": 200
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 3.397435897435898e-05,
+      "loss": 1.1017,
+      "step": 300
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.32466666666666666,
+      "eval_f1_weighted": 0.15914712296594533,
+      "eval_loss": 1.1029257774353027,
+      "eval_precision_weighted": 0.10540844444444444,
+      "eval_recall_weighted": 0.32466666666666666,
+      "eval_runtime": 5.4193,
+      "eval_samples_per_second": 276.79,
+      "eval_steps_per_second": 69.197,
+      "step": 312
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 2.863247863247863e-05,
+      "loss": 1.0994,
+      "step": 400
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 2.3290598290598293e-05,
+      "loss": 1.1003,
+      "step": 500
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.794871794871795e-05,
+      "loss": 1.0999,
+      "step": 600
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.35333333333333333,
+      "eval_f1_weighted": 0.1844991789819376,
+      "eval_loss": 1.0978268384933472,
+      "eval_precision_weighted": 0.12484444444444445,
+      "eval_recall_weighted": 0.35333333333333333,
+      "eval_runtime": 6.1353,
+      "eval_samples_per_second": 244.485,
+      "eval_steps_per_second": 61.121,
+      "step": 625
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 1.2606837606837608e-05,
+      "loss": 1.0999,
+      "step": 700
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 7.264957264957266e-06,
+      "loss": 1.0995,
+      "step": 800
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 1.9230769230769234e-06,
+      "loss": 1.099,
+      "step": 900
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.32466666666666666,
+      "eval_f1_weighted": 0.15914712296594533,
+      "eval_loss": 1.0989837646484375,
+      "eval_precision_weighted": 0.10540844444444444,
+      "eval_recall_weighted": 0.32466666666666666,
+      "eval_runtime": 5.3918,
+      "eval_samples_per_second": 278.202,
+      "eval_steps_per_second": 69.55,
+      "step": 936
+    },
+    {
+      "epoch": 3.0,
+      "step": 936,
+      "total_flos": 5792280106446720.0,
+      "train_loss": 1.100847668117947,
+      "train_runtime": 456.1632,
+      "train_samples_per_second": 65.766,
+      "train_steps_per_second": 2.052
+    }
+  ],
+  "max_steps": 936,
+  "num_train_epochs": 3,
+  "total_flos": 5792280106446720.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69152455c19e5361f5b9784369ecc2c8e4bd0cbcf337477a85c43c2705296563
+size 3643