Add checkpoints

README.md

@@ -0,0 +1,76 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- glue
+metrics:
+- accuracy
+model-index:
+- name: fnet-large-finetuned-rte
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE RTE
+      type: glue
+      args: rte
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.6425992779783394
+---
+
+<!-- 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. -->
+
+# fnet-large-finetuned-rte
+
+This model is a fine-tuned version of [google/fnet-large](https://huggingface.co/google/fnet-large) on the GLUE RTE dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7528
+- Accuracy: 0.6426
+
+## 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: 4
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.7105        | 1.0   | 623  | 0.6887          | 0.5740   |
+| 0.6714        | 2.0   | 1246 | 0.6742          | 0.6209   |
+| 0.509         | 3.0   | 1869 | 0.7528          | 0.6426   |
+
+
+### Framework versions
+
+- Transformers 4.11.0.dev0
+- Pytorch 1.9.0
+- Datasets 1.12.1
+- Tokenizers 0.10.3

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.6425992779783394,
+    "eval_loss": 0.7528035044670105,
+    "eval_runtime": 6.0647,
+    "eval_samples": 277,
+    "eval_samples_per_second": 45.674,
+    "eval_steps_per_second": 5.771,
+    "train_loss": 0.6302928485737694,
+    "train_runtime": 568.3379,
+    "train_samples": 2490,
+    "train_samples_per_second": 13.144,
+    "train_steps_per_second": 3.289
+}

checkpoint-1246/config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "google/fnet-large",
+  "architectures": [
+    "FNetForSequenceClassification"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "finetuning_task": "rte",
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "entailment",
+    "1": "not_entailment"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "entailment": 0,
+    "not_entailment": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "fnet",
+  "num_hidden_layers": 24,
+  "pad_token_id": 3,
+  "torch_dtype": "float32",
+  "tpu_short_seq_length": 512,
+  "transformers_version": "4.11.0.dev0",
+  "type_vocab_size": 4,
+  "use_tpu_fourier_optimizations": false,
+  "vocab_size": 32000
+}

checkpoint-1246/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3492a9c2bb2541aa54dc3e8ad537271c2b75087f5b2f04f5d2c0f4978e0d17d4
+size 1895696981

checkpoint-1246/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cb625a37111bd4c8ebb494e633fe8d6b3c995d0643119485350dca980b5d8bb
+size 947877033

checkpoint-1246/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bda81bb568b20cc7bb434b01295f33871c4acae43d5b6e0791d29f0db0da9d2b
+size 14503

checkpoint-1246/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:807b68d396323acc4f245eabe77c6ea863a93c99404ff54acaba04cf222fa29a
+size 623

checkpoint-1246/special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}

checkpoint-1246/tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "remove_space": true, "keep_accents": true, "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "model_max_length": 512, "special_tokens_map_file": "/home/gunjan/.cache/huggingface/transformers/9a50cd9b3771023230b1128ab5e112461bf36f5826d5f7eb654348e956979a54.a2cfb41d43ad2ac50fa89998bfa88393398e3bb3439ee99e1b00933bce2eb1ba", "name_or_path": "google/fnet-large", "tokenizer_class": "FNetTokenizer"}

checkpoint-1246/trainer_state.json

@@ -0,0 +1,46 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "global_step": 1246,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.7105,
+      "step": 623
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5740072202166066,
+      "eval_loss": 0.6886927485466003,
+      "eval_runtime": 6.0294,
+      "eval_samples_per_second": 45.941,
+      "eval_steps_per_second": 5.805,
+      "step": 623
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.6714,
+      "step": 1246
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6209386281588448,
+      "eval_loss": 0.6742456555366516,
+      "eval_runtime": 6.0186,
+      "eval_samples_per_second": 46.024,
+      "eval_steps_per_second": 5.815,
+      "step": 1246
+    }
+  ],
+  "max_steps": 1869,
+  "num_train_epochs": 3,
+  "total_flos": 3115568174653440.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1246/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d36887e8ab392d1a5424956af0db4e0cfe9dd19432d7c3050e22f58e047346aa
+size 2735

checkpoint-1869/config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "google/fnet-large",
+  "architectures": [
+    "FNetForSequenceClassification"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "finetuning_task": "rte",
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "entailment",
+    "1": "not_entailment"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "entailment": 0,
+    "not_entailment": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "fnet",
+  "num_hidden_layers": 24,
+  "pad_token_id": 3,
+  "torch_dtype": "float32",
+  "tpu_short_seq_length": 512,
+  "transformers_version": "4.11.0.dev0",
+  "type_vocab_size": 4,
+  "use_tpu_fourier_optimizations": false,
+  "vocab_size": 32000
+}

checkpoint-1869/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84959bd434ce766b7c3be594c07f3f216a33d64f67c075d60f70cfa03214f402
+size 1895696981

checkpoint-1869/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5c64cf6ca8405535ddcd62938eea726e58e0386a5d9327bb07a3a2fb89098e4
+size 947877033

checkpoint-1869/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a19ec7562690bcc02674fc0edc83d200e950ef12f6e470a2b31543faca8d6f61
+size 14503

checkpoint-1869/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2780fd14be91c71e9874620e45e474625b70b5f31dd07192fac262b87276483d
+size 623

checkpoint-1869/special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}

checkpoint-1869/tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "remove_space": true, "keep_accents": true, "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "model_max_length": 512, "special_tokens_map_file": "/home/gunjan/.cache/huggingface/transformers/9a50cd9b3771023230b1128ab5e112461bf36f5826d5f7eb654348e956979a54.a2cfb41d43ad2ac50fa89998bfa88393398e3bb3439ee99e1b00933bce2eb1ba", "name_or_path": "google/fnet-large", "tokenizer_class": "FNetTokenizer"}

checkpoint-1869/trainer_state.json

@@ -0,0 +1,61 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 1869,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.7105,
+      "step": 623
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5740072202166066,
+      "eval_loss": 0.6886927485466003,
+      "eval_runtime": 6.0294,
+      "eval_samples_per_second": 45.941,
+      "eval_steps_per_second": 5.805,
+      "step": 623
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.6714,
+      "step": 1246
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6209386281588448,
+      "eval_loss": 0.6742456555366516,
+      "eval_runtime": 6.0186,
+      "eval_samples_per_second": 46.024,
+      "eval_steps_per_second": 5.815,
+      "step": 1246
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.509,
+      "step": 1869
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6425992779783394,
+      "eval_loss": 0.7528035044670105,
+      "eval_runtime": 6.0214,
+      "eval_samples_per_second": 46.002,
+      "eval_steps_per_second": 5.813,
+      "step": 1869
+    }
+  ],
+  "max_steps": 1869,
+  "num_train_epochs": 3,
+  "total_flos": 4673352261980160.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1869/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d36887e8ab392d1a5424956af0db4e0cfe9dd19432d7c3050e22f58e047346aa
+size 2735

checkpoint-623/config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "google/fnet-large",
+  "architectures": [
+    "FNetForSequenceClassification"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "finetuning_task": "rte",
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "entailment",
+    "1": "not_entailment"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "entailment": 0,
+    "not_entailment": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "fnet",
+  "num_hidden_layers": 24,
+  "pad_token_id": 3,
+  "torch_dtype": "float32",
+  "tpu_short_seq_length": 512,
+  "transformers_version": "4.11.0.dev0",
+  "type_vocab_size": 4,
+  "use_tpu_fourier_optimizations": false,
+  "vocab_size": 32000
+}

checkpoint-623/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b16835d44719522e55b2361859ec2a84d1ffb8db27a4258b6b8403fb99155a05
+size 1895696981

checkpoint-623/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93330005017a57fa1008a7e0cf7240fdc2f5cf900755695267420230c2684782
+size 947877033

checkpoint-623/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d4b804a57d065bd1783e83c401c2fc0a793c12eeb84bd3f20413a851a3f0140
+size 14503

checkpoint-623/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d992d5a47c42b0fca55fe41cd42bb27e0d0969d9b7c8286695f30f06cabed401
+size 623

checkpoint-623/special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}

checkpoint-623/tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "remove_space": true, "keep_accents": true, "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "model_max_length": 512, "special_tokens_map_file": "/home/gunjan/.cache/huggingface/transformers/9a50cd9b3771023230b1128ab5e112461bf36f5826d5f7eb654348e956979a54.a2cfb41d43ad2ac50fa89998bfa88393398e3bb3439ee99e1b00933bce2eb1ba", "name_or_path": "google/fnet-large", "tokenizer_class": "FNetTokenizer"}

checkpoint-623/trainer_state.json

@@ -0,0 +1,31 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "global_step": 623,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.7105,
+      "step": 623
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5740072202166066,
+      "eval_loss": 0.6886927485466003,
+      "eval_runtime": 6.0294,
+      "eval_samples_per_second": 45.941,
+      "eval_steps_per_second": 5.805,
+      "step": 623
+    }
+  ],
+  "max_steps": 1869,
+  "num_train_epochs": 3,
+  "total_flos": 1557784087326720.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-623/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d36887e8ab392d1a5424956af0db4e0cfe9dd19432d7c3050e22f58e047346aa
+size 2735

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "google/fnet-large",
+  "architectures": [
+    "FNetForSequenceClassification"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "finetuning_task": "rte",
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "entailment",
+    "1": "not_entailment"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "entailment": 0,
+    "not_entailment": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "fnet",
+  "num_hidden_layers": 24,
+  "pad_token_id": 3,
+  "torch_dtype": "float32",
+  "tpu_short_seq_length": 512,
+  "transformers_version": "4.11.0.dev0",
+  "type_vocab_size": 4,
+  "use_tpu_fourier_optimizations": false,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.6425992779783394,
+    "eval_loss": 0.7528035044670105,
+    "eval_runtime": 6.0647,
+    "eval_samples": 277,
+    "eval_samples_per_second": 45.674,
+    "eval_steps_per_second": 5.771
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5c64cf6ca8405535ddcd62938eea726e58e0386a5d9327bb07a3a2fb89098e4
+size 947877033

runs/Sep24_11-12-57_patrick-general-gpu/1632481991.8449812/events.out.tfevents.1632481991.patrick-general-gpu.1063977.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d28d63e36c317d4270bcfcce8ed6e74de399e6d595f6ac92de9909864e6c0ba4
+size 4346

runs/Sep24_11-12-57_patrick-general-gpu/events.out.tfevents.1632481991.patrick-general-gpu.1063977.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d91970e555336b89032d9b86d871f33f3c72d61b2fd34edf14d86ac63613bff
+size 4974

runs/Sep24_11-12-57_patrick-general-gpu/events.out.tfevents.1632482567.patrick-general-gpu.1063977.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36faf1c6df0a7f57341a15b5c6473ef3c5d4870d95c52b171672dc0f192da2f0
+size 363

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "remove_space": true, "keep_accents": true, "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "model_max_length": 512, "special_tokens_map_file": "/home/gunjan/.cache/huggingface/transformers/9a50cd9b3771023230b1128ab5e112461bf36f5826d5f7eb654348e956979a54.a2cfb41d43ad2ac50fa89998bfa88393398e3bb3439ee99e1b00933bce2eb1ba", "name_or_path": "google/fnet-large", "tokenizer_class": "FNetTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.6302928485737694,
+    "train_runtime": 568.3379,
+    "train_samples": 2490,
+    "train_samples_per_second": 13.144,
+    "train_steps_per_second": 3.289
+}

trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 1869,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.7105,
+      "step": 623
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5740072202166066,
+      "eval_loss": 0.6886927485466003,
+      "eval_runtime": 6.0294,
+      "eval_samples_per_second": 45.941,
+      "eval_steps_per_second": 5.805,
+      "step": 623
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.6714,
+      "step": 1246
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6209386281588448,
+      "eval_loss": 0.6742456555366516,
+      "eval_runtime": 6.0186,
+      "eval_samples_per_second": 46.024,
+      "eval_steps_per_second": 5.815,
+      "step": 1246
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.509,
+      "step": 1869
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6425992779783394,
+      "eval_loss": 0.7528035044670105,
+      "eval_runtime": 6.0214,
+      "eval_samples_per_second": 46.002,
+      "eval_steps_per_second": 5.813,
+      "step": 1869
+    },
+    {
+      "epoch": 3.0,
+      "step": 1869,
+      "total_flos": 4673352261980160.0,
+      "train_loss": 0.6302928485737694,
+      "train_runtime": 568.3379,
+      "train_samples_per_second": 13.144,
+      "train_steps_per_second": 3.289
+    }
+  ],
+  "max_steps": 1869,
+  "num_train_epochs": 3,
+  "total_flos": 4673352261980160.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d36887e8ab392d1a5424956af0db4e0cfe9dd19432d7c3050e22f58e047346aa
+size 2735