Training in progress, epoch 3

checkpoint-1605/config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "google/fnet-base",
+  "architectures": [
+    "FNetForSequenceClassification"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "finetuning_task": "cola",
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "unacceptable",
+    "1": "acceptable"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "acceptable": 1,
+    "unacceptable": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "fnet",
+  "num_hidden_layers": 12,
+  "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-1605/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32f61f465b3ee19b1ba73b7a4b0a12a73043501526edb4e49f905a8d855e44e2
+size 662962261

checkpoint-1605/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2663d881bea73fc94c3a6fee90ae84e7a071a6ae9cd1b0bb7eace5ad5f5163a
+size 331497705

checkpoint-1605/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3073cce146d32a4cbdc8f7f1fd5e284dabd15186d6e0df89890ec1c34375f613
+size 14503

checkpoint-1605/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1acca92a8b10bd06cc866eafb8aeb9d4f85bcdb2d57143bebcfe2bc573e5d33a
+size 623

checkpoint-1605/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-1605/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": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "special_tokens_map_file": "./special_tokens_map.json", "name_or_path": "google/fnet-base", "model_max_length": 512, "tokenizer_class": "FNetTokenizer"}

checkpoint-1605/trainer_state.json

@@ -0,0 +1,61 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 1605,
+  "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": 0.5895,
+      "step": 535
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6146270632743835,
+      "eval_matthews_correlation": 0.16988650877044353,
+      "eval_runtime": 7.5781,
+      "eval_samples_per_second": 137.634,
+      "eval_steps_per_second": 17.287,
+      "step": 535
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.4656,
+      "step": 1070
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5666966438293457,
+      "eval_matthews_correlation": 0.30468062994701894,
+      "eval_runtime": 7.5686,
+      "eval_samples_per_second": 137.807,
+      "eval_steps_per_second": 17.308,
+      "step": 1070
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.3329,
+      "step": 1605
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5929099917411804,
+      "eval_matthews_correlation": 0.35940659235571387,
+      "eval_runtime": 7.5654,
+      "eval_samples_per_second": 137.865,
+      "eval_steps_per_second": 17.316,
+      "step": 1605
+    }
+  ],
+  "max_steps": 1605,
+  "num_train_epochs": 3,
+  "total_flos": 4562104380880896.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1605/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1065b6c21962e07acc7e5e66d233473b94f201230ab4baac099ee8ece74e5327
+size 2799

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85a6d9d605e9095607d42698a9b93353f860d7ec7d068fcae5dafcb027c4c7fd
+oid sha256:f2663d881bea73fc94c3a6fee90ae84e7a071a6ae9cd1b0bb7eace5ad5f5163a
 size 331497705

runs/Sep16_19-30-53_patrick-general-gpu/events.out.tfevents.1631820668.patrick-general-gpu.205020.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:195cf06a0cbb228ee1919e0e60eca2f51be36f37f9f68e2f17a6ef4846a712c1
-size 4164
+oid sha256:ba6d5bd7febf0a97a957cd66f7bb445a5d9d432650464ed60ac68ba42ca591f3
+size 4656