Training in progress, epoch 4, checkpoint

checkpoint-1072/config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "google/fnet-base",
+  "actual_seq_length": 512,
+  "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,
+  "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,
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "tpu_short_seq_length": 512,
+  "transformers_version": "4.42.0.dev0",
+  "type_vocab_size": 4,
+  "use_fft": true,
+  "use_latest": false,
+  "use_tpu_fourier_optimizations": false,
+  "vocab_size": 32000
+}

checkpoint-1072/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45720b1ba38cba214975ef146067dce24a52a8dd99d025d703f3e5ff016761d3
+size 331462608

checkpoint-1072/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78ff32b6f5f8e9145c4af37b5b91e1181c3ce0d719dcb73b5160cc90f99b0e77
+size 662989765

checkpoint-1072/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5737040a23e0ba2a33463945e4bec84847833be7c64aeb9a9e33df4bfa942898
+size 14575

checkpoint-1072/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37c2860225da3dfba5fb9dc73e04ce10437008815cf226bee7bf45caffa794bf
+size 627

checkpoint-1072/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1072/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "[MASK]",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "keep_accents": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "remove_space": true,
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "FNetTokenizer",
+  "unk_token": "<unk>"
+}

checkpoint-1072/trainer_state.json

@@ -0,0 +1,97 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 1072,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 9.199758529663086,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.61,
+      "step": 268
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.581834614276886,
+      "eval_matthews_correlation": 0.1605505486389139,
+      "eval_runtime": 8.5337,
+      "eval_samples_per_second": 122.221,
+      "eval_steps_per_second": 7.734,
+      "step": 268
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 7.077225685119629,
+      "learning_rate": 1.2e-05,
+      "loss": 0.5265,
+      "step": 536
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5488986968994141,
+      "eval_matthews_correlation": 0.3414642281150747,
+      "eval_runtime": 8.5064,
+      "eval_samples_per_second": 122.614,
+      "eval_steps_per_second": 7.759,
+      "step": 536
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 9.864019393920898,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.4161,
+      "step": 804
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5453676581382751,
+      "eval_matthews_correlation": 0.3451229816764349,
+      "eval_runtime": 8.5021,
+      "eval_samples_per_second": 122.676,
+      "eval_steps_per_second": 7.763,
+      "step": 804
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 5.3014726638793945,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.3324,
+      "step": 1072
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.574592113494873,
+      "eval_matthews_correlation": 0.3868717129142223,
+      "eval_runtime": 8.4987,
+      "eval_samples_per_second": 122.724,
+      "eval_steps_per_second": 7.766,
+      "step": 1072
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1340,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6082805841174528.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1072/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d37219932d78f454fedda9dcf9514306d19f0518eab06266cbde4f0fbddf00de
+size 4667