Training in progress, epoch 3

checkpoint-690/config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "google/fnet-base",
+  "architectures": [
+    "FNetForSequenceClassification"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "finetuning_task": "mrpc",
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "not_equivalent",
+    "1": "equivalent"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "equivalent": 1,
+    "not_equivalent": 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-690/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4e88be976f69c3bb4f2f5d866e068633b491ba98e428ba834ce2f22bdbee590
+size 662962261

checkpoint-690/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2f4d4d9490f4b55b3077ada545046c09522ef4ee6fbd7cdb12fea3f0f63c6d2
+size 331497705

checkpoint-690/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98d89195ac304872f96ba768ed654f5c8b07c5ad8598bcd661e152cc8a067582
+size 14503

checkpoint-690/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0cf3ce8e7365e59eba2550cf0339839704f78b96897c1e66c20f680f3730989
+size 623

checkpoint-690/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-690/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-690/trainer_state.json

@@ -0,0 +1,67 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 690,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.544,
+      "step": 230
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7328431372549019,
+      "eval_combined_score": 0.7813981676914135,
+      "eval_f1": 0.8299531981279251,
+      "eval_loss": 0.5272471308708191,
+      "eval_runtime": 2.9626,
+      "eval_samples_per_second": 137.716,
+      "eval_steps_per_second": 17.215,
+      "step": 230
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.2e-05,
+      "loss": 0.4034,
+      "step": 460
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7254901960784313,
+      "eval_combined_score": 0.7776387150604923,
+      "eval_f1": 0.8297872340425533,
+      "eval_loss": 0.6210632920265198,
+      "eval_runtime": 2.9625,
+      "eval_samples_per_second": 137.721,
+      "eval_steps_per_second": 17.215,
+      "step": 460
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.2602,
+      "step": 690
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7230392156862745,
+      "eval_combined_score": 0.7768119616662257,
+      "eval_f1": 0.830584707646177,
+      "eval_loss": 0.9109526872634888,
+      "eval_runtime": 2.9562,
+      "eval_samples_per_second": 138.014,
+      "eval_steps_per_second": 17.252,
+      "step": 690
+    }
+  ],
+  "max_steps": 1150,
+  "num_train_epochs": 5,
+  "total_flos": 1956940576432128.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-690/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f60be56a92d65e72efa4b0a6aeb22bf463a1b2d3bd996251ddb8045bd4fad5f
+size 2799

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92c9c356fe8da5f8df41c039afc60c9b5edcd50eb9b82c9162fbba7ae4090841
+oid sha256:a2f4d4d9490f4b55b3077ada545046c09522ef4ee6fbd7cdb12fea3f0f63c6d2
 size 331497705

runs/Sep16_17-30-11_patrick-general-gpu/events.out.tfevents.1631813426.patrick-general-gpu.181934.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a119a1933e122717278b2f168e949a8e67f4b334fb025658da3014eaa0212915
-size 4352
+oid sha256:2d2bfeddac12b1c77bd79c9e7676fb38be15a9687ff8606290ff2af5eeb92806
+size 4936