Training in progress, epoch 3

checkpoint-1080/config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "google/fnet-base",
+  "architectures": [
+    "FNetForSequenceClassification"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "finetuning_task": "stsb",
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 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-1080/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e735253a514cc2c0f79aaf4e3edf13c3056ad22d55145e0843ca7dc777472009
+size 662956117

checkpoint-1080/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de4eebdaf76581e9d2b1591ea760fbfe79f6f5829477e3d183d2c6bff5e8839a
+size 331494633

checkpoint-1080/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c41e9f52a3754df91fa341960dc35e16bc94805466ea42f583bd94d97e82a53
+size 14503

checkpoint-1080/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:527295045d2586065b1903e97996e4dbfc999e3944d447aefd0d55843d2c92d2
+size 623

checkpoint-1080/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-1080/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-1080/trainer_state.json

@@ -0,0 +1,67 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 1080,
+  "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": 1.5473,
+      "step": 360
+    },
+    {
+      "epoch": 1.0,
+      "eval_combined_score": 0.8120419393156919,
+      "eval_loss": 0.7750807404518127,
+      "eval_pearson": 0.8115414805311705,
+      "eval_runtime": 10.8984,
+      "eval_samples_per_second": 137.634,
+      "eval_spearmanr": 0.8125423981002132,
+      "eval_steps_per_second": 17.25,
+      "step": 360
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.6954,
+      "step": 720
+    },
+    {
+      "epoch": 2.0,
+      "eval_combined_score": 0.8145095741908042,
+      "eval_loss": 0.8717353343963623,
+      "eval_pearson": 0.8159860577723805,
+      "eval_runtime": 10.909,
+      "eval_samples_per_second": 137.502,
+      "eval_spearmanr": 0.8130330906092277,
+      "eval_steps_per_second": 17.234,
+      "step": 720
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.4828,
+      "step": 1080
+    },
+    {
+      "epoch": 3.0,
+      "eval_combined_score": 0.8237743551253471,
+      "eval_loss": 0.789396345615387,
+      "eval_pearson": 0.825608960477892,
+      "eval_runtime": 10.9264,
+      "eval_samples_per_second": 137.282,
+      "eval_spearmanr": 0.8219397497728022,
+      "eval_steps_per_second": 17.206,
+      "step": 1080
+    }
+  ],
+  "max_steps": 1080,
+  "num_train_epochs": 3,
+  "total_flos": 3067148834731008.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1080/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e5c6eb180bb5162515a2b4e6e16c49ba285a05c5fb2d9ca9fa6f6e3fa827889
+size 2799

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:575ac348a486eb875c9b5018bcf08e8961e9d2f8525d87facacf5f120da6568d
+oid sha256:de4eebdaf76581e9d2b1591ea760fbfe79f6f5829477e3d183d2c6bff5e8839a
 size 331494633

runs/Sep19_15-39-26_patrick-general-gpu/events.out.tfevents.1632065982.patrick-general-gpu.509410.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:856395f3745ee8c6860fb98dbf3e3dcdf5162fd0597db224e9309fd024fd019b
-size 4306
+oid sha256:a6f491d2df56edb97594ba0071576f5b4ae2cbb6f900c10b4e13a2f78adaa57c
+size 4896