Training in progress, epoch 3

checkpoint-12630/config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "google/fnet-base",
+  "architectures": [
+    "FNetForSequenceClassification"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "finetuning_task": "sst2",
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "negative",
+    "1": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "negative": 0,
+    "positive": 1
+  },
+  "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-12630/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0172d03ea98100c526b53f859ed4bf2225e4d70d6bd1bea95640cc3d4d67ad09
+size 662962261

checkpoint-12630/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e262ed3190492c449f147b269b67d92687ac8bb7eb3db9e6483e23b0359564f0
+size 331497705

checkpoint-12630/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f2af6fe84ff52bb30008cceaf033bd0cadbf0a0f33eb58df36218ace19c193b
+size 14503

checkpoint-12630/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55d12134d4d1d0b70b5996eb59099da9fc12a4d3548d43e6aba424b4512591b1
+size 623

checkpoint-12630/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-12630/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-12630/trainer_state.json

@@ -0,0 +1,61 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 12630,
+  "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": 0.2956,
+      "step": 4210
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8818807339449541,
+      "eval_loss": 0.3128007650375366,
+      "eval_runtime": 6.3233,
+      "eval_samples_per_second": 137.902,
+      "eval_steps_per_second": 17.238,
+      "step": 4210
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.1746,
+      "step": 8420
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8979357798165137,
+      "eval_loss": 0.38503018021583557,
+      "eval_runtime": 6.3387,
+      "eval_samples_per_second": 137.568,
+      "eval_steps_per_second": 17.196,
+      "step": 8420
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.1204,
+      "step": 12630
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8944954128440367,
+      "eval_loss": 0.4674423038959503,
+      "eval_runtime": 6.3626,
+      "eval_samples_per_second": 137.05,
+      "eval_steps_per_second": 17.131,
+      "step": 12630
+    }
+  ],
+  "max_steps": 12630,
+  "num_train_epochs": 3,
+  "total_flos": 3.5931840480405504e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-12630/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a45e8f8a6be9a994d34ead5bf4a34c6c366dd946a5f7bcf5b8811be8ffa4f9c
+size 2799

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e1d430a37d7227f2ff689dfe9836ff507b99cf6e911a7b78439d25332b54598
+oid sha256:e262ed3190492c449f147b269b67d92687ac8bb7eb3db9e6483e23b0359564f0
 size 331497705

runs/Sep19_08-31-53_patrick-general-gpu/events.out.tfevents.1632040336.patrick-general-gpu.480409.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07bec62a368f913a44fd6366ace888d0066df49e7b96ea538acd30712c971b10
-size 4128
+oid sha256:6aa17276d922ebd22b9f235d1392d85f025932f019949918d4e0d87821de00c5
+size 4608