Training in progress, epoch 3

checkpoint-19641/config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "google/fnet-base",
+  "architectures": [
+    "FNetForSequenceClassification"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "finetuning_task": "qnli",
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "entailment",
+    "1": "not_entailment"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "entailment": 0,
+    "not_entailment": 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-19641/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:785bd7966e40d943b13595bcc09955869bae75127d8c036ec95d185b76f8da19
+size 662962261

checkpoint-19641/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d94c516d1604a2f02ed53326286ee4442558948de13ea454baddf6fb357eeb9
+size 331497705

checkpoint-19641/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8877f53f28e3377eca887f40add2baf9925b97297a91c1dca1bbe3946eea783d
+size 14503

checkpoint-19641/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf713a80a9c8fd994ed1ace14615354b3454f45dc7a0a20bb4f953559263f7a0
+size 623

checkpoint-19641/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-19641/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-19641/trainer_state.json

@@ -0,0 +1,61 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 19641,
+  "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": 0.4597,
+      "step": 6547
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8411129416071755,
+      "eval_loss": 0.37129390239715576,
+      "eval_runtime": 39.7582,
+      "eval_samples_per_second": 137.406,
+      "eval_steps_per_second": 17.179,
+      "step": 6547
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.3252,
+      "step": 13094
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8420281896393923,
+      "eval_loss": 0.378091961145401,
+      "eval_runtime": 39.5864,
+      "eval_samples_per_second": 138.002,
+      "eval_steps_per_second": 17.253,
+      "step": 13094
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.2243,
+      "step": 19641
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8438586857038257,
+      "eval_loss": 0.4746157228946686,
+      "eval_runtime": 39.7955,
+      "eval_samples_per_second": 137.277,
+      "eval_steps_per_second": 17.163,
+      "step": 19641
+    }
+  ],
+  "max_steps": 19641,
+  "num_train_epochs": 3,
+  "total_flos": 5.588217742563533e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-19641/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e2cf8e9c9c5b47af6e05197b1f1f61e8d510e42060c8bdffd8bdb04e11d2117
+size 2799

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:309efad5ca39972bd302b81f63881446144375ae2ac4528e6ea4cabc724aa113
+oid sha256:9d94c516d1604a2f02ed53326286ee4442558948de13ea454baddf6fb357eeb9
 size 331497705

runs/Sep17_18-08-55_patrick-general-gpu/events.out.tfevents.1631902166.patrick-general-gpu.299149.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d61093893640784e5695aa538d22686828e6693781fd9cd8d6b7424fb9da743
-size 4144
+oid sha256:c0e2db01b1d9a48bb3f80a5a7ebfffc960f550ae03b18c4fcb7ced91243ed102
+size 4633