Training in progress, epoch 3

checkpoint-73632/config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "google/fnet-base",
+  "architectures": [
+    "FNetForSequenceClassification"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "finetuning_task": "mnli",
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "entailment",
+    "1": "neutral",
+    "2": "contradiction"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "contradiction": 2,
+    "entailment": 0,
+    "neutral": 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-73632/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25f9786c7c099a5d0c59c666b6a4bc778dc0f5ff52025d337a81dc68218fec5b
+size 662968661

checkpoint-73632/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a4d683ac587416a9cc504b18bf005fece90f0f4b360fc5ab2b5d4e1912056ed
+size 331500777

checkpoint-73632/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87bfbaa6f56432c2439828796c9f9e93fd49a4f4ad9341a751f62eda7ababb6f
+size 14503

checkpoint-73632/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ea4616a97724a0d5e0c699813c0051393c4215c930dfd1076ec80eac04682b4
+size 623

checkpoint-73632/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-73632/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-73632/trainer_state.json

@@ -0,0 +1,61 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 73632,
+  "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": 0.7143,
+      "step": 24544
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7503820682628629,
+      "eval_loss": 0.6168540120124817,
+      "eval_runtime": 71.4698,
+      "eval_samples_per_second": 137.331,
+      "eval_steps_per_second": 17.168,
+      "step": 24544
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.5407,
+      "step": 49088
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7627101375445746,
+      "eval_loss": 0.6218484044075012,
+      "eval_runtime": 71.2675,
+      "eval_samples_per_second": 137.72,
+      "eval_steps_per_second": 17.217,
+      "step": 49088
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.4178,
+      "step": 73632
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7657666836474784,
+      "eval_loss": 0.6564478278160095,
+      "eval_runtime": 71.6262,
+      "eval_samples_per_second": 137.031,
+      "eval_steps_per_second": 17.131,
+      "step": 73632
+    }
+  ],
+  "max_steps": 73632,
+  "num_train_epochs": 3,
+  "total_flos": 2.095159996537344e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-73632/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec7074326752f68eaba5eb9d6552280139883b78c4355f1f89c5ffc904d6a668
+size 2799

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3e1379cea1fb82ba15fc753d7bedece6095e93c38e5d2bb531282dc35593217
+oid sha256:9a4d683ac587416a9cc504b18bf005fece90f0f4b360fc5ab2b5d4e1912056ed
 size 331500777

runs/Sep17_07-10-01_patrick-general-gpu/events.out.tfevents.1631862669.patrick-general-gpu.234538.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35efd6a769029c1a911c0c82ccdc6fce2bad8efbeedf7d3eabb822eb8178f23c
-size 4198
+oid sha256:3871425bb15e7db46c7147304c2c5cd013aee069a74aa20784346ab0e17185db
+size 4687