Training in progress, epoch 3

checkpoint-468/config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "google/fnet-base",
+  "architectures": [
+    "FNetForSequenceClassification"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "finetuning_task": "rte",
+  "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-468/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35205666cc71f65d1d67f956b4708750ffa743be4bf2455935f439f718f2ebec
+size 662962261

checkpoint-468/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d6e001f19e0ad53bbe482910081fc88ece828710d3fac64b016231386135e23
+size 331497705

checkpoint-468/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ffb4b1f5d5749177f7362512bb9e2072ca8460ef7fdfb3759d56b1f75fb0189
+size 14503

checkpoint-468/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15a5bf2f5d5fb5f4bf00355a36dde18b1c59d2735f963718d2986d0692f55eae
+size 623

checkpoint-468/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-468/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-468/trainer_state.json

@@ -0,0 +1,61 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 468,
+  "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": 0.6829,
+      "step": 156
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5703971119133574,
+      "eval_loss": 0.6657100915908813,
+      "eval_runtime": 2.0131,
+      "eval_samples_per_second": 137.6,
+      "eval_steps_per_second": 17.386,
+      "step": 156
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.6174,
+      "step": 312
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6101083032490975,
+      "eval_loss": 0.6784032583236694,
+      "eval_runtime": 2.013,
+      "eval_samples_per_second": 137.609,
+      "eval_steps_per_second": 17.387,
+      "step": 312
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.5141,
+      "step": 468
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.628158844765343,
+      "eval_loss": 0.6978281736373901,
+      "eval_runtime": 2.0128,
+      "eval_samples_per_second": 137.616,
+      "eval_steps_per_second": 17.388,
+      "step": 468
+    }
+  ],
+  "max_steps": 468,
+  "num_train_epochs": 3,
+  "total_flos": 1328457479639040.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-468/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2785b0a5856d6dcded05366f24390f17de2bc55f955abf2c62f58cd45feda2ba
+size 2735

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:703325ffcce92834a555de711f8d2ea5175af28d0cb351b6d0eb917c1e40a72e
+oid sha256:9d6e001f19e0ad53bbe482910081fc88ece828710d3fac64b016231386135e23
 size 331497705

runs/Sep19_05-47-04_patrick-general-gpu/events.out.tfevents.1632030438.patrick-general-gpu.457696.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e38f1de6ffcdbb07eab6c410618378017bdf30f0724ff009108005b33a1ee155
-size 4140
+oid sha256:c9bc8feff1907d548c781d25e898b20690750cf8c160312ef8e882aed9cd34ea
+size 4620