Training in progress, epoch 4

checkpoint-3668/config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "google/fnet-large",
+  "architectures": [
+    "FNetForSequenceClassification"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "finetuning_task": "mrpc",
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "not_equivalent",
+    "1": "equivalent"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "equivalent": 1,
+    "not_equivalent": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "fnet",
+  "num_hidden_layers": 24,
+  "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-3668/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d6611f64527a4aac6403b1e00adf56c555f7f385e728ea13267c316933f37fc
+size 1895696981

checkpoint-3668/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d367b6948e891cb872f98afb73f9a88e723aedc43d85d6a9bd5896aec073576
+size 947877033

checkpoint-3668/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70010efb3ac9f3cad893a2e0139bca7c063b4380e3c630eb17285bf0f185b944
+size 14503

checkpoint-3668/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aff0894304e2fef9b08254d2b9e80857b7723e16fb0299d164d287cb7e9a1547
+size 623

checkpoint-3668/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-3668/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": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "model_max_length": 512, "special_tokens_map_file": "/home/gunjan/.cache/huggingface/transformers/9a50cd9b3771023230b1128ab5e112461bf36f5826d5f7eb654348e956979a54.a2cfb41d43ad2ac50fa89998bfa88393398e3bb3439ee99e1b00933bce2eb1ba", "name_or_path": "google/fnet-large", "tokenizer_class": "FNetTokenizer"}

checkpoint-3668/trainer_state.json

@@ -0,0 +1,84 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "global_step": 3668,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.5656,
+      "step": 917
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7843137254901961,
+      "eval_combined_score": 0.821189120809614,
+      "eval_f1": 0.8580645161290321,
+      "eval_loss": 0.699867844581604,
+      "eval_runtime": 8.9164,
+      "eval_samples_per_second": 45.758,
+      "eval_steps_per_second": 5.72,
+      "step": 917
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.2e-05,
+      "loss": 0.3874,
+      "step": 1834
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8088235294117647,
+      "eval_combined_score": 0.8389755230951441,
+      "eval_f1": 0.8691275167785235,
+      "eval_loss": 0.727956235408783,
+      "eval_runtime": 8.877,
+      "eval_samples_per_second": 45.961,
+      "eval_steps_per_second": 5.745,
+      "step": 1834
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.1627,
+      "step": 2751
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8161764705882353,
+      "eval_combined_score": 0.8471126255380201,
+      "eval_f1": 0.878048780487805,
+      "eval_loss": 1.127362847328186,
+      "eval_runtime": 8.9375,
+      "eval_samples_per_second": 45.65,
+      "eval_steps_per_second": 5.706,
+      "step": 2751
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.0751,
+      "step": 3668
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8333333333333334,
+      "eval_combined_score": 0.8601882613510521,
+      "eval_f1": 0.8870431893687708,
+      "eval_loss": 1.0288920402526855,
+      "eval_runtime": 8.9056,
+      "eval_samples_per_second": 45.814,
+      "eval_steps_per_second": 5.727,
+      "step": 3668
+    }
+  ],
+  "max_steps": 4585,
+  "num_train_epochs": 5,
+  "total_flos": 9179039409340416.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3668/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:657099f26b9ebf81238e7bf9cc628151eb18005ffc77e7bb727ff2354dea4627
+size 2799

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89a711959fd3c7e046316df744c6fa95f149f69aaf2c3196bfbd41fe9ebe47e2
+oid sha256:2d367b6948e891cb872f98afb73f9a88e723aedc43d85d6a9bd5896aec073576
 size 947877033

runs/Sep22_08-35-16_patrick-general-gpu/events.out.tfevents.1632299743.patrick-general-gpu.791924.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5acc7a9b6288a48e47268a9577242695be685def62b08929b9d1cd9ee4485a90
-size 4940
+oid sha256:45c6246b5ffcf2601834df13e76cc5a0f30037041e92f45509773ce930990a62
+size 5524