Training in progress, epoch 5

checkpoint-10690/config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "google/fnet-large",
+  "actual_seq_length": 512,
+  "architectures": [
+    "FNetForSequenceClassification"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "finetuning_task": "cola",
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "unacceptable",
+    "1": "acceptable"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "acceptable": 1,
+    "unacceptable": 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_fft": true,
+  "use_latest": false,
+  "use_tpu_fourier_optimizations": false,
+  "vocab_size": 32000
+}

checkpoint-10690/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d270aedf328aaa438673594da4826d9f31a31d7c4af519ee7eb696657c62ce1
+size 1895696981

checkpoint-10690/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c4fcd4ee96c83fc27adff4630d4bfbb76378d74a487794ada817222a3366845
+size 947877033

checkpoint-10690/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac6127405939f4fdefc0921a0df1c32c4ed2391a9a1ec5a630262dc561211b3d
+size 14503

checkpoint-10690/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72dddf8b2128e28cd54b474628338ca3ce3aa8dd5f435a999e6a514c71edf483
+size 623

checkpoint-10690/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-10690/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-10690/trainer_state.json

@@ -0,0 +1,91 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "global_step": 10690,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.6700000000000002e-05,
+      "loss": 0.6345,
+      "step": 2138
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6611062288284302,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 22.7702,
+      "eval_samples_per_second": 45.805,
+      "eval_steps_per_second": 5.753,
+      "step": 2138
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.3400000000000002e-05,
+      "loss": 0.6359,
+      "step": 4276
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6839953064918518,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 22.7541,
+      "eval_samples_per_second": 45.838,
+      "eval_steps_per_second": 5.757,
+      "step": 4276
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1e-07,
+      "loss": 0.6331,
+      "step": 6414
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6499619483947754,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 22.8768,
+      "eval_samples_per_second": 45.592,
+      "eval_steps_per_second": 5.726,
+      "step": 6414
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 8.966666666666667e-06,
+      "loss": 0.6342,
+      "step": 8552
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.6344217658042908,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 22.7688,
+      "eval_samples_per_second": 45.808,
+      "eval_steps_per_second": 5.753,
+      "step": 8552
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 1e-07,
+      "loss": 0.6312,
+      "step": 10690
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.6500726342201233,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 22.7519,
+      "eval_samples_per_second": 45.842,
+      "eval_steps_per_second": 5.758,
+      "step": 10690
+    }
+  ],
+  "max_steps": 10690,
+  "num_train_epochs": 5,
+  "total_flos": 2.674821632676864e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-10690/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2b3cbcd454a5a4d6468403c35afb445edf3e467c93e6c69346c08e194b71c3f
+size 2799

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a22d40964c44ad4b1e7148bacb1f54f2502520f8bcff83cc80ae3026d707ea6
+oid sha256:1c4fcd4ee96c83fc27adff4630d4bfbb76378d74a487794ada817222a3366845
 size 947877033

runs/Oct10_19-05-40_patrick-general-gpu/events.out.tfevents.1633892756.patrick-general-gpu.125503.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b464946c39a534b7f3f52dc9fafca5932b13dd6e5c16b79b572b61d47d7800dc
-size 3768
+oid sha256:1c948bd98023c44aa14a8569fddadf0202d6d271d154cb83234eaf39d0811306
+size 4260