Training in progress, epoch 4

checkpoint-8552/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-8552/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a2ac5c8e3edc06a1348f4f4c5274c3dc78e7e33d1666ce9c900740d3a95180c
+size 1895696981

checkpoint-8552/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2026be213de9e967e07d8a374455c2c3b55a79dd7a7f1acfa394dc003594143
+size 947877033

checkpoint-8552/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f247af074dbaa1be03637760c76d9fc7323467179c4207dd46233699c320ae10
+size 14503

checkpoint-8552/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0226777751c14a204a52d00d817f7bbbb439b5d4f71c2052cc4004db96ca9f9f
+size 623

checkpoint-8552/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-8552/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-8552/trainer_state.json

@@ -0,0 +1,76 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "global_step": 8552,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.5566666666666666e-05,
+      "loss": 0.6212,
+      "step": 2138
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6539720296859741,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 22.7284,
+      "eval_samples_per_second": 45.89,
+      "eval_steps_per_second": 5.764,
+      "step": 2138
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 2.6700000000000002e-05,
+      "loss": 0.62,
+      "step": 4276
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6409146785736084,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 22.7182,
+      "eval_samples_per_second": 45.91,
+      "eval_steps_per_second": 5.766,
+      "step": 4276
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.783333333333333e-05,
+      "loss": 0.6182,
+      "step": 6414
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6234332919120789,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 22.7216,
+      "eval_samples_per_second": 45.904,
+      "eval_steps_per_second": 5.765,
+      "step": 6414
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 8.966666666666667e-06,
+      "loss": 0.6181,
+      "step": 8552
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.6234201192855835,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 22.7101,
+      "eval_samples_per_second": 45.927,
+      "eval_steps_per_second": 5.768,
+      "step": 8552
+    }
+  ],
+  "max_steps": 10690,
+  "num_train_epochs": 5,
+  "total_flos": 2.139857306141491e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-8552/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88518180b48b7d86e915e89c08d25d45c9dd551905fa41d34c4933dfadcb9385
+size 2799

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd40bce63a5c383faa601fcd60966460e58f97aa6d6bfa79c0992789faf8671a
+oid sha256:f2026be213de9e967e07d8a374455c2c3b55a79dd7a7f1acfa394dc003594143
 size 947877033

runs/Oct10_19-39-15_patrick-general-gpu/events.out.tfevents.1633894776.patrick-general-gpu.131003.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75e58a166d46410eb2b539f0b1117ebb600740ac3cb5320c43121d6051dfa722
-size 4752
+oid sha256:14a1c6d365b80f31ffc2e589199d8806015dc9bed6170f9211b0a62ce02ebaed
+size 5244