Training in progress, epoch 3

checkpoint-6414/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-6414/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:519d399e171a012994ccce3ab9887e9afc33dd56eff3af2c78c0d813c5a959b5
+size 1895696981

checkpoint-6414/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81249b0d27cddd42b66cc24109ff25d252ca2a434279db734502f0e7da638d69
+size 947877033

checkpoint-6414/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccb46f4b7d44eaed90819f3e91fee2f01af644625f3152f3618c58b96dab6a95
+size 14503

checkpoint-6414/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86642ce7c252487cfeeb5babe32f76b49d66747d74e741e5949756c534404d01
+size 623

checkpoint-6414/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-6414/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-6414/trainer_state.json

@@ -0,0 +1,61 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 6414,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 7.408177408177407e-05,
+      "loss": 0.6408,
+      "step": 2138
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.7329378128051758,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 22.7321,
+      "eval_samples_per_second": 45.882,
+      "eval_steps_per_second": 5.763,
+      "step": 2138
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3.704088704088704e-05,
+      "loss": 0.6589,
+      "step": 4276
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6311050057411194,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 22.7597,
+      "eval_samples_per_second": 45.827,
+      "eval_steps_per_second": 5.756,
+      "step": 4276
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.6467,
+      "step": 6414
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6554446816444397,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 22.7256,
+      "eval_samples_per_second": 45.895,
+      "eval_steps_per_second": 5.764,
+      "step": 6414
+    }
+  ],
+  "max_steps": 6414,
+  "num_train_epochs": 3,
+  "total_flos": 1.6048929796061184e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-6414/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86815fd44d40e13e4091bbc8889512f9aedd06f2b30d63cfd01d96a1aa69432c
+size 2799

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c954b9cbf43c9ee57d606144921472345c7a799db2d6917b15d7a5a8906f623a
+oid sha256:81249b0d27cddd42b66cc24109ff25d252ca2a434279db734502f0e7da638d69
 size 947877033

runs/Oct10_07-25-26_patrick-general-gpu/events.out.tfevents.1633850743.patrick-general-gpu.98066.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec6099d939377cdc3a0145b35970e18e440a0adc9e10d2c15ae7166e9be6f42e
-size 4257
+oid sha256:c1cb8e887d24367e8ee7840322d8229673fe9b9a7f57993d6d9b9afc05fce2cd
+size 4749