Training in progress, epoch 5

checkpoint-200/config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "google/fnet-base",
+  "architectures": [
+    "FNetForSequenceClassification"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "finetuning_task": "wnli",
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "not_entailment",
+    "1": "entailment"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "entailment": 1,
+    "not_entailment": 0
+  },
+  "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-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9f3707cf356216bf94f8045998ee0ff364c01be603134bdb1e28699b23f0156
+size 662962197

checkpoint-200/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c825b4c933a950d7d3f60ee6674d84bec214f9c3db0266f400941dccadf9409a
+size 331497705

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:958c9e2a682eede97b84ae0076803f0bb839eb5ed5a43542930dccb2e9fc49c3
+size 14503

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af2d9de141c4d7c893f366f03bc36eb1e21b38067602ae80b7cfc2d4d1ad8d24
+size 623

checkpoint-200/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-200/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-200/trainer_state.json

@@ -0,0 +1,91 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "global_step": 200,
+  "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": 0.7052,
+      "step": 40
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5633802816901409,
+      "eval_loss": 0.6902039051055908,
+      "eval_runtime": 0.5271,
+      "eval_samples_per_second": 134.707,
+      "eval_steps_per_second": 17.076,
+      "step": 40
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.2e-05,
+      "loss": 0.6957,
+      "step": 80
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.43661971830985913,
+      "eval_loss": 0.7012577056884766,
+      "eval_runtime": 0.5221,
+      "eval_samples_per_second": 135.995,
+      "eval_steps_per_second": 17.239,
+      "step": 80
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.6898,
+      "step": 120
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5352112676056338,
+      "eval_loss": 0.6898324489593506,
+      "eval_runtime": 0.5232,
+      "eval_samples_per_second": 135.691,
+      "eval_steps_per_second": 17.2,
+      "step": 120
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.6958,
+      "step": 160
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5633802816901409,
+      "eval_loss": 0.6874184608459473,
+      "eval_runtime": 0.5224,
+      "eval_samples_per_second": 135.906,
+      "eval_steps_per_second": 17.228,
+      "step": 160
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0,
+      "loss": 0.6982,
+      "step": 200
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5492957746478874,
+      "eval_loss": 0.6887156963348389,
+      "eval_runtime": 0.523,
+      "eval_samples_per_second": 135.751,
+      "eval_steps_per_second": 17.208,
+      "step": 200
+    }
+  ],
+  "max_steps": 200,
+  "num_train_epochs": 5,
+  "total_flos": 564638888601600.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0018d0bd5493d2abb91a78e7fe6494461f7f4d10944b54be5c94d6f6c54f5859
+size 2799

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fe832b99d1cedb1f93201b4d006be4b4ab822195e72e15f8fa2db8483e6361a
+oid sha256:c825b4c933a950d7d3f60ee6674d84bec214f9c3db0266f400941dccadf9409a
 size 331497705

runs/Sep16_18-42-03_patrick-general-gpu/events.out.tfevents.1631817737.patrick-general-gpu.194163.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45e7b48829e156ea65cddff0a729cc931e4b80a7143ac333269412b1c3e1f149
-size 5077
+oid sha256:a7c06557997450138a2e9f842f00f90c573d0f7e2cf8143b69d72cf762e34740
+size 5557