Training in progress, epoch 5

checkpoint-200/config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "bert-base-cased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "finetuning_task": "wnli",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "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": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.11.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de880f7a9fc27e0cde054bd5dc93cd1d001badc310c2be4bc4a925a9b6c3255d
+size 866610781

checkpoint-200/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd13885fe088da7af9ef9db9d28612699bb6c238ca4e58ea0bcf3713f12a07bd
+size 433331373

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75fcb94f650bfb3f83f0aa7e6aa5780886fe98a194def868b04913481a2a15c0
+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": "[MASK]"}

checkpoint-200/tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-cased", "tokenizer_class": "BertTokenizer"}

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": 0.7299,
+      "step": 40
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5633802816901409,
+      "eval_loss": 0.6923056840896606,
+      "eval_runtime": 0.73,
+      "eval_samples_per_second": 97.265,
+      "eval_steps_per_second": 12.329,
+      "step": 40
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.2e-05,
+      "loss": 0.6982,
+      "step": 80
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.38028169014084506,
+      "eval_loss": 0.7026631832122803,
+      "eval_runtime": 0.7338,
+      "eval_samples_per_second": 96.754,
+      "eval_steps_per_second": 12.265,
+      "step": 80
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.6972,
+      "step": 120
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.4507042253521127,
+      "eval_loss": 0.7005189657211304,
+      "eval_runtime": 0.7321,
+      "eval_samples_per_second": 96.982,
+      "eval_steps_per_second": 12.293,
+      "step": 120
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.6992,
+      "step": 160
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5352112676056338,
+      "eval_loss": 0.6976626515388489,
+      "eval_runtime": 0.7339,
+      "eval_samples_per_second": 96.738,
+      "eval_steps_per_second": 12.263,
+      "step": 160
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0,
+      "loss": 0.699,
+      "step": 200
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.4647887323943662,
+      "eval_loss": 0.6995509266853333,
+      "eval_runtime": 0.7321,
+      "eval_samples_per_second": 96.976,
+      "eval_steps_per_second": 12.293,
+      "step": 200
+    }
+  ],
+  "max_steps": 200,
+  "num_train_epochs": 5,
+  "total_flos": 835377600768000.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04198b57eef90f34dae9a352cd24db86f2af39af571e6944ddb87456406dcc51
+size 2799

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:362411023988cb11f148076484eb6cff51abd2e3dfa5d70eab744fb9aa240909
+oid sha256:dd13885fe088da7af9ef9db9d28612699bb6c238ca4e58ea0bcf3713f12a07bd
 size 433331373

runs/Sep16_17-01-08_patrick-general-gpu/events.out.tfevents.1631811685.patrick-general-gpu.176909.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18f6bc0de1b0a348799eaa5cfe94a6ad86be0109c752e7d98947bbad15fcdbc0
-size 5139
+oid sha256:4ede4e75f14c18ec42f0ec26e7ead74b96baa9b739267718c01dd4a2ca00abd0
+size 5619