model

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "bert-base-cased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4
+  },
+  "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": "4.28.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd9c94b99e78e8a226738947ad87a943c491e70bebbe4d726a0f09b940943d9d
+size 32555

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab58200c77bca47202aa3ce27e256e59eada8401c6de8de8945b5ad2ed49ac17
+size 433329269

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0e0a2d422817e3e0f564fd85a32f5b018638912386a99b6269ddd68a71a1811
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:975255733c2a3d175b1cba829d893071860772a4ea5d3dc231562601ce2d570b
+size 627

trainer_state.json

@@ -0,0 +1,126 @@
+{
+  "best_metric": 1.0495396852493286,
+  "best_model_checkpoint": "test_/checkpoint-1125",
+  "epoch": 5.0,
+  "global_step": 1875,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.001,
+      "loss": 1.1181,
+      "step": 375
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.1535536050796509,
+      "eval_micro_f1": 0.6113333333333333,
+      "eval_runtime": 126.2386,
+      "eval_samples_per_second": 23.765,
+      "eval_steps_per_second": 0.372,
+      "eval_unavg_f1": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.7587918907736864
+      ],
+      "step": 375
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.001,
+      "loss": 1.0798,
+      "step": 750
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.0706086158752441,
+      "eval_micro_f1": 0.6136666666666667,
+      "eval_runtime": 122.9816,
+      "eval_samples_per_second": 24.394,
+      "eval_steps_per_second": 0.382,
+      "eval_unavg_f1": [
+        0.006644518272425249,
+        0.0,
+        0.028985507246376815,
+        0.058577405857740586,
+        0.7663512092534175
+      ],
+      "step": 750
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.001,
+      "loss": 1.0675,
+      "step": 1125
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.0495396852493286,
+      "eval_micro_f1": 0.624,
+      "eval_runtime": 131.2327,
+      "eval_samples_per_second": 22.86,
+      "eval_steps_per_second": 0.358,
+      "eval_unavg_f1": [
+        0.1888888888888889,
+        0.0,
+        0.015936254980079684,
+        0.1500815660685155,
+        0.7806367204535543
+      ],
+      "step": 1125
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.001,
+      "loss": 1.0589,
+      "step": 1500
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.0587749481201172,
+      "eval_micro_f1": 0.613,
+      "eval_runtime": 124.3983,
+      "eval_samples_per_second": 24.116,
+      "eval_steps_per_second": 0.378,
+      "eval_unavg_f1": [
+        0.025889967637540454,
+        0.0,
+        0.0,
+        0.21601016518424399,
+        0.7831729693443723
+      ],
+      "step": 1500
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.001,
+      "loss": 1.046,
+      "step": 1875
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 1.053810715675354,
+      "eval_micro_f1": 0.6356666666666667,
+      "eval_runtime": 131.9922,
+      "eval_samples_per_second": 22.729,
+      "eval_steps_per_second": 0.356,
+      "eval_unavg_f1": [
+        0.4607046070460704,
+        0.0,
+        0.0,
+        0.1947449768160742,
+        0.801148600143575
+      ],
+      "step": 1875
+    }
+  ],
+  "max_steps": 3750,
+  "num_train_epochs": 10,
+  "total_flos": 1.2524308467099072e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:900496fa0e33f70e39e30210a4a6e5ed70be9f7df0410fdb1f48ae99ef5d3404
+size 3515