first commit, all the files added

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "distilbert-base-uncased-finetuned-sst-2-english",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "finetuning_task": "sst-2",
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "NEGATIVE",
+    "1": "POSITIVE"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "NEGATIVE": 0,
+    "POSITIVE": 1
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.20.1",
+  "vocab_size": 30522
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a1df273c7f0d4cb5fa35a5a355d9c935806889ac22bb2228aa64c269fec75d9
+size 535700065

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e3c780eb8009b9bc0b598f65d5c724ac7bfb7a2bdc3d985125b01298a4e7eae
+size 267854321

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0f2f74f7f558ab164dc08759a1603062c3c4de00034a78823223667cabbb076
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8d5cd2984885ae326d50c41c5c631bf58ec64cba465012f723e0614d1cf06ec
+size 623

trainer_state.json

@@ -0,0 +1,196 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9891196834817013,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "learning_rate": 1e-05,
+      "loss": 1.012,
+      "step": 100
+    },
+    {
+      "epoch": 0.1,
+      "eval_acc": 0.9251113585746102,
+      "eval_f1 score": 0.9269220320565063,
+      "eval_loss": 0.1983393132686615,
+      "eval_precision": 0.8821096173733195,
+      "eval_recall": 0.976531196336577,
+      "eval_runtime": 29.7994,
+      "eval_samples_per_second": 120.54,
+      "eval_steps_per_second": 3.792,
+      "step": 100
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 2e-05,
+      "loss": 0.0588,
+      "step": 200
+    },
+    {
+      "epoch": 0.2,
+      "eval_acc": 0.9974944320712695,
+      "eval_f1 score": 0.9974307736226092,
+      "eval_loss": 0.008134149946272373,
+      "eval_precision": 0.994874715261959,
+      "eval_recall": 1.0,
+      "eval_runtime": 29.7706,
+      "eval_samples_per_second": 120.656,
+      "eval_steps_per_second": 3.796,
+      "step": 200
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 3e-05,
+      "loss": 0.0094,
+      "step": 300
+    },
+    {
+      "epoch": 0.3,
+      "eval_acc": 0.9991648106904232,
+      "eval_f1 score": 0.9991421218187019,
+      "eval_loss": 0.0014619326684623957,
+      "eval_precision": 0.9982857142857143,
+      "eval_recall": 1.0,
+      "eval_runtime": 29.7156,
+      "eval_samples_per_second": 120.879,
+      "eval_steps_per_second": 3.803,
+      "step": 300
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 4e-05,
+      "loss": 0.003,
+      "step": 400
+    },
+    {
+      "epoch": 0.4,
+      "eval_acc": 0.9991648106904232,
+      "eval_f1 score": 0.9991411394217007,
+      "eval_loss": 0.0031169140711426735,
+      "eval_precision": 0.9994272623138603,
+      "eval_recall": 0.9988551803091014,
+      "eval_runtime": 29.7394,
+      "eval_samples_per_second": 120.782,
+      "eval_steps_per_second": 3.8,
+      "step": 400
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 5e-05,
+      "loss": 0.0033,
+      "step": 500
+    },
+    {
+      "epoch": 0.49,
+      "eval_acc": 0.998608017817372,
+      "eval_f1 score": 0.9985710202915119,
+      "eval_loss": 0.009261890314519405,
+      "eval_precision": 0.9971461187214612,
+      "eval_recall": 1.0,
+      "eval_runtime": 29.7575,
+      "eval_samples_per_second": 120.709,
+      "eval_steps_per_second": 3.797,
+      "step": 500
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 4.021526418786693e-05,
+      "loss": 0.0059,
+      "step": 600
+    },
+    {
+      "epoch": 0.59,
+      "eval_acc": 0.9997216035634744,
+      "eval_f1 score": 0.9997138769670958,
+      "eval_loss": 0.002947951899841428,
+      "eval_precision": 0.9994279176201373,
+      "eval_recall": 1.0,
+      "eval_runtime": 29.8118,
+      "eval_samples_per_second": 120.489,
+      "eval_steps_per_second": 3.79,
+      "step": 600
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 3.0430528375733857e-05,
+      "loss": 0.0025,
+      "step": 700
+    },
+    {
+      "epoch": 0.69,
+      "eval_acc": 1.0,
+      "eval_f1 score": 1.0,
+      "eval_loss": 0.00011875820928253233,
+      "eval_precision": 1.0,
+      "eval_recall": 1.0,
+      "eval_runtime": 29.727,
+      "eval_samples_per_second": 120.833,
+      "eval_steps_per_second": 3.801,
+      "step": 700
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.064579256360078e-05,
+      "loss": 0.0001,
+      "step": 800
+    },
+    {
+      "epoch": 0.79,
+      "eval_acc": 0.9994432071269488,
+      "eval_f1 score": 0.9994272623138604,
+      "eval_loss": 0.0010784701444208622,
+      "eval_precision": 1.0,
+      "eval_recall": 0.9988551803091014,
+      "eval_runtime": 29.689,
+      "eval_samples_per_second": 120.987,
+      "eval_steps_per_second": 3.806,
+      "step": 800
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.086105675146771e-05,
+      "loss": 0.0042,
+      "step": 900
+    },
+    {
+      "epoch": 0.89,
+      "eval_acc": 1.0,
+      "eval_f1 score": 1.0,
+      "eval_loss": 0.00021645698870997876,
+      "eval_precision": 1.0,
+      "eval_recall": 1.0,
+      "eval_runtime": 29.7217,
+      "eval_samples_per_second": 120.855,
+      "eval_steps_per_second": 3.802,
+      "step": 900
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.076320939334638e-06,
+      "loss": 0.0037,
+      "step": 1000
+    },
+    {
+      "epoch": 0.99,
+      "eval_acc": 1.0,
+      "eval_f1 score": 1.0,
+      "eval_loss": 0.0003033815883100033,
+      "eval_precision": 1.0,
+      "eval_recall": 1.0,
+      "eval_runtime": 29.7302,
+      "eval_samples_per_second": 120.82,
+      "eval_steps_per_second": 3.801,
+      "step": 1000
+    }
+  ],
+  "max_steps": 1011,
+  "num_train_epochs": 1,
+  "total_flos": 4238956756992000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13e47fbc29a305256c2ef1fe242107315741a33435bfeded3027f2780b50e58a
+size 3247