Upload 10 files

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/home/vera/Desktop/sst_movie_reviews/sst-TAPT-bert-large-continue",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.22.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0829508767711a32a7b3407530152c4015bb2a390b78449ed6868ddeb850132
+size 2681380253

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48347d8387bcde74d443730e5a4a3b241a4826d0ad844f07f91ec9f7414d7d58
+size 1340711725

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd9a9957442eed6a503ce4ce093fa8a50609104db077223260ae7f86b1a6609c
+size 15523

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e60258e9108ffab60da59fa90b3efa9a2ff8ccdb3d81b236c9ad41f10148a7d
+size 623

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "/home/vera/Desktop/sst_movie_reviews/sst-TAPT-bert-large-continue",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]",
+  "use_fast": true
+}

trainer_state.json

@@ -0,0 +1,178 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "global_step": 6070,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.8352553542009887e-05,
+      "loss": 0.2073,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.9750730374140043,
+      "eval_loss": 0.08468761295080185,
+      "eval_runtime": 237.9595,
+      "eval_samples_per_second": 326.173,
+      "eval_steps_per_second": 2.551,
+      "step": 607
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 1.6705107084019773e-05,
+      "loss": 0.1121,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.986432880313593,
+      "eval_loss": 0.04612227529287338,
+      "eval_runtime": 237.9341,
+      "eval_samples_per_second": 326.208,
+      "eval_steps_per_second": 2.551,
+      "step": 1214
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 1.5057660626029655e-05,
+      "loss": 0.0823,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.9916420153073202,
+      "eval_loss": 0.02950172871351242,
+      "eval_runtime": 237.7454,
+      "eval_samples_per_second": 326.467,
+      "eval_steps_per_second": 2.553,
+      "step": 1821
+    },
+    {
+      "epoch": 3.29,
+      "learning_rate": 1.341021416803954e-05,
+      "loss": 0.0593,
+      "step": 2000
+    },
+    {
+      "epoch": 4.0,
+      "eval_f1": 0.9947999625222524,
+      "eval_loss": 0.01778862066566944,
+      "eval_runtime": 237.6987,
+      "eval_samples_per_second": 326.531,
+      "eval_steps_per_second": 2.554,
+      "step": 2428
+    },
+    {
+      "epoch": 4.12,
+      "learning_rate": 1.1762767710049425e-05,
+      "loss": 0.0422,
+      "step": 2500
+    },
+    {
+      "epoch": 4.94,
+      "learning_rate": 1.011532125205931e-05,
+      "loss": 0.03,
+      "step": 3000
+    },
+    {
+      "epoch": 5.0,
+      "eval_f1": 0.9961641778789194,
+      "eval_loss": 0.012077880091965199,
+      "eval_runtime": 237.5463,
+      "eval_samples_per_second": 326.741,
+      "eval_steps_per_second": 2.555,
+      "step": 3035
+    },
+    {
+      "epoch": 5.77,
+      "learning_rate": 8.467874794069193e-06,
+      "loss": 0.0215,
+      "step": 3500
+    },
+    {
+      "epoch": 6.0,
+      "eval_f1": 0.9972702243570969,
+      "eval_loss": 0.008092650212347507,
+      "eval_runtime": 237.646,
+      "eval_samples_per_second": 326.603,
+      "eval_steps_per_second": 2.554,
+      "step": 3642
+    },
+    {
+      "epoch": 6.59,
+      "learning_rate": 6.8204283360790776e-06,
+      "loss": 0.0159,
+      "step": 4000
+    },
+    {
+      "epoch": 7.0,
+      "eval_f1": 0.997763649349585,
+      "eval_loss": 0.006471516564488411,
+      "eval_runtime": 237.5957,
+      "eval_samples_per_second": 326.673,
+      "eval_steps_per_second": 2.555,
+      "step": 4249
+    },
+    {
+      "epoch": 7.41,
+      "learning_rate": 5.172981878088963e-06,
+      "loss": 0.0141,
+      "step": 4500
+    },
+    {
+      "epoch": 8.0,
+      "eval_f1": 0.9986060513769636,
+      "eval_loss": 0.0039009908214211464,
+      "eval_runtime": 237.631,
+      "eval_samples_per_second": 326.624,
+      "eval_steps_per_second": 2.554,
+      "step": 4856
+    },
+    {
+      "epoch": 8.24,
+      "learning_rate": 3.525535420098847e-06,
+      "loss": 0.0089,
+      "step": 5000
+    },
+    {
+      "epoch": 9.0,
+      "eval_f1": 0.9990627269958058,
+      "eval_loss": 0.0030426010489463806,
+      "eval_runtime": 237.6288,
+      "eval_samples_per_second": 326.627,
+      "eval_steps_per_second": 2.554,
+      "step": 5463
+    },
+    {
+      "epoch": 9.06,
+      "learning_rate": 1.8780889621087318e-06,
+      "loss": 0.0079,
+      "step": 5500
+    },
+    {
+      "epoch": 9.88,
+      "learning_rate": 2.3064250411861617e-07,
+      "loss": 0.0057,
+      "step": 6000
+    },
+    {
+      "epoch": 10.0,
+      "eval_f1": 0.9991682773970597,
+      "eval_loss": 0.002530897269025445,
+      "eval_runtime": 237.7374,
+      "eval_samples_per_second": 326.478,
+      "eval_steps_per_second": 2.553,
+      "step": 6070
+    }
+  ],
+  "max_steps": 6070,
+  "num_train_epochs": 10,
+  "total_flos": 1.8083196174016512e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe128dfde7edbd11404fb7a18d1c22f32efb6d12770f4d5ee4a9f8f1faabbd70
+size 3439