Upload 7 files

config.json

@@ -0,0 +1,104 @@
+{
+  "_name_or_path": "roberta-base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "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",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13",
+    "14": "LABEL_14",
+    "15": "LABEL_15",
+    "16": "LABEL_16",
+    "17": "LABEL_17",
+    "18": "LABEL_18",
+    "19": "LABEL_19",
+    "20": "LABEL_20",
+    "21": "LABEL_21",
+    "22": "LABEL_22",
+    "23": "LABEL_23",
+    "24": "LABEL_24",
+    "25": "LABEL_25",
+    "26": "LABEL_26",
+    "27": "LABEL_27",
+    "28": "LABEL_28",
+    "29": "LABEL_29",
+    "30": "LABEL_30",
+    "31": "LABEL_31",
+    "32": "LABEL_32",
+    "33": "LABEL_33",
+    "34": "LABEL_34",
+    "35": "LABEL_35"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_13": 13,
+    "LABEL_14": 14,
+    "LABEL_15": 15,
+    "LABEL_16": 16,
+    "LABEL_17": 17,
+    "LABEL_18": 18,
+    "LABEL_19": 19,
+    "LABEL_2": 2,
+    "LABEL_20": 20,
+    "LABEL_21": 21,
+    "LABEL_22": 22,
+    "LABEL_23": 23,
+    "LABEL_24": 24,
+    "LABEL_25": 25,
+    "LABEL_26": 26,
+    "LABEL_27": 27,
+    "LABEL_28": 28,
+    "LABEL_29": 29,
+    "LABEL_3": 3,
+    "LABEL_30": 30,
+    "LABEL_31": 31,
+    "LABEL_32": 32,
+    "LABEL_33": 33,
+    "LABEL_34": 34,
+    "LABEL_35": 35,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d28f5b47ca3252454cbc889911434ee4f023e50413d3b5cf22492e60aa1a03e
+size 498717408

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:059a74fd606934ade13655339749cd90204c1814f5599da1d0494baf44eb581c
+size 997554682

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7a94955a0a320eafc7414411c2ee6b557c9219743c6206f5e0cbbdb28188f97
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d828e0cbf0b47fe0c156ab9e555a50f034d4d1b4b6022ee3cc70f880bd4fd91
+size 1064

trainer_state.json

@@ -0,0 +1,101 @@
+{
+  "best_metric": 0.8571428571428571,
+  "best_model_checkpoint": "roberta-based/checkpoint-925",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 925,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 5.441559314727783,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 1.7332,
+      "step": 185
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7997557997557998,
+      "eval_loss": 1.0176318883895874,
+      "eval_runtime": 5.1197,
+      "eval_samples_per_second": 159.97,
+      "eval_steps_per_second": 5.078,
+      "step": 185
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 11.958271980285645,
+      "learning_rate": 1.2e-05,
+      "loss": 0.6767,
+      "step": 370
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8290598290598291,
+      "eval_loss": 0.7341179847717285,
+      "eval_runtime": 5.1381,
+      "eval_samples_per_second": 159.396,
+      "eval_steps_per_second": 5.06,
+      "step": 370
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 8.717308044433594,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.4469,
+      "step": 555
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8473748473748474,
+      "eval_loss": 0.6683215498924255,
+      "eval_runtime": 5.2018,
+      "eval_samples_per_second": 157.446,
+      "eval_steps_per_second": 4.998,
+      "step": 555
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 14.097502708435059,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.3435,
+      "step": 740
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8522588522588522,
+      "eval_loss": 0.6408819556236267,
+      "eval_runtime": 5.2227,
+      "eval_samples_per_second": 156.816,
+      "eval_steps_per_second": 4.978,
+      "step": 740
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 7.630906105041504,
+      "learning_rate": 0.0,
+      "loss": 0.2829,
+      "step": 925
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8571428571428571,
+      "eval_loss": 0.6410605311393738,
+      "eval_runtime": 5.1314,
+      "eval_samples_per_second": 159.606,
+      "eval_steps_per_second": 5.067,
+      "step": 925
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 925,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 2736984690806400.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2851c86c20f91b756a0798e16f15f8f274a08f737278710e86c0ab09ac310b37
+size 4984