Upload 10 files

config.json

@@ -0,0 +1,129 @@
+{
+  "_num_labels": 5,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "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",
+    "36": "LABEL_36",
+    "37": "LABEL_37",
+    "38": "LABEL_38",
+    "39": "LABEL_39",
+    "40": "LABEL_40",
+    "41": "LABEL_41",
+    "42": "LABEL_42",
+    "43": "LABEL_43",
+    "44": "LABEL_44",
+    "45": "LABEL_45"
+  },
+  "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_36": 36,
+    "LABEL_37": 37,
+    "LABEL_38": 38,
+    "LABEL_39": 39,
+    "LABEL_4": 4,
+    "LABEL_40": 40,
+    "LABEL_41": 41,
+    "LABEL_42": 42,
+    "LABEL_43": 43,
+    "LABEL_44": 44,
+    "LABEL_45": 45,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 50000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:442e6bb72c6a313d6e4a28cac8a5fd085f687f098ec0e348aebc0ecb36069438
+size 497930416

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:907663d4eb59a6b39f6aee6fefb494fb78e1d21b37bf6388c0803b272931ddca
+size 14391

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a24d36c2d0e9d626fa824d5e9fc43c32cbdeb5639db3b2625b6fafabfd5ffc2
+size 1465

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 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,382 @@
+{
+  "best_global_step": 425,
+  "best_metric": 0.9176470588235294,
+  "best_model_checkpoint": "./bert-samudra-model\\checkpoint-425",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 425,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.11764705882352941,
+      "grad_norm": 10.0350341796875,
+      "learning_rate": 1.9894117647058826e-05,
+      "loss": 3.8456,
+      "step": 10
+    },
+    {
+      "epoch": 0.23529411764705882,
+      "grad_norm": 10.431258201599121,
+      "learning_rate": 1.9776470588235296e-05,
+      "loss": 3.826,
+      "step": 20
+    },
+    {
+      "epoch": 0.35294117647058826,
+      "grad_norm": 11.249832153320312,
+      "learning_rate": 1.9658823529411765e-05,
+      "loss": 3.6472,
+      "step": 30
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 10.304410934448242,
+      "learning_rate": 1.9541176470588235e-05,
+      "loss": 3.5359,
+      "step": 40
+    },
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 11.847091674804688,
+      "learning_rate": 1.942352941176471e-05,
+      "loss": 3.3157,
+      "step": 50
+    },
+    {
+      "epoch": 0.7058823529411765,
+      "grad_norm": 9.621623039245605,
+      "learning_rate": 1.930588235294118e-05,
+      "loss": 3.1498,
+      "step": 60
+    },
+    {
+      "epoch": 0.8235294117647058,
+      "grad_norm": 11.151117324829102,
+      "learning_rate": 1.918823529411765e-05,
+      "loss": 2.9821,
+      "step": 70
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 9.83305549621582,
+      "learning_rate": 1.907058823529412e-05,
+      "loss": 2.9091,
+      "step": 80
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5294117647058824,
+      "eval_loss": 2.518275737762451,
+      "eval_runtime": 2.8699,
+      "eval_samples_per_second": 59.235,
+      "eval_steps_per_second": 7.666,
+      "step": 85
+    },
+    {
+      "epoch": 1.0588235294117647,
+      "grad_norm": 9.598007202148438,
+      "learning_rate": 1.895294117647059e-05,
+      "loss": 2.5816,
+      "step": 90
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 9.898895263671875,
+      "learning_rate": 1.883529411764706e-05,
+      "loss": 2.3487,
+      "step": 100
+    },
+    {
+      "epoch": 1.2941176470588236,
+      "grad_norm": 11.571386337280273,
+      "learning_rate": 1.871764705882353e-05,
+      "loss": 2.1136,
+      "step": 110
+    },
+    {
+      "epoch": 1.4117647058823528,
+      "grad_norm": 11.180049896240234,
+      "learning_rate": 1.86e-05,
+      "loss": 2.0731,
+      "step": 120
+    },
+    {
+      "epoch": 1.5294117647058822,
+      "grad_norm": 9.434500694274902,
+      "learning_rate": 1.848235294117647e-05,
+      "loss": 1.9983,
+      "step": 130
+    },
+    {
+      "epoch": 1.6470588235294117,
+      "grad_norm": 8.993762969970703,
+      "learning_rate": 1.836470588235294e-05,
+      "loss": 1.7445,
+      "step": 140
+    },
+    {
+      "epoch": 1.7647058823529411,
+      "grad_norm": 9.424057960510254,
+      "learning_rate": 1.8247058823529415e-05,
+      "loss": 1.7651,
+      "step": 150
+    },
+    {
+      "epoch": 1.8823529411764706,
+      "grad_norm": 8.946263313293457,
+      "learning_rate": 1.8129411764705885e-05,
+      "loss": 1.6938,
+      "step": 160
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 9.5614013671875,
+      "learning_rate": 1.8011764705882354e-05,
+      "loss": 1.539,
+      "step": 170
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8117647058823529,
+      "eval_loss": 1.4311776161193848,
+      "eval_runtime": 2.9195,
+      "eval_samples_per_second": 58.23,
+      "eval_steps_per_second": 7.536,
+      "step": 170
+    },
+    {
+      "epoch": 2.1176470588235294,
+      "grad_norm": 8.067319869995117,
+      "learning_rate": 1.7894117647058824e-05,
+      "loss": 1.2424,
+      "step": 180
+    },
+    {
+      "epoch": 2.235294117647059,
+      "grad_norm": 9.209125518798828,
+      "learning_rate": 1.7776470588235294e-05,
+      "loss": 1.1468,
+      "step": 190
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "grad_norm": 9.35853099822998,
+      "learning_rate": 1.7658823529411768e-05,
+      "loss": 1.0893,
+      "step": 200
+    },
+    {
+      "epoch": 2.4705882352941178,
+      "grad_norm": 7.949193477630615,
+      "learning_rate": 1.7541176470588238e-05,
+      "loss": 1.1078,
+      "step": 210
+    },
+    {
+      "epoch": 2.588235294117647,
+      "grad_norm": 10.602166175842285,
+      "learning_rate": 1.7423529411764707e-05,
+      "loss": 0.9902,
+      "step": 220
+    },
+    {
+      "epoch": 2.7058823529411766,
+      "grad_norm": 8.58541488647461,
+      "learning_rate": 1.7305882352941177e-05,
+      "loss": 0.9298,
+      "step": 230
+    },
+    {
+      "epoch": 2.8235294117647056,
+      "grad_norm": 6.725298881530762,
+      "learning_rate": 1.7188235294117647e-05,
+      "loss": 0.8838,
+      "step": 240
+    },
+    {
+      "epoch": 2.9411764705882355,
+      "grad_norm": 8.761615753173828,
+      "learning_rate": 1.7070588235294117e-05,
+      "loss": 0.8112,
+      "step": 250
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.888235294117647,
+      "eval_loss": 0.8797827959060669,
+      "eval_runtime": 2.1675,
+      "eval_samples_per_second": 78.433,
+      "eval_steps_per_second": 10.15,
+      "step": 255
+    },
+    {
+      "epoch": 3.0588235294117645,
+      "grad_norm": 5.102208137512207,
+      "learning_rate": 1.695294117647059e-05,
+      "loss": 0.7609,
+      "step": 260
+    },
+    {
+      "epoch": 3.176470588235294,
+      "grad_norm": 8.779169082641602,
+      "learning_rate": 1.683529411764706e-05,
+      "loss": 0.6983,
+      "step": 270
+    },
+    {
+      "epoch": 3.2941176470588234,
+      "grad_norm": 4.434069633483887,
+      "learning_rate": 1.671764705882353e-05,
+      "loss": 0.5764,
+      "step": 280
+    },
+    {
+      "epoch": 3.411764705882353,
+      "grad_norm": 12.731746673583984,
+      "learning_rate": 1.66e-05,
+      "loss": 0.5199,
+      "step": 290
+    },
+    {
+      "epoch": 3.5294117647058822,
+      "grad_norm": 6.222368240356445,
+      "learning_rate": 1.648235294117647e-05,
+      "loss": 0.5333,
+      "step": 300
+    },
+    {
+      "epoch": 3.6470588235294117,
+      "grad_norm": 5.6505560874938965,
+      "learning_rate": 1.6364705882352944e-05,
+      "loss": 0.4524,
+      "step": 310
+    },
+    {
+      "epoch": 3.764705882352941,
+      "grad_norm": 5.23166036605835,
+      "learning_rate": 1.6247058823529413e-05,
+      "loss": 0.4974,
+      "step": 320
+    },
+    {
+      "epoch": 3.8823529411764706,
+      "grad_norm": 6.096327304840088,
+      "learning_rate": 1.6129411764705883e-05,
+      "loss": 0.4621,
+      "step": 330
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 7.395042419433594,
+      "learning_rate": 1.6011764705882353e-05,
+      "loss": 0.4012,
+      "step": 340
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8941176470588236,
+      "eval_loss": 0.5824028253555298,
+      "eval_runtime": 2.3688,
+      "eval_samples_per_second": 71.766,
+      "eval_steps_per_second": 9.287,
+      "step": 340
+    },
+    {
+      "epoch": 4.117647058823529,
+      "grad_norm": 5.869823455810547,
+      "learning_rate": 1.5894117647058823e-05,
+      "loss": 0.3211,
+      "step": 350
+    },
+    {
+      "epoch": 4.235294117647059,
+      "grad_norm": 4.795381546020508,
+      "learning_rate": 1.5776470588235297e-05,
+      "loss": 0.3647,
+      "step": 360
+    },
+    {
+      "epoch": 4.352941176470588,
+      "grad_norm": 3.4636142253875732,
+      "learning_rate": 1.5658823529411766e-05,
+      "loss": 0.2564,
+      "step": 370
+    },
+    {
+      "epoch": 4.470588235294118,
+      "grad_norm": 10.156576156616211,
+      "learning_rate": 1.5541176470588236e-05,
+      "loss": 0.2745,
+      "step": 380
+    },
+    {
+      "epoch": 4.588235294117647,
+      "grad_norm": 2.828077554702759,
+      "learning_rate": 1.5423529411764706e-05,
+      "loss": 0.2418,
+      "step": 390
+    },
+    {
+      "epoch": 4.705882352941177,
+      "grad_norm": 3.717984199523926,
+      "learning_rate": 1.5305882352941176e-05,
+      "loss": 0.2605,
+      "step": 400
+    },
+    {
+      "epoch": 4.823529411764706,
+      "grad_norm": 1.5987720489501953,
+      "learning_rate": 1.5188235294117648e-05,
+      "loss": 0.2369,
+      "step": 410
+    },
+    {
+      "epoch": 4.9411764705882355,
+      "grad_norm": 3.3276009559631348,
+      "learning_rate": 1.507058823529412e-05,
+      "loss": 0.2366,
+      "step": 420
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9176470588235294,
+      "eval_loss": 0.4427616000175476,
+      "eval_runtime": 3.6872,
+      "eval_samples_per_second": 46.106,
+      "eval_steps_per_second": 5.967,
+      "step": 425
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1700,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 29670808006140.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a415994487ce23b91cbe554ff2a98e506824c0a21bbf412ddad8d0ba9f6b8d6
+size 5713