Upload folder using huggingface_hub

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "ProsusAI/finbert",
+  "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": "positive",
+    "1": "negative",
+    "2": "neutral"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "negative": 1,
+    "neutral": 2,
+    "positive": 0
+  },
+  "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": "4.46.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0f1372a98474a8a5bdfcfce093c3cf5c7d00aabb5d8c7f3e82a657cd5512668
+size 437961724

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ff96db94351077a537e63bd3c214322ab89ba172307f5fb2488705a6df09fca
+size 876044037

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98c08f29176f25af8f22d8f16a7b397da2f95e7d4aa320076049fad0bbeb4ce4
+size 14639

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70fabc5269785aa082a908e8622f55b8bbc0a78e118746cddd1b0062ad9ab4d2
+size 627

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 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "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,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "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 +1,190 @@
+{
+  "best_metric": 0.6687281727790833,
+  "best_model_checkpoint": "/home/boris.ustyugov/exness/deepschool_deploy/hw3-hf-transformers/finetuned_model/checkpoint-1000",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "grad_norm": 22.86173439025879,
+      "learning_rate": 1.9666666666666666e-05,
+      "loss": 0.869,
+      "step": 50
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 57.24214172363281,
+      "learning_rate": 1.9333333333333333e-05,
+      "loss": 0.7937,
+      "step": 100
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 10.02920913696289,
+      "learning_rate": 1.9e-05,
+      "loss": 0.9386,
+      "step": 150
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.9098700881004333,
+      "learning_rate": 1.866666666666667e-05,
+      "loss": 0.8032,
+      "step": 200
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.5401331782341003,
+      "learning_rate": 1.8333333333333333e-05,
+      "loss": 0.6767,
+      "step": 250
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 20.837909698486328,
+      "learning_rate": 1.8e-05,
+      "loss": 0.9775,
+      "step": 300
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.4586431086063385,
+      "learning_rate": 1.7666666666666668e-05,
+      "loss": 1.1348,
+      "step": 350
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 87.78131103515625,
+      "learning_rate": 1.7333333333333336e-05,
+      "loss": 0.7649,
+      "step": 400
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.21819159388542175,
+      "learning_rate": 1.7e-05,
+      "loss": 0.7158,
+      "step": 450
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.24447402358055115,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.6868,
+      "step": 500
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 295.1979064941406,
+      "learning_rate": 1.6333333333333335e-05,
+      "loss": 0.619,
+      "step": 550
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.19443568587303162,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 1.1763,
+      "step": 600
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.4207628071308136,
+      "learning_rate": 1.5666666666666667e-05,
+      "loss": 0.7286,
+      "step": 650
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.18366234004497528,
+      "learning_rate": 1.5333333333333334e-05,
+      "loss": 0.7069,
+      "step": 700
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.16538876295089722,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.7595,
+      "step": 750
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.14904990792274475,
+      "learning_rate": 1.4666666666666666e-05,
+      "loss": 0.6224,
+      "step": 800
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.3615138530731201,
+      "learning_rate": 1.4333333333333334e-05,
+      "loss": 0.6529,
+      "step": 850
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.09473315626382828,
+      "learning_rate": 1.4e-05,
+      "loss": 0.7342,
+      "step": 900
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.5744537711143494,
+      "learning_rate": 1.3666666666666667e-05,
+      "loss": 1.0007,
+      "step": 950
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.12679271399974823,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.93,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6687281727790833,
+      "eval_runtime": 4.802,
+      "eval_samples_per_second": 104.123,
+      "eval_steps_per_second": 52.061,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 3000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.01
+      },
+      "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": 526226835456000.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:541e6f7f57f67a3a1c9907085521ba701b57db0f57f225a02ca245b98ef6d506
+size 4923