Upload best model from trial 14

HF_FT_Carmel_Preprocess1_Data/trial_14/checkpoint-3090/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

HF_FT_Carmel_Preprocess1_Data/trial_14/checkpoint-3090/config.json

@@ -0,0 +1,49 @@
+{
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "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"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4
+  },
+  "layer_norm_eps": 1e-07,
+  "legacy": true,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.55.1",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

HF_FT_Carmel_Preprocess1_Data/trial_14/checkpoint-3090/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:feeb42eb74358d28ad6e86090de740257d98d86a444771f12ad897bb22e18cd4
+size 737728508

HF_FT_Carmel_Preprocess1_Data/trial_14/checkpoint-3090/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8a188f11f33322dc2d9de6d06544f6fcb9af5928e49504c0b805db5626e3984
+size 1475576826

HF_FT_Carmel_Preprocess1_Data/trial_14/checkpoint-3090/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dee66f50e2161db3301ab48e5878ebe16e745b5ecfb21cb02605bbb951b4600
+size 14244

HF_FT_Carmel_Preprocess1_Data/trial_14/checkpoint-3090/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3a1f769eb8453e4fafb6fa7148aa89fca7e2318b6e6671395c487aa124e46f3
+size 1064

HF_FT_Carmel_Preprocess1_Data/trial_14/checkpoint-3090/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

HF_FT_Carmel_Preprocess1_Data/trial_14/checkpoint-3090/spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

HF_FT_Carmel_Preprocess1_Data/trial_14/checkpoint-3090/tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

HF_FT_Carmel_Preprocess1_Data/trial_14/checkpoint-3090/trainer_state.json

@@ -0,0 +1,145 @@
+{
+  "best_global_step": null,
+  "best_metric": 0.8763362487852284,
+  "best_model_checkpoint": null,
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 3090,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 6.279489517211914,
+      "learning_rate": 1.410738370645236e-05,
+      "loss": 1.3949,
+      "step": 515
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6025267249757046,
+      "eval_f1": 0.5993739541640919,
+      "eval_loss": 1.12865149974823,
+      "eval_runtime": 17.4215,
+      "eval_samples_per_second": 472.519,
+      "eval_steps_per_second": 14.809,
+      "step": 515
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 7.4561448097229,
+      "learning_rate": 2.8242213684707158e-05,
+      "loss": 0.939,
+      "step": 1030
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7854713313896987,
+      "eval_f1": 0.7847142979916254,
+      "eval_loss": 0.8375873565673828,
+      "eval_runtime": 17.3941,
+      "eval_samples_per_second": 473.263,
+      "eval_steps_per_second": 14.833,
+      "step": 1030
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 8.811366081237793,
+      "learning_rate": 4.2377043662961956e-05,
+      "loss": 0.7701,
+      "step": 1545
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8341836734693877,
+      "eval_f1": 0.8341584878065191,
+      "eval_loss": 0.7567286491394043,
+      "eval_runtime": 17.3857,
+      "eval_samples_per_second": 473.493,
+      "eval_steps_per_second": 14.84,
+      "step": 1545
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 6.209693431854248,
+      "learning_rate": 5.288445055827553e-05,
+      "loss": 0.7007,
+      "step": 2060
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8378279883381924,
+      "eval_f1": 0.8380539374279756,
+      "eval_loss": 0.7788376212120056,
+      "eval_runtime": 17.3649,
+      "eval_samples_per_second": 474.06,
+      "eval_steps_per_second": 14.858,
+      "step": 2060
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 3.959907293319702,
+      "learning_rate": 5.214282535696478e-05,
+      "loss": 0.6391,
+      "step": 2575
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8504616132167152,
+      "eval_f1": 0.8503795327319785,
+      "eval_loss": 0.7440983057022095,
+      "eval_runtime": 17.4021,
+      "eval_samples_per_second": 473.047,
+      "eval_steps_per_second": 14.826,
+      "step": 2575
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 5.116758823394775,
+      "learning_rate": 5.044493827540735e-05,
+      "loss": 0.5958,
+      "step": 3090
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8763362487852284,
+      "eval_f1": 0.8762904368449055,
+      "eval_loss": 0.699774980545044,
+      "eval_runtime": 17.3889,
+      "eval_samples_per_second": 473.405,
+      "eval_steps_per_second": 14.837,
+      "step": 3090
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 10300,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 4,
+        "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": 1.29949803004032e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

HF_FT_Carmel_Preprocess1_Data/trial_14/checkpoint-3090/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0e81b3c219291b742f0fd6194a8ee6534e08fd5e6feafae3ca79269354f6fae
+size 5368