Training in progress, step 3180

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ed89d0c2b190d14e375b998417dafd6607517178c8317dbed91bd66a39a179f
+oid sha256:e39c4f5a6351f3075b5b3741515b1cd2a71b546343c8e64ebfd362859c446880
 size 268290900

run-0/checkpoint-2226/config.json

@@ -0,0 +1,331 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "restaurant_reviews",
+    "1": "nutrition_info",
+    "2": "account_blocked",
+    "3": "oil_change_how",
+    "4": "time",
+    "5": "weather",
+    "6": "redeem_rewards",
+    "7": "interest_rate",
+    "8": "gas_type",
+    "9": "accept_reservations",
+    "10": "smart_home",
+    "11": "user_name",
+    "12": "report_lost_card",
+    "13": "repeat",
+    "14": "whisper_mode",
+    "15": "what_are_your_hobbies",
+    "16": "order",
+    "17": "jump_start",
+    "18": "schedule_meeting",
+    "19": "meeting_schedule",
+    "20": "freeze_account",
+    "21": "what_song",
+    "22": "meaning_of_life",
+    "23": "restaurant_reservation",
+    "24": "traffic",
+    "25": "make_call",
+    "26": "text",
+    "27": "bill_balance",
+    "28": "improve_credit_score",
+    "29": "change_language",
+    "30": "no",
+    "31": "measurement_conversion",
+    "32": "timer",
+    "33": "flip_coin",
+    "34": "do_you_have_pets",
+    "35": "balance",
+    "36": "tell_joke",
+    "37": "last_maintenance",
+    "38": "exchange_rate",
+    "39": "uber",
+    "40": "car_rental",
+    "41": "credit_limit",
+    "42": "oos",
+    "43": "shopping_list",
+    "44": "expiration_date",
+    "45": "routing",
+    "46": "meal_suggestion",
+    "47": "tire_change",
+    "48": "todo_list",
+    "49": "card_declined",
+    "50": "rewards_balance",
+    "51": "change_accent",
+    "52": "vaccines",
+    "53": "reminder_update",
+    "54": "food_last",
+    "55": "change_ai_name",
+    "56": "bill_due",
+    "57": "who_do_you_work_for",
+    "58": "share_location",
+    "59": "international_visa",
+    "60": "calendar",
+    "61": "translate",
+    "62": "carry_on",
+    "63": "book_flight",
+    "64": "insurance_change",
+    "65": "todo_list_update",
+    "66": "timezone",
+    "67": "cancel_reservation",
+    "68": "transactions",
+    "69": "credit_score",
+    "70": "report_fraud",
+    "71": "spending_history",
+    "72": "directions",
+    "73": "spelling",
+    "74": "insurance",
+    "75": "what_is_your_name",
+    "76": "reminder",
+    "77": "where_are_you_from",
+    "78": "distance",
+    "79": "payday",
+    "80": "flight_status",
+    "81": "find_phone",
+    "82": "greeting",
+    "83": "alarm",
+    "84": "order_status",
+    "85": "confirm_reservation",
+    "86": "cook_time",
+    "87": "damaged_card",
+    "88": "reset_settings",
+    "89": "pin_change",
+    "90": "replacement_card_duration",
+    "91": "new_card",
+    "92": "roll_dice",
+    "93": "income",
+    "94": "taxes",
+    "95": "date",
+    "96": "who_made_you",
+    "97": "pto_request",
+    "98": "tire_pressure",
+    "99": "how_old_are_you",
+    "100": "rollover_401k",
+    "101": "pto_request_status",
+    "102": "how_busy",
+    "103": "application_status",
+    "104": "recipe",
+    "105": "calendar_update",
+    "106": "play_music",
+    "107": "yes",
+    "108": "direct_deposit",
+    "109": "credit_limit_change",
+    "110": "gas",
+    "111": "pay_bill",
+    "112": "ingredients_list",
+    "113": "lost_luggage",
+    "114": "goodbye",
+    "115": "what_can_i_ask_you",
+    "116": "book_hotel",
+    "117": "are_you_a_bot",
+    "118": "next_song",
+    "119": "change_speed",
+    "120": "plug_type",
+    "121": "maybe",
+    "122": "w2",
+    "123": "oil_change_when",
+    "124": "thank_you",
+    "125": "shopping_list_update",
+    "126": "pto_balance",
+    "127": "order_checks",
+    "128": "travel_alert",
+    "129": "fun_fact",
+    "130": "sync_device",
+    "131": "schedule_maintenance",
+    "132": "apr",
+    "133": "transfer",
+    "134": "ingredient_substitution",
+    "135": "calories",
+    "136": "current_location",
+    "137": "international_fees",
+    "138": "calculator",
+    "139": "definition",
+    "140": "next_holiday",
+    "141": "update_playlist",
+    "142": "mpg",
+    "143": "min_payment",
+    "144": "change_user_name",
+    "145": "restaurant_suggestion",
+    "146": "travel_notification",
+    "147": "cancel",
+    "148": "pto_used",
+    "149": "travel_suggestion",
+    "150": "change_volume"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "accept_reservations": 9,
+    "account_blocked": 2,
+    "alarm": 83,
+    "application_status": 103,
+    "apr": 132,
+    "are_you_a_bot": 117,
+    "balance": 35,
+    "bill_balance": 27,
+    "bill_due": 56,
+    "book_flight": 63,
+    "book_hotel": 116,
+    "calculator": 138,
+    "calendar": 60,
+    "calendar_update": 105,
+    "calories": 135,
+    "cancel": 147,
+    "cancel_reservation": 67,
+    "car_rental": 40,
+    "card_declined": 49,
+    "carry_on": 62,
+    "change_accent": 51,
+    "change_ai_name": 55,
+    "change_language": 29,
+    "change_speed": 119,
+    "change_user_name": 144,
+    "change_volume": 150,
+    "confirm_reservation": 85,
+    "cook_time": 86,
+    "credit_limit": 41,
+    "credit_limit_change": 109,
+    "credit_score": 69,
+    "current_location": 136,
+    "damaged_card": 87,
+    "date": 95,
+    "definition": 139,
+    "direct_deposit": 108,
+    "directions": 72,
+    "distance": 78,
+    "do_you_have_pets": 34,
+    "exchange_rate": 38,
+    "expiration_date": 44,
+    "find_phone": 81,
+    "flight_status": 80,
+    "flip_coin": 33,
+    "food_last": 54,
+    "freeze_account": 20,
+    "fun_fact": 129,
+    "gas": 110,
+    "gas_type": 8,
+    "goodbye": 114,
+    "greeting": 82,
+    "how_busy": 102,
+    "how_old_are_you": 99,
+    "improve_credit_score": 28,
+    "income": 93,
+    "ingredient_substitution": 134,
+    "ingredients_list": 112,
+    "insurance": 74,
+    "insurance_change": 64,
+    "interest_rate": 7,
+    "international_fees": 137,
+    "international_visa": 59,
+    "jump_start": 17,
+    "last_maintenance": 37,
+    "lost_luggage": 113,
+    "make_call": 25,
+    "maybe": 121,
+    "meal_suggestion": 46,
+    "meaning_of_life": 22,
+    "measurement_conversion": 31,
+    "meeting_schedule": 19,
+    "min_payment": 143,
+    "mpg": 142,
+    "new_card": 91,
+    "next_holiday": 140,
+    "next_song": 118,
+    "no": 30,
+    "nutrition_info": 1,
+    "oil_change_how": 3,
+    "oil_change_when": 123,
+    "oos": 42,
+    "order": 16,
+    "order_checks": 127,
+    "order_status": 84,
+    "pay_bill": 111,
+    "payday": 79,
+    "pin_change": 89,
+    "play_music": 106,
+    "plug_type": 120,
+    "pto_balance": 126,
+    "pto_request": 97,
+    "pto_request_status": 101,
+    "pto_used": 148,
+    "recipe": 104,
+    "redeem_rewards": 6,
+    "reminder": 76,
+    "reminder_update": 53,
+    "repeat": 13,
+    "replacement_card_duration": 90,
+    "report_fraud": 70,
+    "report_lost_card": 12,
+    "reset_settings": 88,
+    "restaurant_reservation": 23,
+    "restaurant_reviews": 0,
+    "restaurant_suggestion": 145,
+    "rewards_balance": 50,
+    "roll_dice": 92,
+    "rollover_401k": 100,
+    "routing": 45,
+    "schedule_maintenance": 131,
+    "schedule_meeting": 18,
+    "share_location": 58,
+    "shopping_list": 43,
+    "shopping_list_update": 125,
+    "smart_home": 10,
+    "spelling": 73,
+    "spending_history": 71,
+    "sync_device": 130,
+    "taxes": 94,
+    "tell_joke": 36,
+    "text": 26,
+    "thank_you": 124,
+    "time": 4,
+    "timer": 32,
+    "timezone": 66,
+    "tire_change": 47,
+    "tire_pressure": 98,
+    "todo_list": 48,
+    "todo_list_update": 65,
+    "traffic": 24,
+    "transactions": 68,
+    "transfer": 133,
+    "translate": 61,
+    "travel_alert": 128,
+    "travel_notification": 146,
+    "travel_suggestion": 149,
+    "uber": 39,
+    "update_playlist": 141,
+    "user_name": 11,
+    "vaccines": 52,
+    "w2": 122,
+    "weather": 5,
+    "what_are_your_hobbies": 15,
+    "what_can_i_ask_you": 115,
+    "what_is_your_name": 75,
+    "what_song": 21,
+    "where_are_you_from": 77,
+    "whisper_mode": 14,
+    "who_do_you_work_for": 57,
+    "who_made_you": 96,
+    "yes": 107
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0",
+  "vocab_size": 30522
+}

run-0/checkpoint-2226/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:260ece6d0e31833624519f6f51ee0b07b12091e1b3a3500ee17af7c64edba1b0
+size 268290900

run-0/checkpoint-2226/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6b979551ab8bdec1ebeec3129ed997818840d28fabab0edbb45495dd24ff6aa
+size 536641018

run-0/checkpoint-2226/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73aac57daf9622fa2240f61d454eeb9ca3c3b3e1932f7c53132d59e331b24bc0
+size 13990

run-0/checkpoint-2226/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ea195022b7a2fa1b5b6665ff3ac3f1d1c1ba4e0babbc4b87514eca79802f03a
+size 1064

run-0/checkpoint-2226/special_tokens_map.json

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

run-0/checkpoint-2226/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-0/checkpoint-2226/trainer_state.json

@@ -0,0 +1,140 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 2226,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9968553459119497,
+      "grad_norm": 0.637270987033844,
+      "learning_rate": 1.7151841868823e-05,
+      "loss": 0.4092,
+      "step": 317
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5932258064516129,
+      "eval_loss": 0.20514699816703796,
+      "eval_runtime": 2.8479,
+      "eval_samples_per_second": 1088.527,
+      "eval_steps_per_second": 22.824,
+      "step": 318
+    },
+    {
+      "epoch": 1.9937106918238994,
+      "grad_norm": 0.5349993109703064,
+      "learning_rate": 1.4303683737646003e-05,
+      "loss": 0.1725,
+      "step": 634
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8203225806451613,
+      "eval_loss": 0.10115758329629898,
+      "eval_runtime": 2.9228,
+      "eval_samples_per_second": 1060.623,
+      "eval_steps_per_second": 22.239,
+      "step": 636
+    },
+    {
+      "epoch": 2.990566037735849,
+      "grad_norm": 0.5367943644523621,
+      "learning_rate": 1.1455525606469004e-05,
+      "loss": 0.1093,
+      "step": 951
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8774193548387097,
+      "eval_loss": 0.06855319440364838,
+      "eval_runtime": 2.7283,
+      "eval_samples_per_second": 1136.218,
+      "eval_steps_per_second": 23.824,
+      "step": 954
+    },
+    {
+      "epoch": 3.9874213836477987,
+      "grad_norm": 0.39646974205970764,
+      "learning_rate": 8.607367475292004e-06,
+      "loss": 0.0832,
+      "step": 1268
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8951612903225806,
+      "eval_loss": 0.053471531718969345,
+      "eval_runtime": 2.9292,
+      "eval_samples_per_second": 1058.326,
+      "eval_steps_per_second": 22.191,
+      "step": 1272
+    },
+    {
+      "epoch": 4.984276729559748,
+      "grad_norm": 0.3076865077018738,
+      "learning_rate": 5.759209344115006e-06,
+      "loss": 0.0704,
+      "step": 1585
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9,
+      "eval_loss": 0.045573726296424866,
+      "eval_runtime": 3.2771,
+      "eval_samples_per_second": 945.96,
+      "eval_steps_per_second": 19.835,
+      "step": 1590
+    },
+    {
+      "epoch": 5.981132075471698,
+      "grad_norm": 0.32759594917297363,
+      "learning_rate": 2.911051212938006e-06,
+      "loss": 0.0634,
+      "step": 1902
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9058064516129032,
+      "eval_loss": 0.0414934903383255,
+      "eval_runtime": 3.3068,
+      "eval_samples_per_second": 937.468,
+      "eval_steps_per_second": 19.657,
+      "step": 1908
+    },
+    {
+      "epoch": 6.977987421383648,
+      "grad_norm": 0.32366815209388733,
+      "learning_rate": 6.289308176100629e-08,
+      "loss": 0.0599,
+      "step": 2219
+    }
+  ],
+  "logging_steps": 317,
+  "max_steps": 2226,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 1000000000.0,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 578219881979544.0,
+  "train_batch_size": 48,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.2613699502770426,
+    "num_train_epochs": 7,
+    "temperature": 9
+  }
+}

run-0/checkpoint-2226/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e81ec872947cb7f3b2fb73a042eb72aab0151e6784c7937c76cbd14473fd51b
+size 5432

run-1/checkpoint-2862/config.json

@@ -326,6 +326,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.47.1",
+  "transformers_version": "4.47.0",
   "vocab_size": 30522
 }

run-1/checkpoint-2862/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd49d9fed4d63ff70ccf669cdd06027bd63c93903a136a53cb3b5045948a815c
+oid sha256:9485849fc0f0619157aa7247a4b8c39d8dfc23d577ec0b7a1bea0cf750df421f
 size 268290900

run-1/checkpoint-2862/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9070031d06060d90440e64a4923632ac3124825b3b707313668acd353160cdbd
-size 536643898
+oid sha256:585c9dc0ed78d00cdde852275b7d2821654d6ad9b4d8ec79438d49ec18d9dfcc
+size 536641018

run-1/checkpoint-2862/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41b5282f1cde964bf5a382eb03f1cdd87f1c8e2f60e43277b3453f63947f5933
-size 14244
+oid sha256:e29353d4954fcf585947caa6a0a3fa59c7379d49f3bc56c6a4bd276fef18ca98
+size 13990

run-1/checkpoint-2862/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a738824491ff8b261b6db2a842e15bf80355d04a07892a16df2c4715b2ee556
+oid sha256:3c64bfaed33db311081ee0596530a03699ac7659f0cf4f57a488fea34df98816
 size 1064

run-1/checkpoint-2862/trainer_state.json

@@ -10,137 +10,137 @@
   "log_history": [
     {
       "epoch": 0.9968553459119497,
-      "grad_norm": 0.6337465047836304,
+      "grad_norm": 0.6216608881950378,
       "learning_rate": 1.7784765897973445e-05,
-      "loss": 0.3867,
+      "loss": 0.3805,
       "step": 317
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5703225806451613,
-      "eval_loss": 0.19408121705055237,
-      "eval_runtime": 1.3792,
-      "eval_samples_per_second": 2247.653,
-      "eval_steps_per_second": 47.128,
+      "eval_accuracy": 0.5790322580645161,
+      "eval_loss": 0.18826216459274292,
+      "eval_runtime": 2.6452,
+      "eval_samples_per_second": 1171.927,
+      "eval_steps_per_second": 24.573,
       "step": 318
     },
     {
       "epoch": 1.9937106918238994,
-      "grad_norm": 0.5281593799591064,
+      "grad_norm": 0.5106726288795471,
       "learning_rate": 1.556953179594689e-05,
-      "loss": 0.1621,
+      "loss": 0.1584,
       "step": 634
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.8274193548387097,
-      "eval_loss": 0.0953042134642601,
-      "eval_runtime": 1.5805,
-      "eval_samples_per_second": 1961.446,
-      "eval_steps_per_second": 41.127,
+      "eval_accuracy": 0.8203225806451613,
+      "eval_loss": 0.0928473100066185,
+      "eval_runtime": 2.7805,
+      "eval_samples_per_second": 1114.911,
+      "eval_steps_per_second": 23.377,
       "step": 636
     },
     {
       "epoch": 2.990566037735849,
-      "grad_norm": 0.4498799741268158,
+      "grad_norm": 0.4919030964374542,
       "learning_rate": 1.3354297693920338e-05,
-      "loss": 0.1018,
+      "loss": 0.1001,
       "step": 951
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.8806451612903226,
-      "eval_loss": 0.06378939002752304,
-      "eval_runtime": 1.5977,
-      "eval_samples_per_second": 1940.328,
-      "eval_steps_per_second": 40.684,
+      "eval_accuracy": 0.8787096774193548,
+      "eval_loss": 0.06263605505228043,
+      "eval_runtime": 2.6683,
+      "eval_samples_per_second": 1161.795,
+      "eval_steps_per_second": 24.36,
       "step": 954
     },
     {
       "epoch": 3.9874213836477987,
-      "grad_norm": 0.3946130573749542,
+      "grad_norm": 0.3679712116718292,
       "learning_rate": 1.1139063591893781e-05,
-      "loss": 0.0769,
+      "loss": 0.0754,
       "step": 1268
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.8980645161290323,
-      "eval_loss": 0.04853447526693344,
-      "eval_runtime": 1.6017,
-      "eval_samples_per_second": 1935.5,
-      "eval_steps_per_second": 40.583,
+      "eval_accuracy": 0.8974193548387097,
+      "eval_loss": 0.048369407653808594,
+      "eval_runtime": 2.749,
+      "eval_samples_per_second": 1127.668,
+      "eval_steps_per_second": 23.645,
       "step": 1272
     },
     {
       "epoch": 4.984276729559748,
-      "grad_norm": 0.2938636541366577,
+      "grad_norm": 0.27457061409950256,
       "learning_rate": 8.923829489867226e-06,
-      "loss": 0.0634,
+      "loss": 0.0627,
       "step": 1585
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.9067741935483871,
-      "eval_loss": 0.04064928740262985,
-      "eval_runtime": 1.4207,
-      "eval_samples_per_second": 2182.039,
-      "eval_steps_per_second": 45.752,
+      "eval_accuracy": 0.9064516129032258,
+      "eval_loss": 0.04010023921728134,
+      "eval_runtime": 2.7621,
+      "eval_samples_per_second": 1122.344,
+      "eval_steps_per_second": 23.533,
       "step": 1590
     },
     {
       "epoch": 5.981132075471698,
-      "grad_norm": 0.3579629063606262,
+      "grad_norm": 0.29231536388397217,
       "learning_rate": 6.708595387840672e-06,
-      "loss": 0.0555,
+      "loss": 0.0551,
       "step": 1902
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.9135483870967742,
-      "eval_loss": 0.03552273288369179,
-      "eval_runtime": 1.617,
-      "eval_samples_per_second": 1917.16,
-      "eval_steps_per_second": 40.199,
+      "eval_accuracy": 0.9119354838709678,
+      "eval_loss": 0.035356562584638596,
+      "eval_runtime": 3.1487,
+      "eval_samples_per_second": 984.536,
+      "eval_steps_per_second": 20.643,
       "step": 1908
     },
     {
       "epoch": 6.977987421383648,
-      "grad_norm": 0.2372261881828308,
+      "grad_norm": 0.30922219157218933,
       "learning_rate": 4.4933612858141165e-06,
-      "loss": 0.0508,
+      "loss": 0.0503,
       "step": 2219
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.9193548387096774,
-      "eval_loss": 0.033018212765455246,
-      "eval_runtime": 1.8153,
-      "eval_samples_per_second": 1707.728,
-      "eval_steps_per_second": 35.807,
+      "eval_accuracy": 0.9180645161290323,
+      "eval_loss": 0.03271542862057686,
+      "eval_runtime": 3.1361,
+      "eval_samples_per_second": 988.49,
+      "eval_steps_per_second": 20.726,
       "step": 2226
     },
     {
       "epoch": 7.9748427672955975,
-      "grad_norm": 0.26516783237457275,
+      "grad_norm": 0.27570685744285583,
       "learning_rate": 2.2781271837875614e-06,
-      "loss": 0.0479,
+      "loss": 0.0474,
       "step": 2536
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.9219354838709677,
-      "eval_loss": 0.03124028816819191,
-      "eval_runtime": 1.622,
-      "eval_samples_per_second": 1911.172,
-      "eval_steps_per_second": 40.073,
+      "eval_accuracy": 0.9203225806451613,
+      "eval_loss": 0.031012877821922302,
+      "eval_runtime": 2.9764,
+      "eval_samples_per_second": 1041.529,
+      "eval_steps_per_second": 21.839,
       "step": 2544
     },
     {
       "epoch": 8.971698113207546,
-      "grad_norm": 0.26064929366111755,
+      "grad_norm": 0.40512949228286743,
       "learning_rate": 6.289308176100629e-08,
-      "loss": 0.0462,
+      "loss": 0.046,
       "step": 2853
     }
   ],
@@ -165,8 +165,8 @@
   "train_batch_size": 48,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.26432685644138476,
+    "alpha": 0.006547213182126477,
     "num_train_epochs": 9,
-    "temperature": 15
+    "temperature": 20
   }
 }

run-1/checkpoint-2862/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a4cd3bd3d7b199838f7cc7ce3902cc5b5197f609f99417e50920c79fb92f710
-size 5368
+oid sha256:8b47f481f10cd643596d93df6439f6f373ebc1e96283a4fb4c2f3edf61ab3458
+size 5432

run-11/checkpoint-3180/config.json

@@ -326,6 +326,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.47.1",
+  "transformers_version": "4.47.0",
   "vocab_size": 30522
 }

run-11/checkpoint-3180/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c11c8d8fd5dab07dc0da9a774d4ac9892b28391145c860a4321a6d78b2468e5
+oid sha256:e39c4f5a6351f3075b5b3741515b1cd2a71b546343c8e64ebfd362859c446880
 size 268290900

run-11/checkpoint-3180/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf56a6a19086ea10089ac80d4b475b67fd4477ea849dc7ec47b9c3add6cf41d2
-size 536643898
+oid sha256:e5cf890b0e900fa8fb9af90e4a9608e082d3b705681d57cfdb8cf04b75a95eec
+size 536641018

run-11/checkpoint-3180/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4929abc25ddcb4d4986245c01bee45e03155019fd32282d1467b43fbdcdaed02
-size 14244
+oid sha256:2fbdf6070082bd7f064003b0a80093bbcf8031eab17e8484cd03c2f330dae634
+size 13990

run-11/checkpoint-3180/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33fadc11bb5c6bd0a5ea603f5e48cedcd72384fa2714656ecf6f8da629f7ae05
+oid sha256:7377b4a081dc59fc9c5a604a8fe62d7aa1f698f549e73e5c90d42a32e2a0d766
 size 1064

run-11/checkpoint-3180/trainer_state.json

@@ -10,153 +10,153 @@
   "log_history": [
     {
       "epoch": 0.9968553459119497,
-      "grad_norm": 0.9062672853469849,
+      "grad_norm": 0.6248980164527893,
       "learning_rate": 1.8006289308176103e-05,
-      "loss": 0.8042,
+      "loss": 0.3888,
       "step": 317
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6709677419354839,
-      "eval_loss": 0.4064599573612213,
-      "eval_runtime": 1.3737,
-      "eval_samples_per_second": 2256.722,
-      "eval_steps_per_second": 47.318,
+      "eval_accuracy": 0.5883870967741935,
+      "eval_loss": 0.19156621396541595,
+      "eval_runtime": 3.2342,
+      "eval_samples_per_second": 958.508,
+      "eval_steps_per_second": 20.098,
       "step": 318
     },
     {
       "epoch": 1.9937106918238994,
-      "grad_norm": 0.7205497026443481,
+      "grad_norm": 0.5106106400489807,
       "learning_rate": 1.6012578616352204e-05,
-      "loss": 0.3038,
+      "loss": 0.1606,
       "step": 634
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.847741935483871,
-      "eval_loss": 0.1362968385219574,
-      "eval_runtime": 1.392,
-      "eval_samples_per_second": 2227.027,
-      "eval_steps_per_second": 46.696,
+      "eval_accuracy": 0.824516129032258,
+      "eval_loss": 0.09305667877197266,
+      "eval_runtime": 3.4512,
+      "eval_samples_per_second": 898.226,
+      "eval_steps_per_second": 18.834,
       "step": 636
     },
     {
       "epoch": 2.990566037735849,
-      "grad_norm": 0.5987477898597717,
+      "grad_norm": 0.4880390465259552,
       "learning_rate": 1.4018867924528304e-05,
-      "loss": 0.1395,
+      "loss": 0.1004,
       "step": 951
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.8990322580645161,
-      "eval_loss": 0.07024983316659927,
-      "eval_runtime": 1.4088,
-      "eval_samples_per_second": 2200.388,
-      "eval_steps_per_second": 46.137,
+      "eval_accuracy": 0.8829032258064516,
+      "eval_loss": 0.061857614666223526,
+      "eval_runtime": 3.24,
+      "eval_samples_per_second": 956.798,
+      "eval_steps_per_second": 20.062,
       "step": 954
     },
     {
       "epoch": 3.9874213836477987,
-      "grad_norm": 0.5540674924850464,
+      "grad_norm": 0.36079642176628113,
       "learning_rate": 1.2025157232704403e-05,
-      "loss": 0.0891,
+      "loss": 0.0748,
       "step": 1268
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.9187096774193548,
-      "eval_loss": 0.04933710768818855,
-      "eval_runtime": 1.6037,
-      "eval_samples_per_second": 1932.992,
-      "eval_steps_per_second": 40.53,
+      "eval_accuracy": 0.8987096774193548,
+      "eval_loss": 0.04717925190925598,
+      "eval_runtime": 3.2015,
+      "eval_samples_per_second": 968.283,
+      "eval_steps_per_second": 20.303,
       "step": 1272
     },
     {
       "epoch": 4.984276729559748,
-      "grad_norm": 0.42864474654197693,
+      "grad_norm": 0.271781861782074,
       "learning_rate": 1.0031446540880504e-05,
-      "loss": 0.0692,
+      "loss": 0.0615,
       "step": 1585
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.9241935483870968,
-      "eval_loss": 0.04158218950033188,
-      "eval_runtime": 1.4224,
-      "eval_samples_per_second": 2179.482,
-      "eval_steps_per_second": 45.699,
+      "eval_accuracy": 0.9103225806451613,
+      "eval_loss": 0.038652800023555756,
+      "eval_runtime": 3.1772,
+      "eval_samples_per_second": 975.707,
+      "eval_steps_per_second": 20.458,
       "step": 1590
     },
     {
       "epoch": 5.981132075471698,
-      "grad_norm": 0.4545074999332428,
+      "grad_norm": 0.289711594581604,
       "learning_rate": 8.037735849056606e-06,
-      "loss": 0.0595,
+      "loss": 0.0536,
       "step": 1902
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.9270967741935484,
-      "eval_loss": 0.03682653605937958,
-      "eval_runtime": 1.4223,
-      "eval_samples_per_second": 2179.524,
-      "eval_steps_per_second": 45.7,
+      "eval_accuracy": 0.9158064516129032,
+      "eval_loss": 0.0337749719619751,
+      "eval_runtime": 3.3687,
+      "eval_samples_per_second": 920.232,
+      "eval_steps_per_second": 19.295,
       "step": 1908
     },
     {
       "epoch": 6.977987421383648,
-      "grad_norm": 0.34796932339668274,
+      "grad_norm": 0.3146103024482727,
       "learning_rate": 6.044025157232704e-06,
-      "loss": 0.0538,
+      "loss": 0.0484,
       "step": 2219
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.9316129032258065,
-      "eval_loss": 0.03404370695352554,
-      "eval_runtime": 1.6095,
-      "eval_samples_per_second": 1926.117,
-      "eval_steps_per_second": 40.386,
+      "eval_accuracy": 0.9225806451612903,
+      "eval_loss": 0.03082694299519062,
+      "eval_runtime": 3.1055,
+      "eval_samples_per_second": 998.238,
+      "eval_steps_per_second": 20.931,
       "step": 2226
     },
     {
       "epoch": 7.9748427672955975,
-      "grad_norm": 0.3150351941585541,
+      "grad_norm": 0.27518415451049805,
       "learning_rate": 4.0503144654088055e-06,
-      "loss": 0.0503,
+      "loss": 0.0452,
       "step": 2536
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.9341935483870968,
-      "eval_loss": 0.03234480321407318,
-      "eval_runtime": 1.4255,
-      "eval_samples_per_second": 2174.649,
-      "eval_steps_per_second": 45.597,
+      "eval_accuracy": 0.9251612903225807,
+      "eval_loss": 0.028789741918444633,
+      "eval_runtime": 3.1097,
+      "eval_samples_per_second": 996.886,
+      "eval_steps_per_second": 20.902,
       "step": 2544
     },
     {
       "epoch": 8.971698113207546,
-      "grad_norm": 0.3166097104549408,
+      "grad_norm": 0.40024998784065247,
       "learning_rate": 2.056603773584906e-06,
-      "loss": 0.0479,
+      "loss": 0.0432,
       "step": 2853
     },
     {
       "epoch": 9.0,
-      "eval_accuracy": 0.9341935483870968,
-      "eval_loss": 0.03134315088391304,
-      "eval_runtime": 1.6252,
-      "eval_samples_per_second": 1907.451,
-      "eval_steps_per_second": 39.995,
+      "eval_accuracy": 0.9274193548387096,
+      "eval_loss": 0.027747342362999916,
+      "eval_runtime": 3.1187,
+      "eval_samples_per_second": 994.017,
+      "eval_steps_per_second": 20.842,
       "step": 2862
     },
     {
       "epoch": 9.968553459119496,
-      "grad_norm": 0.27577438950538635,
+      "grad_norm": 0.25973939895629883,
       "learning_rate": 6.289308176100629e-08,
-      "loss": 0.0467,
+      "loss": 0.0422,
       "step": 3170
     }
   ],
@@ -177,12 +177,12 @@
       "attributes": {}
     }
   },
-  "total_flos": 825254092458012.0,
+  "total_flos": 825891210476556.0,
   "train_batch_size": 48,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.5555856325738124,
+    "alpha": 0.3626109413894891,
     "num_train_epochs": 10,
-    "temperature": 2
+    "temperature": 14
   }
 }

run-11/checkpoint-3180/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d588f08c0e85333fa2a4adcf5ec378e9adea9df69c799ff80677ef0f82a3e48a
-size 5368
+oid sha256:ca15aa91e74be22fabab116e726c428471c3d4cc15b083f9638589263aea63f6
+size 5432

run-2/checkpoint-2226/config.json

@@ -326,6 +326,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.46.0",
+  "transformers_version": "4.47.0",
   "vocab_size": 30522
 }

run-2/checkpoint-2226/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7586c4e99d5d4b32e4b1aba4a0ec5b4d63926d57bbe71073884dd6e79ba38719
+oid sha256:d21c2629c2336f045910f7661c94832c377dd49031fde1db8dabc8abf08f4a17
 size 268290900

run-2/checkpoint-2226/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ba3a2fafd95b6ac85b6ad825012445630065461647ce9bd2510c5d0ba04709c
-size 536643898
+oid sha256:7f9d2479050075cf2027eb90d278ea780b4da2cfeb45e2f5c284bfd2e5e24226
+size 536641018

run-2/checkpoint-2226/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c86b31c647c0ba29b04abf0053ecffa46df275085d5f4a709c9ca3bf059c7a52
-size 14244
+oid sha256:73aac57daf9622fa2240f61d454eeb9ca3c3b3e1932f7c53132d59e331b24bc0
+size 13990

run-2/checkpoint-2226/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a714cb799855607cfc29b07fed43ebac40ee6433a3533030fb77d73efbcb03e
+oid sha256:4ea195022b7a2fa1b5b6665ff3ac3f1d1c1ba4e0babbc4b87514eca79802f03a
 size 1064

run-2/checkpoint-2226/tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 512,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

run-2/checkpoint-2226/tokenizer_config.json

@@ -44,6 +44,7 @@
   "clean_up_tokenization_spaces": false,
   "cls_token": "[CLS]",
   "do_lower_case": true,
+  "extra_special_tokens": {},
   "mask_token": "[MASK]",
   "model_max_length": 512,
   "pad_token": "[PAD]",

run-2/checkpoint-2226/trainer_state.json

@@ -10,105 +10,105 @@
   "log_history": [
     {
       "epoch": 0.9968553459119497,
-      "grad_norm": 5.195394515991211,
+      "grad_norm": 0.6303415298461914,
       "learning_rate": 1.7151841868823e-05,
-      "loss": 6.1014,
+      "loss": 0.396,
       "step": 317
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7029032258064516,
-      "eval_loss": 4.2823262214660645,
-      "eval_runtime": 1.6916,
-      "eval_samples_per_second": 1832.562,
-      "eval_steps_per_second": 38.425,
+      "eval_accuracy": 0.5838709677419355,
+      "eval_loss": 0.19831246137619019,
+      "eval_runtime": 2.6427,
+      "eval_samples_per_second": 1173.021,
+      "eval_steps_per_second": 24.596,
       "step": 318
     },
     {
       "epoch": 1.9937106918238994,
-      "grad_norm": 5.344027996063232,
+      "grad_norm": 0.5234273076057434,
       "learning_rate": 1.4303683737646003e-05,
-      "loss": 3.305,
+      "loss": 0.1673,
       "step": 634
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.8483870967741935,
-      "eval_loss": 2.0671064853668213,
-      "eval_runtime": 1.711,
-      "eval_samples_per_second": 1811.854,
-      "eval_steps_per_second": 37.99,
+      "eval_accuracy": 0.8180645161290323,
+      "eval_loss": 0.09887824952602386,
+      "eval_runtime": 2.7628,
+      "eval_samples_per_second": 1122.047,
+      "eval_steps_per_second": 23.527,
       "step": 636
     },
     {
       "epoch": 2.990566037735849,
-      "grad_norm": 5.216258525848389,
+      "grad_norm": 0.5223647356033325,
       "learning_rate": 1.1455525606469004e-05,
-      "loss": 1.6799,
+      "loss": 0.1069,
       "step": 951
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.8990322580645161,
-      "eval_loss": 1.1862024068832397,
-      "eval_runtime": 1.7492,
-      "eval_samples_per_second": 1772.204,
-      "eval_steps_per_second": 37.159,
+      "eval_accuracy": 0.8767741935483871,
+      "eval_loss": 0.06768913567066193,
+      "eval_runtime": 2.6309,
+      "eval_samples_per_second": 1178.293,
+      "eval_steps_per_second": 24.706,
       "step": 954
     },
     {
       "epoch": 3.9874213836477987,
-      "grad_norm": 4.206549167633057,
+      "grad_norm": 0.3927612006664276,
       "learning_rate": 8.607367475292004e-06,
-      "loss": 1.0197,
+      "loss": 0.0819,
       "step": 1268
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.9267741935483871,
-      "eval_loss": 0.9180782437324524,
-      "eval_runtime": 1.7701,
-      "eval_samples_per_second": 1751.329,
-      "eval_steps_per_second": 36.721,
+      "eval_accuracy": 0.8938709677419355,
+      "eval_loss": 0.053172823041677475,
+      "eval_runtime": 2.702,
+      "eval_samples_per_second": 1147.312,
+      "eval_steps_per_second": 24.057,
       "step": 1272
     },
     {
       "epoch": 4.984276729559748,
-      "grad_norm": 3.6865780353546143,
+      "grad_norm": 0.30220165848731995,
       "learning_rate": 5.759209344115006e-06,
-      "loss": 0.78,
+      "loss": 0.0695,
       "step": 1585
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.932258064516129,
-      "eval_loss": 0.8304458856582642,
-      "eval_runtime": 1.7482,
-      "eval_samples_per_second": 1773.229,
-      "eval_steps_per_second": 37.181,
+      "eval_accuracy": 0.8990322580645161,
+      "eval_loss": 0.04547261819243431,
+      "eval_runtime": 3.3407,
+      "eval_samples_per_second": 927.945,
+      "eval_steps_per_second": 19.457,
       "step": 1590
     },
     {
       "epoch": 5.981132075471698,
-      "grad_norm": 5.803775787353516,
+      "grad_norm": 0.3224962651729584,
       "learning_rate": 2.911051212938006e-06,
-      "loss": 0.6853,
+      "loss": 0.0627,
       "step": 1902
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.9387096774193548,
-      "eval_loss": 0.8019915819168091,
-      "eval_runtime": 1.7576,
-      "eval_samples_per_second": 1763.757,
-      "eval_steps_per_second": 36.982,
+      "eval_accuracy": 0.9048387096774193,
+      "eval_loss": 0.04147931933403015,
+      "eval_runtime": 3.1677,
+      "eval_samples_per_second": 978.632,
+      "eval_steps_per_second": 20.52,
       "step": 1908
     },
     {
       "epoch": 6.977987421383648,
-      "grad_norm": 2.3245973587036133,
+      "grad_norm": 0.3125428557395935,
       "learning_rate": 6.289308176100629e-08,
-      "loss": 0.65,
+      "loss": 0.0593,
       "step": 2219
     }
   ],
@@ -133,8 +133,8 @@
   "train_batch_size": 48,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.9269823503052496,
+    "alpha": 0.05047358588899564,
     "num_train_epochs": 7,
-    "temperature": 11
+    "temperature": 12
   }
 }

run-2/checkpoint-2226/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f60d519bd755b34700e62a27d696f9fb6fa5cdd31ac58c6fc58cefb4a3620362
-size 5304
+oid sha256:e04d9c79bf0f03f0a69021b9b478b3ef1483880af663805ddd4ab3f9609ca849
+size 5432

run-3/checkpoint-2862/config.json

@@ -326,6 +326,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.45.2",
+  "transformers_version": "4.47.0",
   "vocab_size": 30522
 }

run-3/checkpoint-2862/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a7bec75e776cd487733ff1e96487bc2505714d839c2eeecdc042accc0f1b3a9
+oid sha256:e23c5dcded5e648aaffdde27776cb5b672800f6039b4720f301681c1f86af41e
 size 268290900

run-3/checkpoint-2862/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c59bbd466a86cf42e2c98a7569a2be10f5bf38a14ecfb954c2c6fccd1a2d2045
-size 536643898
+oid sha256:3251866b820cc8d031edcab3238e24ba3375c651612b4cfda68c770762831809
+size 536641018

run-3/checkpoint-2862/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b9e71d8b85c2c3bd3c2ff01693d7078f05f0c4c5121e6afa9ab875cbeb7116f
-size 14244
+oid sha256:e29353d4954fcf585947caa6a0a3fa59c7379d49f3bc56c6a4bd276fef18ca98
+size 13990

run-3/checkpoint-2862/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a738824491ff8b261b6db2a842e15bf80355d04a07892a16df2c4715b2ee556
+oid sha256:3c64bfaed33db311081ee0596530a03699ac7659f0cf4f57a488fea34df98816
 size 1064

run-3/checkpoint-2862/tokenizer_config.json

@@ -44,6 +44,7 @@
   "clean_up_tokenization_spaces": false,
   "cls_token": "[CLS]",
   "do_lower_case": true,
+  "extra_special_tokens": {},
   "mask_token": "[MASK]",
   "model_max_length": 512,
   "pad_token": "[PAD]",

run-3/checkpoint-2862/trainer_state.json

@@ -10,137 +10,137 @@
   "log_history": [
     {
       "epoch": 0.9968553459119497,
-      "grad_norm": 0.965503990650177,
+      "grad_norm": 0.6225002408027649,
       "learning_rate": 1.7784765897973445e-05,
-      "loss": 0.8047,
+      "loss": 0.3828,
       "step": 317
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6812903225806451,
-      "eval_loss": 0.4058631658554077,
-      "eval_runtime": 1.6943,
-      "eval_samples_per_second": 1829.632,
-      "eval_steps_per_second": 38.363,
+      "eval_accuracy": 0.5812903225806452,
+      "eval_loss": 0.18950515985488892,
+      "eval_runtime": 2.808,
+      "eval_samples_per_second": 1103.991,
+      "eval_steps_per_second": 23.148,
       "step": 318
     },
     {
       "epoch": 1.9937106918238994,
-      "grad_norm": 0.7085171341896057,
+      "grad_norm": 0.5088759064674377,
       "learning_rate": 1.556953179594689e-05,
-      "loss": 0.3062,
+      "loss": 0.1594,
       "step": 634
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.8503225806451613,
-      "eval_loss": 0.13832151889801025,
-      "eval_runtime": 1.7583,
-      "eval_samples_per_second": 1763.081,
-      "eval_steps_per_second": 36.968,
+      "eval_accuracy": 0.8183870967741935,
+      "eval_loss": 0.09329316020011902,
+      "eval_runtime": 3.1063,
+      "eval_samples_per_second": 997.977,
+      "eval_steps_per_second": 20.925,
       "step": 636
     },
     {
       "epoch": 2.990566037735849,
-      "grad_norm": 0.619353711605072,
+      "grad_norm": 0.4906318783760071,
       "learning_rate": 1.3354297693920338e-05,
-      "loss": 0.1421,
+      "loss": 0.1006,
       "step": 951
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.8958064516129032,
-      "eval_loss": 0.07200490683317184,
-      "eval_runtime": 1.7884,
-      "eval_samples_per_second": 1733.388,
-      "eval_steps_per_second": 36.345,
+      "eval_accuracy": 0.8793548387096775,
+      "eval_loss": 0.06283030658960342,
+      "eval_runtime": 4.811,
+      "eval_samples_per_second": 644.359,
+      "eval_steps_per_second": 13.511,
       "step": 954
     },
     {
       "epoch": 3.9874213836477987,
-      "grad_norm": 0.5501407384872437,
+      "grad_norm": 0.3708745539188385,
       "learning_rate": 1.1139063591893781e-05,
-      "loss": 0.0916,
+      "loss": 0.0757,
       "step": 1268
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.9125806451612903,
-      "eval_loss": 0.05142820626497269,
-      "eval_runtime": 1.7858,
-      "eval_samples_per_second": 1735.903,
-      "eval_steps_per_second": 36.398,
+      "eval_accuracy": 0.8961290322580645,
+      "eval_loss": 0.04845510795712471,
+      "eval_runtime": 3.0191,
+      "eval_samples_per_second": 1026.797,
+      "eval_steps_per_second": 21.53,
       "step": 1272
     },
     {
       "epoch": 4.984276729559748,
-      "grad_norm": 0.3894004821777344,
+      "grad_norm": 0.27722346782684326,
       "learning_rate": 8.923829489867226e-06,
-      "loss": 0.0717,
+      "loss": 0.0629,
       "step": 1585
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.925483870967742,
-      "eval_loss": 0.04311361908912659,
-      "eval_runtime": 1.7985,
-      "eval_samples_per_second": 1723.616,
-      "eval_steps_per_second": 36.14,
+      "eval_accuracy": 0.9064516129032258,
+      "eval_loss": 0.040148768573999405,
+      "eval_runtime": 3.1116,
+      "eval_samples_per_second": 996.286,
+      "eval_steps_per_second": 20.89,
       "step": 1590
     },
     {
       "epoch": 5.981132075471698,
-      "grad_norm": 0.4861418902873993,
+      "grad_norm": 0.2924395799636841,
       "learning_rate": 6.708595387840672e-06,
-      "loss": 0.0615,
+      "loss": 0.0553,
       "step": 1902
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.9261290322580645,
-      "eval_loss": 0.03821605071425438,
-      "eval_runtime": 1.8068,
-      "eval_samples_per_second": 1715.761,
-      "eval_steps_per_second": 35.976,
+      "eval_accuracy": 0.9119354838709678,
+      "eval_loss": 0.035382989794015884,
+      "eval_runtime": 3.3223,
+      "eval_samples_per_second": 933.091,
+      "eval_steps_per_second": 19.565,
       "step": 1908
     },
     {
       "epoch": 6.977987421383648,
-      "grad_norm": 0.3920305669307709,
+      "grad_norm": 0.3113860785961151,
       "learning_rate": 4.4933612858141165e-06,
-      "loss": 0.0561,
+      "loss": 0.0504,
       "step": 2219
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.9325806451612904,
-      "eval_loss": 0.035470735281705856,
-      "eval_runtime": 1.7961,
-      "eval_samples_per_second": 1725.979,
-      "eval_steps_per_second": 36.19,
+      "eval_accuracy": 0.917741935483871,
+      "eval_loss": 0.032723989337682724,
+      "eval_runtime": 3.2168,
+      "eval_samples_per_second": 963.691,
+      "eval_steps_per_second": 20.206,
       "step": 2226
     },
     {
       "epoch": 7.9748427672955975,
-      "grad_norm": 0.3401239514350891,
+      "grad_norm": 0.2782796621322632,
       "learning_rate": 2.2781271837875614e-06,
-      "loss": 0.0528,
+      "loss": 0.0475,
       "step": 2536
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.9316129032258065,
-      "eval_loss": 0.03403536230325699,
-      "eval_runtime": 1.8035,
-      "eval_samples_per_second": 1718.877,
-      "eval_steps_per_second": 36.041,
+      "eval_accuracy": 0.9212903225806451,
+      "eval_loss": 0.031014930456876755,
+      "eval_runtime": 3.1818,
+      "eval_samples_per_second": 974.289,
+      "eval_steps_per_second": 20.429,
       "step": 2544
     },
     {
       "epoch": 8.971698113207546,
-      "grad_norm": 0.3334876596927643,
+      "grad_norm": 0.4069852828979492,
       "learning_rate": 6.289308176100629e-08,
-      "loss": 0.0511,
+      "loss": 0.0461,
       "step": 2853
     }
   ],
@@ -165,8 +165,8 @@
   "train_batch_size": 48,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.6623158454366724,
+    "alpha": 0.7922936555306777,
     "num_train_epochs": 9,
-    "temperature": 2
+    "temperature": 18
   }
 }

run-3/checkpoint-2862/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65529af1ef1c2d0831a1f47d1b8ad3ab10ce486dd1675094550361b35d052a83
-size 5304
+oid sha256:97c320388240d19ad0ecfde84599ebf00cd322ef52aedde5ff6bf1e491e5fd63
+size 5432

run-4/checkpoint-3180/config.json

@@ -326,6 +326,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.46.0",
+  "transformers_version": "4.47.0",
   "vocab_size": 30522
 }

run-4/checkpoint-3180/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f62cce617d3ef7392e27e1cde8293e31311afd010709036d9b4a537e663900c1
+oid sha256:cb4df8f034a74c675c822de321d5497106933b35becabed718047a38fa6f5b86
 size 268290900

run-4/checkpoint-3180/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e6613a1e044f4a2530068329d4f97f4e0e4fd2b6291b67717ff98bde1977684
-size 536643898
+oid sha256:3c815349add5182d6fd20f4e3a86cc401804a4cee1914147befb3a4a434d3778
+size 536641018