Training in progress, step 3180

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ae88eff2997cf8baa4f19bc76eed6ee56ba9dca3d564bfe316860bf65c80beb
+oid sha256:7575b8f34069a3556fa6b92e375ecdfcb9def539ef43f6a9a0d5250c2dcd8341
 size 268290900

run-0/checkpoint-1908/config.json

@@ -326,6 +326,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.46.0",
+  "transformers_version": "4.47.1",
   "vocab_size": 30522
 }

run-0/checkpoint-1908/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9802dec6f780ed22e4cc78202f01ab0610369295dbe68e7bfad8b1e9d478ee4
+oid sha256:875c443793e1978ebf94e99d3942007ca7a82c93762ccdb4cd5fb38c9bde3afa
 size 268290900

run-0/checkpoint-1908/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7845b516b6e1c65ce766ad319d099046eae7798541cb9e7f4074098073cbfef
+oid sha256:1cac131bbdd0d0b3e1f4a50be9c390310cd77d69357c01c5659165c5a951d9fb
 size 536643898

run-0/checkpoint-1908/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8962814e39ffe555ee479c61278447db1b9c34b3aeef6bd09c7307fad28bd34
+oid sha256:d14f95ffbaab2d4fa2801f62f4298e1515abfd3ca8cb142a2f4254764699534d
 size 14244

run-0/checkpoint-1908/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-0/checkpoint-1908/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-0/checkpoint-1908/trainer_state.json

@@ -10,89 +10,89 @@
   "log_history": [
     {
       "epoch": 0.9968553459119497,
-      "grad_norm": 5.187047004699707,
+      "grad_norm": 0.632053554058075,
       "learning_rate": 1.6677148846960168e-05,
-      "loss": 6.1132,
+      "loss": 0.3846,
       "step": 317
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7012903225806452,
-      "eval_loss": 4.3197245597839355,
-      "eval_runtime": 1.6635,
-      "eval_samples_per_second": 1863.573,
-      "eval_steps_per_second": 39.075,
+      "eval_accuracy": 0.557741935483871,
+      "eval_loss": 0.19717106223106384,
+      "eval_runtime": 1.3544,
+      "eval_samples_per_second": 2288.857,
+      "eval_steps_per_second": 47.992,
       "step": 318
     },
     {
       "epoch": 1.9937106918238994,
-      "grad_norm": 5.349358081817627,
+      "grad_norm": 0.5204129815101624,
       "learning_rate": 1.3354297693920338e-05,
-      "loss": 3.3768,
+      "loss": 0.1664,
       "step": 634
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.8435483870967742,
-      "eval_loss": 2.160186767578125,
-      "eval_runtime": 1.6762,
-      "eval_samples_per_second": 1849.466,
-      "eval_steps_per_second": 38.779,
+      "eval_accuracy": 0.8083870967741935,
+      "eval_loss": 0.10131523758172989,
+      "eval_runtime": 1.3715,
+      "eval_samples_per_second": 2260.332,
+      "eval_steps_per_second": 47.394,
       "step": 636
     },
     {
       "epoch": 2.990566037735849,
-      "grad_norm": 5.328630447387695,
+      "grad_norm": 0.4809216558933258,
       "learning_rate": 1.0031446540880504e-05,
-      "loss": 1.7892,
+      "loss": 0.1085,
       "step": 951
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.8935483870967742,
-      "eval_loss": 1.2737469673156738,
-      "eval_runtime": 1.7036,
-      "eval_samples_per_second": 1819.697,
-      "eval_steps_per_second": 38.155,
+      "eval_accuracy": 0.8661290322580645,
+      "eval_loss": 0.0708962008357048,
+      "eval_runtime": 1.5023,
+      "eval_samples_per_second": 2063.55,
+      "eval_steps_per_second": 43.268,
       "step": 954
     },
     {
       "epoch": 3.9874213836477987,
-      "grad_norm": 4.597011089324951,
+      "grad_norm": 0.42957639694213867,
       "learning_rate": 6.708595387840672e-06,
-      "loss": 1.1236,
+      "loss": 0.0855,
       "step": 1268
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.92,
-      "eval_loss": 0.9856231808662415,
-      "eval_runtime": 1.7312,
-      "eval_samples_per_second": 1790.696,
-      "eval_steps_per_second": 37.547,
+      "eval_accuracy": 0.8864516129032258,
+      "eval_loss": 0.05744657292962074,
+      "eval_runtime": 1.5889,
+      "eval_samples_per_second": 1950.997,
+      "eval_steps_per_second": 40.908,
       "step": 1272
     },
     {
       "epoch": 4.984276729559748,
-      "grad_norm": 3.8782036304473877,
+      "grad_norm": 0.34376850724220276,
       "learning_rate": 3.385744234800839e-06,
-      "loss": 0.8713,
+      "loss": 0.074,
       "step": 1585
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.9274193548387096,
-      "eval_loss": 0.886253297328949,
-      "eval_runtime": 1.7341,
-      "eval_samples_per_second": 1787.663,
-      "eval_steps_per_second": 37.483,
+      "eval_accuracy": 0.8925806451612903,
+      "eval_loss": 0.05093748867511749,
+      "eval_runtime": 1.4074,
+      "eval_samples_per_second": 2202.709,
+      "eval_steps_per_second": 46.186,
       "step": 1590
     },
     {
       "epoch": 5.981132075471698,
-      "grad_norm": 5.870248794555664,
+      "grad_norm": 0.41636621952056885,
       "learning_rate": 6.289308176100629e-08,
-      "loss": 0.7789,
+      "loss": 0.0688,
       "step": 1902
     }
   ],
@@ -117,8 +117,8 @@
   "train_batch_size": 48,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.5566758316651013,
+    "alpha": 0.05221154439869735,
     "num_train_epochs": 6,
-    "temperature": 13
+    "temperature": 18
   }
 }

run-0/checkpoint-1908/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cf3f665fbce7cfa000c6bd3718a17c74d5e0e7f855dcf4f2aba26ab336ef01e
-size 5304
+oid sha256:c1d8b034fd319d5b7212c7387ccd4249ddb31cdde896a339e1373bbdc1742fd9
+size 5368

run-0/checkpoint-2862/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": "4.47.1",
+  "vocab_size": 30522
+}

run-0/checkpoint-2862/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59402a8e749f6f81edb9fd3634be2caed324507cdd27eccc7b96399c7d8d810d
+size 268290900

run-0/checkpoint-2862/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffb933fe78459386bc0b681965d73015af9d217d38eb07817f880f978519708c
+size 536643898

run-0/checkpoint-2862/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41b5282f1cde964bf5a382eb03f1cdd87f1c8e2f60e43277b3453f63947f5933
+size 14244

run-0/checkpoint-2862/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a738824491ff8b261b6db2a842e15bf80355d04a07892a16df2c4715b2ee556
+size 1064

run-0/checkpoint-2862/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-2862/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-2862/trainer_state.json

@@ -0,0 +1,172 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.0,
+  "eval_steps": 500,
+  "global_step": 2862,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9968553459119497,
+      "grad_norm": 0.6297022104263306,
+      "learning_rate": 1.7784765897973445e-05,
+      "loss": 0.3821,
+      "step": 317
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5680645161290323,
+      "eval_loss": 0.19172954559326172,
+      "eval_runtime": 1.3575,
+      "eval_samples_per_second": 2283.627,
+      "eval_steps_per_second": 47.883,
+      "step": 318
+    },
+    {
+      "epoch": 1.9937106918238994,
+      "grad_norm": 0.5253167152404785,
+      "learning_rate": 1.556953179594689e-05,
+      "loss": 0.1603,
+      "step": 634
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8248387096774193,
+      "eval_loss": 0.09447979182004929,
+      "eval_runtime": 1.5605,
+      "eval_samples_per_second": 1986.57,
+      "eval_steps_per_second": 41.654,
+      "step": 636
+    },
+    {
+      "epoch": 2.990566037735849,
+      "grad_norm": 0.4476560950279236,
+      "learning_rate": 1.3354297693920338e-05,
+      "loss": 0.101,
+      "step": 951
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8806451612903226,
+      "eval_loss": 0.06346584856510162,
+      "eval_runtime": 1.3904,
+      "eval_samples_per_second": 2229.649,
+      "eval_steps_per_second": 46.751,
+      "step": 954
+    },
+    {
+      "epoch": 3.9874213836477987,
+      "grad_norm": 0.3931984305381775,
+      "learning_rate": 1.1139063591893781e-05,
+      "loss": 0.0764,
+      "step": 1268
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8974193548387097,
+      "eval_loss": 0.04843955859541893,
+      "eval_runtime": 1.4033,
+      "eval_samples_per_second": 2209.103,
+      "eval_steps_per_second": 46.32,
+      "step": 1272
+    },
+    {
+      "epoch": 4.984276729559748,
+      "grad_norm": 0.2905353307723999,
+      "learning_rate": 8.923829489867226e-06,
+      "loss": 0.0631,
+      "step": 1585
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9064516129032258,
+      "eval_loss": 0.0406271256506443,
+      "eval_runtime": 1.601,
+      "eval_samples_per_second": 1936.266,
+      "eval_steps_per_second": 40.599,
+      "step": 1590
+    },
+    {
+      "epoch": 5.981132075471698,
+      "grad_norm": 0.3535286486148834,
+      "learning_rate": 6.708595387840672e-06,
+      "loss": 0.0553,
+      "step": 1902
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9129032258064517,
+      "eval_loss": 0.0355432964861393,
+      "eval_runtime": 1.6068,
+      "eval_samples_per_second": 1929.261,
+      "eval_steps_per_second": 40.452,
+      "step": 1908
+    },
+    {
+      "epoch": 6.977987421383648,
+      "grad_norm": 0.23496131598949432,
+      "learning_rate": 4.4933612858141165e-06,
+      "loss": 0.0506,
+      "step": 2219
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.9190322580645162,
+      "eval_loss": 0.033058661967515945,
+      "eval_runtime": 1.6082,
+      "eval_samples_per_second": 1927.576,
+      "eval_steps_per_second": 40.417,
+      "step": 2226
+    },
+    {
+      "epoch": 7.9748427672955975,
+      "grad_norm": 0.26389679312705994,
+      "learning_rate": 2.2781271837875614e-06,
+      "loss": 0.0478,
+      "step": 2536
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.922258064516129,
+      "eval_loss": 0.03128081187605858,
+      "eval_runtime": 1.6078,
+      "eval_samples_per_second": 1928.074,
+      "eval_steps_per_second": 40.427,
+      "step": 2544
+    },
+    {
+      "epoch": 8.971698113207546,
+      "grad_norm": 0.2600725591182709,
+      "learning_rate": 6.289308176100629e-08,
+      "loss": 0.0461,
+      "step": 2853
+    }
+  ],
+  "logging_steps": 317,
+  "max_steps": 2862,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "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": 742838622388212.0,
+  "train_batch_size": 48,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.7443072695022369,
+    "num_train_epochs": 9,
+    "temperature": 18
+  }
+}

run-0/checkpoint-2862/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36388ac8a2e7dc5319f05fd1d375ae42c70e154cbd7c64bd4a744ae715daf213
+size 5368

run-1/checkpoint-3180/config.json

@@ -326,6 +326,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.45.2",
+  "transformers_version": "4.47.1",
   "vocab_size": 30522
 }

run-1/checkpoint-3180/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8608f317b79583c57a72cf842cf0d0cb5b1d2b40dfe81b50b53c6652404325c
+oid sha256:7575b8f34069a3556fa6b92e375ecdfcb9def539ef43f6a9a0d5250c2dcd8341
 size 268290900

run-1/checkpoint-3180/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e856598db54a66dd6f2b35e5e02a0859c10727a86202fb4a3aa04d1d2faa2be
+oid sha256:527ed18d2f98418169aad8ea4f71cd69e6e2c658f07673ca02995611be7c7ac9
 size 536643898

run-1/checkpoint-3180/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acb5062e318cbe7ae055df28b0df8c2fb1c196d1f8ef47a1f6f1de04dd8779ef
+oid sha256:4929abc25ddcb4d4986245c01bee45e03155019fd32282d1467b43fbdcdaed02
 size 14244

run-1/checkpoint-3180/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-1/checkpoint-3180/trainer_state.json

@@ -10,153 +10,153 @@
   "log_history": [
     {
       "epoch": 0.9968553459119497,
-      "grad_norm": 0.731029212474823,
+      "grad_norm": 0.7034338116645813,
       "learning_rate": 1.8006289308176103e-05,
-      "loss": 0.408,
+      "loss": 0.4956,
       "step": 317
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5906451612903226,
-      "eval_loss": 0.20307187736034393,
-      "eval_runtime": 1.6907,
-      "eval_samples_per_second": 1833.602,
-      "eval_steps_per_second": 38.446,
+      "eval_accuracy": 0.6235483870967742,
+      "eval_loss": 0.2479861080646515,
+      "eval_runtime": 1.409,
+      "eval_samples_per_second": 2200.066,
+      "eval_steps_per_second": 46.13,
       "step": 318
     },
     {
       "epoch": 1.9937106918238994,
-      "grad_norm": 0.4595111310482025,
+      "grad_norm": 0.5720874071121216,
       "learning_rate": 1.6012578616352204e-05,
-      "loss": 0.1697,
+      "loss": 0.2003,
       "step": 634
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.8306451612903226,
-      "eval_loss": 0.09759204834699631,
-      "eval_runtime": 1.7036,
-      "eval_samples_per_second": 1819.686,
-      "eval_steps_per_second": 38.155,
+      "eval_accuracy": 0.8458064516129032,
+      "eval_loss": 0.1080671176314354,
+      "eval_runtime": 1.4057,
+      "eval_samples_per_second": 2205.242,
+      "eval_steps_per_second": 46.239,
       "step": 636
     },
     {
       "epoch": 2.990566037735849,
-      "grad_norm": 0.43162059783935547,
+      "grad_norm": 0.4831989109516144,
       "learning_rate": 1.4018867924528304e-05,
-      "loss": 0.104,
+      "loss": 0.1151,
       "step": 951
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.88,
-      "eval_loss": 0.06371938437223434,
-      "eval_runtime": 1.7221,
-      "eval_samples_per_second": 1800.179,
-      "eval_steps_per_second": 37.746,
+      "eval_accuracy": 0.89,
+      "eval_loss": 0.06548640131950378,
+      "eval_runtime": 1.3958,
+      "eval_samples_per_second": 2220.975,
+      "eval_steps_per_second": 46.569,
       "step": 954
     },
     {
       "epoch": 3.9874213836477987,
-      "grad_norm": 0.3561622202396393,
+      "grad_norm": 0.42286917567253113,
       "learning_rate": 1.2025157232704403e-05,
-      "loss": 0.0773,
+      "loss": 0.0818,
       "step": 1268
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.8977419354838709,
-      "eval_loss": 0.04856124520301819,
-      "eval_runtime": 1.7777,
-      "eval_samples_per_second": 1743.857,
-      "eval_steps_per_second": 36.565,
+      "eval_accuracy": 0.9093548387096774,
+      "eval_loss": 0.04679400101304054,
+      "eval_runtime": 1.406,
+      "eval_samples_per_second": 2204.91,
+      "eval_steps_per_second": 46.232,
       "step": 1272
     },
     {
       "epoch": 4.984276729559748,
-      "grad_norm": 0.2814004123210907,
+      "grad_norm": 0.3328923285007477,
       "learning_rate": 1.0031446540880504e-05,
-      "loss": 0.0631,
+      "loss": 0.0651,
       "step": 1585
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.9067741935483871,
-      "eval_loss": 0.0395587794482708,
-      "eval_runtime": 1.7657,
-      "eval_samples_per_second": 1755.721,
-      "eval_steps_per_second": 36.814,
+      "eval_accuracy": 0.92,
+      "eval_loss": 0.03822105750441551,
+      "eval_runtime": 1.4116,
+      "eval_samples_per_second": 2196.097,
+      "eval_steps_per_second": 46.047,
       "step": 1590
     },
     {
       "epoch": 5.981132075471698,
-      "grad_norm": 0.39958587288856506,
+      "grad_norm": 0.39607134461402893,
       "learning_rate": 8.037735849056606e-06,
-      "loss": 0.0544,
+      "loss": 0.0559,
       "step": 1902
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.9183870967741935,
-      "eval_loss": 0.03417970985174179,
-      "eval_runtime": 1.8,
-      "eval_samples_per_second": 1722.246,
-      "eval_steps_per_second": 36.112,
+      "eval_accuracy": 0.9229032258064516,
+      "eval_loss": 0.03295356407761574,
+      "eval_runtime": 1.617,
+      "eval_samples_per_second": 1917.139,
+      "eval_steps_per_second": 40.198,
       "step": 1908
     },
     {
       "epoch": 6.977987421383648,
-      "grad_norm": 0.27226564288139343,
+      "grad_norm": 0.26325827836990356,
       "learning_rate": 6.044025157232704e-06,
-      "loss": 0.0493,
+      "loss": 0.0504,
       "step": 2219
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.9248387096774193,
-      "eval_loss": 0.031123189255595207,
-      "eval_runtime": 1.7804,
-      "eval_samples_per_second": 1741.143,
-      "eval_steps_per_second": 36.508,
+      "eval_accuracy": 0.9296774193548387,
+      "eval_loss": 0.030274854972958565,
+      "eval_runtime": 1.4258,
+      "eval_samples_per_second": 2174.156,
+      "eval_steps_per_second": 45.587,
       "step": 2226
     },
     {
       "epoch": 7.9748427672955975,
-      "grad_norm": 0.2539806067943573,
+      "grad_norm": 0.28463679552078247,
       "learning_rate": 4.0503144654088055e-06,
-      "loss": 0.0459,
+      "loss": 0.0471,
       "step": 2536
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.9258064516129032,
-      "eval_loss": 0.029144473373889923,
-      "eval_runtime": 1.8058,
-      "eval_samples_per_second": 1716.732,
-      "eval_steps_per_second": 35.996,
+      "eval_accuracy": 0.9306451612903226,
+      "eval_loss": 0.028280112892389297,
+      "eval_runtime": 1.6101,
+      "eval_samples_per_second": 1925.4,
+      "eval_steps_per_second": 40.371,
       "step": 2544
     },
     {
       "epoch": 8.971698113207546,
-      "grad_norm": 0.24147309362888336,
+      "grad_norm": 0.2851262390613556,
       "learning_rate": 2.056603773584906e-06,
-      "loss": 0.0438,
+      "loss": 0.0447,
       "step": 2853
     },
     {
       "epoch": 9.0,
-      "eval_accuracy": 0.9270967741935484,
-      "eval_loss": 0.028016844764351845,
-      "eval_runtime": 1.7889,
-      "eval_samples_per_second": 1732.923,
-      "eval_steps_per_second": 36.335,
+      "eval_accuracy": 0.9316129032258065,
+      "eval_loss": 0.027305563911795616,
+      "eval_runtime": 1.4211,
+      "eval_samples_per_second": 2181.375,
+      "eval_steps_per_second": 45.738,
       "step": 2862
     },
     {
       "epoch": 9.968553459119496,
-      "grad_norm": 0.20841307938098907,
+      "grad_norm": 0.23048533499240875,
       "learning_rate": 6.289308176100629e-08,
-      "loss": 0.0426,
+      "loss": 0.0436,
       "step": 3170
     }
   ],
@@ -181,8 +181,8 @@
   "train_batch_size": 48,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.47967279863257795,
+    "alpha": 0.479590968478409,
     "num_train_epochs": 10,
-    "temperature": 9
+    "temperature": 4
   }
 }

run-1/checkpoint-3180/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a25d63abf0cdd55f7279d86dd585a8ef38e8e89522e1ffd1f4a381861fcedd19
-size 5304
+oid sha256:f3bd23609e985559a616c9631c99462f912fb8a30ef310cb72038f93f14e14ab
+size 5368

runs/Dec19_21-14-18_P920/events.out.tfevents.1734616645.P920.569418.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:883c72918604a5c0119bfd0e64903161d6b8543bc114411fef11dd40826dd62d
+size 16136

runs/Dec19_21-14-18_P920/events.out.tfevents.1734617770.P920.569418.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:963f24a847b7d868c1a5dc243478d36192e89eadf8e8107f4a8cc64d0f42eb45
+size 17738

runs/Dec19_21-14-18_P920/events.out.tfevents.1734619113.P920.569418.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e734864403c401b9c440215072b8b84b8a665c3d48e4f35e47bcf02ba3a057a
+size 18273

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31cd5f487e3fbfad20a27180fc05cf6a3ecb007575cd7f6b719b5afc79fd7371
+oid sha256:f3bd23609e985559a616c9631c99462f912fb8a30ef310cb72038f93f14e14ab
 size 5368