Training in progress, step 3800

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ba6a5c243564173590016b93c2b48661f84cf3cbad8b0a7b1d37d2e7d692483
+oid sha256:ad5e3eb1dcb5ad24a1cb4e368a276a43d92ed83cd39eb998c4eea97037975683
 size 275341720

last-checkpoint/README.md

@@ -207,4 +207,4 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 [More Information Needed]
 ### Framework versions
 
-- PEFT 0.20.0
+- PEFT 0.19.1

last-checkpoint/adapter_config.json

@@ -27,21 +27,20 @@
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
-  "monteclora_config": null,
   "peft_type": "LORA",
-  "peft_version": "0.20.0",
+  "peft_version": "0.19.1",
   "qalora_group_size": 16,
   "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "k_proj",
+    "v_proj",
+    "q_proj",
     "down_proj",
-    "o_proj",
     "gate_proj",
-    "q_proj",
-    "k_proj",
-    "up_proj",
-    "v_proj"
+    "o_proj",
+    "up_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",
@@ -49,6 +48,5 @@
   "use_bdlora": null,
   "use_dora": false,
   "use_qalora": false,
-  "use_rslora": false,
-  "velora_config": null
+  "use_rslora": false
 }

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ba6a5c243564173590016b93c2b48661f84cf3cbad8b0a7b1d37d2e7d692483
+oid sha256:266a9975e538d5172b24571c56d759b82af1f6fe5f8401c0cca8b9ee3e084ff7
 size 275341720

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fece671d5a5da026c2f834e973e8da1bc3a0c7781aa88d66ea4fa4a0ec9eccb
+oid sha256:9cc5d6bc9ec977cd43b1a8c67b55e0531dd33ba00194c86475375e0496146b0c
 size 142323235

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e477dbe6ee6901786088d8e8c1ac2b73001161b76c783fff7a8f73c940197360
+oid sha256:45b67858659b4dfc3e1470897037774241f60eeba7a480b68826613d2df0626a
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 200,
   "best_metric": 0.6362597942352295,
   "best_model_checkpoint": "/kaggle/working/faqih_checkpoints/checkpoint-200",
-  "epoch": 0.9470568891811904,
+  "epoch": 0.15784281486353174,
   "eval_steps": 200,
-  "global_step": 3600,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -100,426 +100,6 @@
       "learning_rate": 0.00018473101265822786,
       "loss": 0.6356534576416015,
       "step": 600
-    },
-    {
-      "epoch": 0.17099638276882603,
-      "grad_norm": 0.23116259276866913,
-      "learning_rate": 0.00018341244725738397,
-      "loss": 0.6304442214965821,
-      "step": 650
-    },
-    {
-      "epoch": 0.18414995067412035,
-      "grad_norm": 0.1896994709968567,
-      "learning_rate": 0.00018209388185654008,
-      "loss": 0.6102799224853516,
-      "step": 700
-    },
-    {
-      "epoch": 0.19730351857941467,
-      "grad_norm": 0.20064501464366913,
-      "learning_rate": 0.00018077531645569622,
-      "loss": 0.6039998626708984,
-      "step": 750
-    },
-    {
-      "epoch": 0.21045708648470898,
-      "grad_norm": 0.20514807105064392,
-      "learning_rate": 0.00017945675105485233,
-      "loss": 0.6030560302734375,
-      "step": 800
-    },
-    {
-      "epoch": 0.2236106543900033,
-      "grad_norm": 0.20657017827033997,
-      "learning_rate": 0.00017813818565400844,
-      "loss": 0.5951737976074218,
-      "step": 850
-    },
-    {
-      "epoch": 0.2367642222952976,
-      "grad_norm": 0.21234729886054993,
-      "learning_rate": 0.00017681962025316457,
-      "loss": 0.6114842224121094,
-      "step": 900
-    },
-    {
-      "epoch": 0.2499177902005919,
-      "grad_norm": 0.19885726273059845,
-      "learning_rate": 0.00017550105485232068,
-      "loss": 0.6019914245605469,
-      "step": 950
-    },
-    {
-      "epoch": 0.2630713581058862,
-      "grad_norm": 0.22743742167949677,
-      "learning_rate": 0.0001741824894514768,
-      "loss": 0.6196039962768555,
-      "step": 1000
-    },
-    {
-      "epoch": 0.27622492601118054,
-      "grad_norm": 0.2094801813364029,
-      "learning_rate": 0.00017286392405063293,
-      "loss": 0.5877687454223632,
-      "step": 1050
-    },
-    {
-      "epoch": 0.28937849391647485,
-      "grad_norm": 0.22727341949939728,
-      "learning_rate": 0.00017154535864978904,
-      "loss": 0.6195404434204101,
-      "step": 1100
-    },
-    {
-      "epoch": 0.30253206182176917,
-      "grad_norm": 0.23307493329048157,
-      "learning_rate": 0.00017022679324894515,
-      "loss": 0.6037686920166015,
-      "step": 1150
-    },
-    {
-      "epoch": 0.3156856297270635,
-      "grad_norm": 0.20066751539707184,
-      "learning_rate": 0.00016890822784810128,
-      "loss": 0.6005681228637695,
-      "step": 1200
-    },
-    {
-      "epoch": 0.3288391976323578,
-      "grad_norm": 0.2251257598400116,
-      "learning_rate": 0.0001675896624472574,
-      "loss": 0.5749369049072266,
-      "step": 1250
-    },
-    {
-      "epoch": 0.34199276553765207,
-      "grad_norm": 0.19875267148017883,
-      "learning_rate": 0.0001662710970464135,
-      "loss": 0.5884634399414063,
-      "step": 1300
-    },
-    {
-      "epoch": 0.3551463334429464,
-      "grad_norm": 0.21068838238716125,
-      "learning_rate": 0.00016495253164556964,
-      "loss": 0.5809454345703124,
-      "step": 1350
-    },
-    {
-      "epoch": 0.3682999013482407,
-      "grad_norm": 0.2040138989686966,
-      "learning_rate": 0.00016363396624472575,
-      "loss": 0.6071104431152343,
-      "step": 1400
-    },
-    {
-      "epoch": 0.381453469253535,
-      "grad_norm": 0.21657569706439972,
-      "learning_rate": 0.00016231540084388186,
-      "loss": 0.6062085723876953,
-      "step": 1450
-    },
-    {
-      "epoch": 0.39460703715882933,
-      "grad_norm": 0.21580874919891357,
-      "learning_rate": 0.000160996835443038,
-      "loss": 0.5930040740966797,
-      "step": 1500
-    },
-    {
-      "epoch": 0.40776060506412365,
-      "grad_norm": 0.20997387170791626,
-      "learning_rate": 0.0001596782700421941,
-      "loss": 0.5776944351196289,
-      "step": 1550
-    },
-    {
-      "epoch": 0.42091417296941797,
-      "grad_norm": 0.22081924974918365,
-      "learning_rate": 0.0001583597046413502,
-      "loss": 0.5901007843017578,
-      "step": 1600
-    },
-    {
-      "epoch": 0.4340677408747123,
-      "grad_norm": 0.18726694583892822,
-      "learning_rate": 0.00015704113924050635,
-      "loss": 0.583731803894043,
-      "step": 1650
-    },
-    {
-      "epoch": 0.4472213087800066,
-      "grad_norm": 0.19900982081890106,
-      "learning_rate": 0.00015572257383966246,
-      "loss": 0.5790575027465821,
-      "step": 1700
-    },
-    {
-      "epoch": 0.4603748766853009,
-      "grad_norm": 0.2211243063211441,
-      "learning_rate": 0.00015440400843881857,
-      "loss": 0.577286262512207,
-      "step": 1750
-    },
-    {
-      "epoch": 0.4735284445905952,
-      "grad_norm": 0.2111779749393463,
-      "learning_rate": 0.0001530854430379747,
-      "loss": 0.5685956954956055,
-      "step": 1800
-    },
-    {
-      "epoch": 0.4866820124958895,
-      "grad_norm": 0.21098685264587402,
-      "learning_rate": 0.0001517668776371308,
-      "loss": 0.5858037185668945,
-      "step": 1850
-    },
-    {
-      "epoch": 0.4998355804011838,
-      "grad_norm": 0.1963949352502823,
-      "learning_rate": 0.00015044831223628692,
-      "loss": 0.5649369049072266,
-      "step": 1900
-    },
-    {
-      "epoch": 0.5129891483064781,
-      "grad_norm": 0.21639689803123474,
-      "learning_rate": 0.00014912974683544306,
-      "loss": 0.5866766357421875,
-      "step": 1950
-    },
-    {
-      "epoch": 0.5261427162117724,
-      "grad_norm": 0.2360610067844391,
-      "learning_rate": 0.00014781118143459917,
-      "loss": 0.5642653274536132,
-      "step": 2000
-    },
-    {
-      "epoch": 0.5392962841170668,
-      "grad_norm": 0.17728404700756073,
-      "learning_rate": 0.00014649261603375528,
-      "loss": 0.5934088516235352,
-      "step": 2050
-    },
-    {
-      "epoch": 0.5524498520223611,
-      "grad_norm": 0.22524195909500122,
-      "learning_rate": 0.00014517405063291141,
-      "loss": 0.5913956069946289,
-      "step": 2100
-    },
-    {
-      "epoch": 0.5656034199276554,
-      "grad_norm": 0.18563304841518402,
-      "learning_rate": 0.00014385548523206752,
-      "loss": 0.5767417526245118,
-      "step": 2150
-    },
-    {
-      "epoch": 0.5787569878329497,
-      "grad_norm": 0.2004818171262741,
-      "learning_rate": 0.00014253691983122363,
-      "loss": 0.5942864227294922,
-      "step": 2200
-    },
-    {
-      "epoch": 0.591910555738244,
-      "grad_norm": 0.2049906700849533,
-      "learning_rate": 0.00014121835443037977,
-      "loss": 0.571412467956543,
-      "step": 2250
-    },
-    {
-      "epoch": 0.6050641236435383,
-      "grad_norm": 0.19811300933361053,
-      "learning_rate": 0.00013989978902953588,
-      "loss": 0.5904967880249024,
-      "step": 2300
-    },
-    {
-      "epoch": 0.6182176915488327,
-      "grad_norm": 0.2060481756925583,
-      "learning_rate": 0.000138581223628692,
-      "loss": 0.5787500381469727,
-      "step": 2350
-    },
-    {
-      "epoch": 0.631371259454127,
-      "grad_norm": 0.18603748083114624,
-      "learning_rate": 0.00013726265822784812,
-      "loss": 0.5815290832519531,
-      "step": 2400
-    },
-    {
-      "epoch": 0.6445248273594213,
-      "grad_norm": 0.21810391545295715,
-      "learning_rate": 0.00013594409282700423,
-      "loss": 0.5819861221313477,
-      "step": 2450
-    },
-    {
-      "epoch": 0.6576783952647156,
-      "grad_norm": 0.20363149046897888,
-      "learning_rate": 0.00013462552742616034,
-      "loss": 0.5840290069580079,
-      "step": 2500
-    },
-    {
-      "epoch": 0.6708319631700098,
-      "grad_norm": 0.21661260724067688,
-      "learning_rate": 0.00013330696202531648,
-      "loss": 0.5717618179321289,
-      "step": 2550
-    },
-    {
-      "epoch": 0.6839855310753041,
-      "grad_norm": 0.21132707595825195,
-      "learning_rate": 0.0001319883966244726,
-      "loss": 0.5572832489013672,
-      "step": 2600
-    },
-    {
-      "epoch": 0.6971390989805984,
-      "grad_norm": 0.1978549361228943,
-      "learning_rate": 0.0001306698312236287,
-      "loss": 0.5476178741455078,
-      "step": 2650
-    },
-    {
-      "epoch": 0.7102926668858928,
-      "grad_norm": 0.20024415850639343,
-      "learning_rate": 0.0001293512658227848,
-      "loss": 0.5517565155029297,
-      "step": 2700
-    },
-    {
-      "epoch": 0.7234462347911871,
-      "grad_norm": 0.20441296696662903,
-      "learning_rate": 0.00012803270042194094,
-      "loss": 0.5709645462036133,
-      "step": 2750
-    },
-    {
-      "epoch": 0.7365998026964814,
-      "grad_norm": 0.2133142352104187,
-      "learning_rate": 0.00012671413502109705,
-      "loss": 0.5618978881835938,
-      "step": 2800
-    },
-    {
-      "epoch": 0.7497533706017757,
-      "grad_norm": 0.2041858285665512,
-      "learning_rate": 0.00012539556962025316,
-      "loss": 0.5499007034301758,
-      "step": 2850
-    },
-    {
-      "epoch": 0.76290693850707,
-      "grad_norm": 0.23104150593280792,
-      "learning_rate": 0.0001240770042194093,
-      "loss": 0.5771116256713867,
-      "step": 2900
-    },
-    {
-      "epoch": 0.7760605064123643,
-      "grad_norm": 0.20818471908569336,
-      "learning_rate": 0.0001227584388185654,
-      "loss": 0.559295654296875,
-      "step": 2950
-    },
-    {
-      "epoch": 0.7892140743176587,
-      "grad_norm": 0.19819001853466034,
-      "learning_rate": 0.00012143987341772152,
-      "loss": 0.5422830963134766,
-      "step": 3000
-    },
-    {
-      "epoch": 0.802367642222953,
-      "grad_norm": 0.2149215042591095,
-      "learning_rate": 0.00012012130801687764,
-      "loss": 0.5710384368896484,
-      "step": 3050
-    },
-    {
-      "epoch": 0.8155212101282473,
-      "grad_norm": 0.1951475739479065,
-      "learning_rate": 0.00011880274261603376,
-      "loss": 0.5525796127319336,
-      "step": 3100
-    },
-    {
-      "epoch": 0.8286747780335416,
-      "grad_norm": 0.20850563049316406,
-      "learning_rate": 0.00011748417721518987,
-      "loss": 0.5578081512451172,
-      "step": 3150
-    },
-    {
-      "epoch": 0.8418283459388359,
-      "grad_norm": 0.21047161519527435,
-      "learning_rate": 0.000116165611814346,
-      "loss": 0.5627962112426758,
-      "step": 3200
-    },
-    {
-      "epoch": 0.8549819138441302,
-      "grad_norm": 0.20235857367515564,
-      "learning_rate": 0.00011484704641350212,
-      "loss": 0.5524932861328125,
-      "step": 3250
-    },
-    {
-      "epoch": 0.8681354817494246,
-      "grad_norm": 0.23249448835849762,
-      "learning_rate": 0.00011352848101265823,
-      "loss": 0.5648232269287109,
-      "step": 3300
-    },
-    {
-      "epoch": 0.8812890496547189,
-      "grad_norm": 0.21543475985527039,
-      "learning_rate": 0.00011220991561181435,
-      "loss": 0.542757682800293,
-      "step": 3350
-    },
-    {
-      "epoch": 0.8944426175600132,
-      "grad_norm": 0.19726432859897614,
-      "learning_rate": 0.00011089135021097049,
-      "loss": 0.5540407943725586,
-      "step": 3400
-    },
-    {
-      "epoch": 0.9075961854653075,
-      "grad_norm": 0.21633584797382355,
-      "learning_rate": 0.00010957278481012658,
-      "loss": 0.5423409271240235,
-      "step": 3450
-    },
-    {
-      "epoch": 0.9207497533706018,
-      "grad_norm": 0.1918056756258011,
-      "learning_rate": 0.0001082542194092827,
-      "loss": 0.5391794967651368,
-      "step": 3500
-    },
-    {
-      "epoch": 0.933903321275896,
-      "grad_norm": 0.20544877648353577,
-      "learning_rate": 0.00010693565400843884,
-      "loss": 0.5497972106933594,
-      "step": 3550
-    },
-    {
-      "epoch": 0.9470568891811904,
-      "grad_norm": 0.20916621387004852,
-      "learning_rate": 0.00010561708860759494,
-      "loss": 0.5546447372436524,
-      "step": 3600
     }
   ],
   "logging_steps": 50,
@@ -539,7 +119,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.4861555044678656e+18,
+  "total_flos": 7.489718726034186e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34f353c448b484cfebf8c7e25bfc7699a62f45447bbb965aeca60fbba78dbc3f
+oid sha256:2dcb9fd1efebc7c487e99696e7655a5dce1fb979ef93fc72ec06ba1e079f6ebf
 size 5777