Training in progress, step 500, checkpoint

last-checkpoint/adapter_config.json

@@ -20,7 +20,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 128,
+  "lora_alpha": 256,
   "lora_bias": false,
   "lora_dropout": 0,
   "megatron_config": null,
@@ -29,17 +29,17 @@
   "peft_type": "LORA",
   "peft_version": "0.18.1",
   "qalora_group_size": 16,
-  "r": 64,
+  "r": 128,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "up_proj",
-    "down_proj",
     "gate_proj",
-    "o_proj",
+    "down_proj",
+    "up_proj",
+    "q_proj",
+    "v_proj",
     "k_proj",
-    "v_proj"
+    "o_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6eda6363323c6d79792a81bd69d938b3a58d34e1eb645e055ee597b8bf472ad
-size 60785144
+oid sha256:018cb6d9db46f0ce13f349c696bdff67ba6a901dfa5aed13a0d047c7e30d4f9c
+size 121537408

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebc1f15cea2729790f76d46a9aa205d07f6d4e3b1ddf01b2a41c940267766469
-size 31149205
+oid sha256:68e7ed425766c35922189444ff63fdd81e7ebecc193c7c6e5fc44ea98e0cc541
+size 62000725

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:181c5f0270cf39930062ddfa3767a2481d0c360f120b11f8e25dbf533a1cdaba
+oid sha256:f1d565802a8e26c4e8a31328752b7a7fdc186d9401aa008e65697d0ad8c22e33
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd1b8760497cf2afe6ff758fde5edda9af4f73c2c6f23659a7e5f0cb97215d93
+oid sha256:4b9811df9ea96a4280268b28843ba2166267f887cc556319f28a0df33b75a25a
 size 1465

last-checkpoint/trainer_state.json

@@ -2,1066 +2,366 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.0,
+  "epoch": 0.32,
   "eval_steps": 500,
-  "global_step": 1500,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.02,
-      "grad_norm": 6.955190181732178,
+      "epoch": 0.0064,
+      "grad_norm": 40.911293029785156,
       "learning_rate": 9e-05,
-      "loss": 1.8499,
+      "loss": 1.1173,
       "step": 10
     },
     {
-      "epoch": 0.04,
-      "grad_norm": 8.705879211425781,
+      "epoch": 0.0128,
+      "grad_norm": 4.927021026611328,
       "learning_rate": 0.00019,
-      "loss": 0.1145,
+      "loss": 0.9803,
       "step": 20
     },
     {
-      "epoch": 0.06,
-      "grad_norm": 1.1119884252548218,
-      "learning_rate": 0.00019998175187996916,
-      "loss": 0.0391,
+      "epoch": 0.0192,
+      "grad_norm": 13.638679504394531,
+      "learning_rate": 0.00019999816639538432,
+      "loss": 0.4325,
       "step": 30
     },
     {
-      "epoch": 0.08,
-      "grad_norm": 1.489068865776062,
-      "learning_rate": 0.0001999186805091047,
-      "loss": 0.0224,
+      "epoch": 0.0256,
+      "grad_norm": 3.560319423675537,
+      "learning_rate": 0.00019999182809538713,
+      "loss": 0.1852,
       "step": 40
     },
     {
-      "epoch": 0.1,
-      "grad_norm": 0.8914257884025574,
-      "learning_rate": 0.00019981058901312606,
-      "loss": 0.0211,
+      "epoch": 0.032,
+      "grad_norm": 0.6141765117645264,
+      "learning_rate": 0.00019998096274980728,
+      "loss": 0.1316,
       "step": 50
     },
     {
-      "epoch": 0.12,
-      "grad_norm": 0.17663325369358063,
-      "learning_rate": 0.00019965752609456464,
-      "loss": 0.0078,
+      "epoch": 0.0384,
+      "grad_norm": 12.074165344238281,
+      "learning_rate": 0.00019996557085056414,
+      "loss": 0.1166,
       "step": 60
     },
     {
-      "epoch": 0.14,
-      "grad_norm": 0.03448864817619324,
-      "learning_rate": 0.00019945956071862003,
-      "loss": 0.0081,
+      "epoch": 0.0448,
+      "grad_norm": 3.718775749206543,
+      "learning_rate": 0.00019994565309451292,
+      "loss": 0.1073,
       "step": 70
     },
     {
-      "epoch": 0.16,
-      "grad_norm": 4.913799285888672,
-      "learning_rate": 0.00019921678208208654,
-      "loss": 0.0047,
+      "epoch": 0.0512,
+      "grad_norm": 3.271156072616577,
+      "learning_rate": 0.0001999212103834132,
+      "loss": 0.2006,
       "step": 80
     },
     {
-      "epoch": 0.18,
-      "grad_norm": 0.6515750885009766,
-      "learning_rate": 0.00019892929957316397,
-      "loss": 0.0115,
+      "epoch": 0.0576,
+      "grad_norm": 1.295325756072998,
+      "learning_rate": 0.00019989224382388813,
+      "loss": 0.0938,
       "step": 90
     },
     {
-      "epoch": 0.2,
-      "grad_norm": 0.25924447178840637,
-      "learning_rate": 0.00019859724272217099,
-      "loss": 0.0168,
+      "epoch": 0.064,
+      "grad_norm": 1.3511019945144653,
+      "learning_rate": 0.00019985875472737415,
+      "loss": 0.0729,
       "step": 100
     },
     {
-      "epoch": 0.22,
-      "grad_norm": 0.21993209421634674,
-      "learning_rate": 0.0001982207611431827,
-      "loss": 0.0097,
+      "epoch": 0.0704,
+      "grad_norm": 0.43467989563941956,
+      "learning_rate": 0.00019982074461006194,
+      "loss": 0.0511,
       "step": 110
     },
     {
-      "epoch": 0.24,
-      "grad_norm": 1.2233567237854004,
-      "learning_rate": 0.00019780002446661966,
-      "loss": 0.0079,
+      "epoch": 0.0768,
+      "grad_norm": 0.451219767332077,
+      "learning_rate": 0.0001997782151928274,
+      "loss": 0.0431,
       "step": 120
     },
     {
-      "epoch": 0.26,
-      "grad_norm": 0.14659936726093292,
-      "learning_rate": 0.0001973352222628176,
-      "loss": 0.0041,
+      "epoch": 0.0832,
+      "grad_norm": 0.5558948516845703,
+      "learning_rate": 0.00019973116840115397,
+      "loss": 0.1314,
       "step": 130
     },
     {
-      "epoch": 0.28,
-      "grad_norm": 0.13708041608333588,
-      "learning_rate": 0.0001968265639566135,
-      "loss": 0.0047,
+      "epoch": 0.0896,
+      "grad_norm": 0.31716081500053406,
+      "learning_rate": 0.00019967960636504547,
+      "loss": 0.058,
       "step": 140
     },
     {
-      "epoch": 0.3,
-      "grad_norm": 0.11654426902532578,
-      "learning_rate": 0.0001962742787329852,
-      "loss": 0.0039,
+      "epoch": 0.096,
+      "grad_norm": 0.08058512210845947,
+      "learning_rate": 0.00019962353141892946,
+      "loss": 0.0373,
       "step": 150
     },
     {
-      "epoch": 0.32,
-      "grad_norm": 0.1725812405347824,
-      "learning_rate": 0.00019567861543378837,
-      "loss": 0.0041,
+      "epoch": 0.1024,
+      "grad_norm": 0.0707520842552185,
+      "learning_rate": 0.00019956294610155186,
+      "loss": 0.0288,
       "step": 160
     },
     {
-      "epoch": 0.34,
-      "grad_norm": 0.002145808655768633,
-      "learning_rate": 0.00019503984244563616,
-      "loss": 0.0017,
+      "epoch": 0.1088,
+      "grad_norm": 0.06796549260616302,
+      "learning_rate": 0.00019949785315586172,
+      "loss": 0.026,
       "step": 170
     },
     {
-      "epoch": 0.36,
-      "grad_norm": 2.0850086212158203,
-      "learning_rate": 0.000194358247578973,
-      "loss": 0.0048,
+      "epoch": 0.1152,
+      "grad_norm": 1.5500516891479492,
+      "learning_rate": 0.00019942825552888717,
+      "loss": 0.029,
       "step": 180
     },
     {
-      "epoch": 0.38,
-      "grad_norm": 0.07945302873849869,
-      "learning_rate": 0.00019363413793839658,
-      "loss": 0.0051,
+      "epoch": 0.1216,
+      "grad_norm": 0.6438320279121399,
+      "learning_rate": 0.00019935415637160203,
+      "loss": 0.0321,
       "step": 190
     },
     {
-      "epoch": 0.4,
-      "grad_norm": 0.231564462184906,
-      "learning_rate": 0.00019286783978428624,
-      "loss": 0.0078,
+      "epoch": 0.128,
+      "grad_norm": 0.7204006314277649,
+      "learning_rate": 0.0001992755590387831,
+      "loss": 0.0359,
       "step": 200
     },
     {
-      "epoch": 0.42,
-      "grad_norm": 0.013585828244686127,
-      "learning_rate": 0.00019205969838580094,
-      "loss": 0.0042,
+      "epoch": 0.1344,
+      "grad_norm": 0.28932827711105347,
+      "learning_rate": 0.0001991924670888582,
+      "loss": 0.0252,
       "step": 210
     },
     {
-      "epoch": 0.44,
-      "grad_norm": 0.009324288927018642,
-      "learning_rate": 0.00019121007786531178,
-      "loss": 0.0056,
+      "epoch": 0.1408,
+      "grad_norm": 0.46170133352279663,
+      "learning_rate": 0.0001991048842837452,
+      "loss": 0.0191,
       "step": 220
     },
     {
-      "epoch": 0.46,
-      "grad_norm": 0.0634087324142456,
-      "learning_rate": 0.00019031936103434044,
-      "loss": 0.0046,
+      "epoch": 0.1472,
+      "grad_norm": 13.702939987182617,
+      "learning_rate": 0.00019901281458868173,
+      "loss": 0.0851,
       "step": 230
     },
     {
-      "epoch": 0.48,
-      "grad_norm": 0.06287066638469696,
-      "learning_rate": 0.00018938794922107675,
-      "loss": 0.0028,
+      "epoch": 0.1536,
+      "grad_norm": 0.1703188419342041,
+      "learning_rate": 0.00019891626217204538,
+      "loss": 0.032,
       "step": 240
     },
     {
-      "epoch": 0.5,
-      "grad_norm": 0.0060167331248521805,
-      "learning_rate": 0.00018841626208955292,
-      "loss": 0.0027,
+      "epoch": 0.16,
+      "grad_norm": 0.1269959956407547,
+      "learning_rate": 0.00019881523140516535,
+      "loss": 0.0254,
       "step": 250
     },
     {
-      "epoch": 0.52,
-      "grad_norm": 0.0029571247287094593,
-      "learning_rate": 0.0001874047374505569,
-      "loss": 0.0046,
+      "epoch": 0.1664,
+      "grad_norm": 0.39395102858543396,
+      "learning_rate": 0.00019870972686212427,
+      "loss": 0.0465,
       "step": 260
     },
     {
-      "epoch": 0.54,
-      "grad_norm": 0.0028790035285055637,
-      "learning_rate": 0.00018635383106436855,
-      "loss": 0.0028,
+      "epoch": 0.1728,
+      "grad_norm": 0.7702052593231201,
+      "learning_rate": 0.00019859975331955126,
+      "loss": 0.0332,
       "step": 270
     },
     {
-      "epoch": 0.56,
-      "grad_norm": 0.04535164311528206,
-      "learning_rate": 0.00018526401643540922,
-      "loss": 0.0046,
+      "epoch": 0.1792,
+      "grad_norm": 0.12844760715961456,
+      "learning_rate": 0.00019848531575640557,
+      "loss": 0.044,
       "step": 280
     },
     {
-      "epoch": 0.58,
-      "grad_norm": 0.09899382293224335,
-      "learning_rate": 0.0001841357845988957,
-      "loss": 0.0037,
+      "epoch": 0.1856,
+      "grad_norm": 0.36863207817077637,
+      "learning_rate": 0.00019836641935375125,
+      "loss": 0.0233,
       "step": 290
     },
     {
-      "epoch": 0.6,
-      "grad_norm": 0.6568487286567688,
-      "learning_rate": 0.00018296964389959578,
-      "loss": 0.0101,
+      "epoch": 0.192,
+      "grad_norm": 0.9188430309295654,
+      "learning_rate": 0.00019824306949452254,
+      "loss": 0.0276,
       "step": 300
     },
     {
-      "epoch": 0.62,
-      "grad_norm": 0.16598820686340332,
-      "learning_rate": 0.00018176611976278441,
-      "loss": 0.0237,
+      "epoch": 0.1984,
+      "grad_norm": 0.49796220660209656,
+      "learning_rate": 0.00019811527176328016,
+      "loss": 0.0303,
       "step": 310
     },
     {
-      "epoch": 0.64,
-      "grad_norm": 0.08521094173192978,
-      "learning_rate": 0.00018052575445750419,
-      "loss": 0.0058,
+      "epoch": 0.2048,
+      "grad_norm": 0.29771795868873596,
+      "learning_rate": 0.00019798303194595846,
+      "loss": 0.0148,
       "step": 320
     },
     {
-      "epoch": 0.66,
-      "grad_norm": 1.5081530809402466,
-      "learning_rate": 0.00017924910685223643,
-      "loss": 0.0205,
+      "epoch": 0.2112,
+      "grad_norm": 0.08168808370828629,
+      "learning_rate": 0.00019784635602960353,
+      "loss": 0.0147,
       "step": 330
     },
     {
-      "epoch": 0.68,
-      "grad_norm": 0.35874947905540466,
-      "learning_rate": 0.0001779367521630931,
-      "loss": 0.1046,
+      "epoch": 0.2176,
+      "grad_norm": 0.0375661738216877,
+      "learning_rate": 0.00019770525020210204,
+      "loss": 0.0181,
       "step": 340
     },
     {
-      "epoch": 0.7,
-      "grad_norm": 0.229485422372818,
-      "learning_rate": 0.00017658928169464312,
-      "loss": 0.0129,
+      "epoch": 0.224,
+      "grad_norm": 0.032354097813367844,
+      "learning_rate": 0.00019755972085190124,
+      "loss": 0.0136,
       "step": 350
     },
     {
-      "epoch": 0.72,
-      "grad_norm": 0.4974204897880554,
-      "learning_rate": 0.00017520730257348946,
-      "loss": 0.006,
+      "epoch": 0.2304,
+      "grad_norm": 0.03650612756609917,
+      "learning_rate": 0.0001974097745677195,
+      "loss": 0.0134,
       "step": 360
     },
     {
-      "epoch": 0.74,
-      "grad_norm": 0.8693443536758423,
-      "learning_rate": 0.00017379143747471768,
-      "loss": 0.0075,
+      "epoch": 0.2368,
+      "grad_norm": 0.04585101455450058,
+      "learning_rate": 0.00019725541813824825,
+      "loss": 0.018,
       "step": 370
     },
     {
-      "epoch": 0.76,
-      "grad_norm": 1.4635262489318848,
-      "learning_rate": 0.00017234232434133883,
-      "loss": 0.0077,
+      "epoch": 0.2432,
+      "grad_norm": 0.02587795816361904,
+      "learning_rate": 0.00019709665855184447,
+      "loss": 0.0171,
       "step": 380
     },
     {
-      "epoch": 0.78,
-      "grad_norm": 0.047906193882226944,
-      "learning_rate": 0.00017086061609685257,
-      "loss": 0.0094,
+      "epoch": 0.2496,
+      "grad_norm": 0.019718684256076813,
+      "learning_rate": 0.00019693350299621442,
+      "loss": 0.0126,
       "step": 390
     },
     {
-      "epoch": 0.8,
-      "grad_norm": 0.13906188309192657,
-      "learning_rate": 0.00016934698035106133,
-      "loss": 0.0096,
+      "epoch": 0.256,
+      "grad_norm": 0.01756865903735161,
+      "learning_rate": 0.0001967659588580881,
+      "loss": 0.0107,
       "step": 400
     },
     {
-      "epoch": 0.82,
-      "grad_norm": 0.11411689221858978,
-      "learning_rate": 0.00016780209909926676,
-      "loss": 0.0092,
+      "epoch": 0.2624,
+      "grad_norm": 0.017915094271302223,
+      "learning_rate": 0.00019659403372288489,
+      "loss": 0.0102,
       "step": 410
     },
     {
-      "epoch": 0.84,
-      "grad_norm": 0.011227969080209732,
-      "learning_rate": 0.00016622666841498463,
-      "loss": 0.0084,
+      "epoch": 0.2688,
+      "grad_norm": 0.01841767504811287,
+      "learning_rate": 0.00019641773537437004,
+      "loss": 0.0108,
       "step": 420
     },
     {
-      "epoch": 0.86,
-      "grad_norm": 1.5423718690872192,
-      "learning_rate": 0.00016462139813631693,
-      "loss": 0.0041,
+      "epoch": 0.2752,
+      "grad_norm": 0.01479355152696371,
+      "learning_rate": 0.00019623707179430253,
+      "loss": 0.0116,
       "step": 430
     },
     {
-      "epoch": 0.88,
-      "grad_norm": 0.347548246383667,
-      "learning_rate": 0.00016298701154612147,
-      "loss": 0.0046,
+      "epoch": 0.2816,
+      "grad_norm": 0.01765090599656105,
+      "learning_rate": 0.00019605205116207333,
+      "loss": 0.0119,
       "step": 440
     },
     {
-      "epoch": 0.9,
-      "grad_norm": 0.03537672758102417,
-      "learning_rate": 0.00016132424504612406,
-      "loss": 0.016,
+      "epoch": 0.288,
+      "grad_norm": 0.014900445006787777,
+      "learning_rate": 0.0001958626818543353,
+      "loss": 0.0128,
       "step": 450
     },
     {
-      "epoch": 0.92,
-      "grad_norm": 0.05080743879079819,
-      "learning_rate": 0.00015963384782511993,
-      "loss": 0.006,
+      "epoch": 0.2944,
+      "grad_norm": 0.01522466167807579,
+      "learning_rate": 0.00019566897244462398,
+      "loss": 0.0129,
       "step": 460
     },
     {
-      "epoch": 0.94,
-      "grad_norm": 0.00858448538929224,
-      "learning_rate": 0.00015791658152141327,
-      "loss": 0.0047,
+      "epoch": 0.3008,
+      "grad_norm": 0.014997781254351139,
+      "learning_rate": 0.0001954709317029693,
+      "loss": 0.0129,
       "step": 470
     },
     {
-      "epoch": 0.96,
-      "grad_norm": 0.19455233216285706,
-      "learning_rate": 0.00015617321987964776,
-      "loss": 0.0044,
+      "epoch": 0.3072,
+      "grad_norm": 0.01686343364417553,
+      "learning_rate": 0.00019526856859549863,
+      "loss": 0.0135,
       "step": 480
     },
     {
-      "epoch": 0.98,
-      "grad_norm": 0.08450737595558167,
-      "learning_rate": 0.00015440454840218225,
-      "loss": 0.0039,
+      "epoch": 0.3136,
+      "grad_norm": 0.012961529195308685,
+      "learning_rate": 0.00019506189228403082,
+      "loss": 0.0127,
       "step": 490
     },
     {
-      "epoch": 1.0,
-      "grad_norm": 0.006426886655390263,
-      "learning_rate": 0.00015261136399516873,
-      "loss": 0.003,
+      "epoch": 0.32,
+      "grad_norm": 0.0174432210624218,
+      "learning_rate": 0.00019485091212566132,
+      "loss": 0.0117,
       "step": 500
-    },
-    {
-      "epoch": 1.02,
-      "grad_norm": 0.11707904934883118,
-      "learning_rate": 0.00015079447460949238,
-      "loss": 0.0053,
-      "step": 510
-    },
-    {
-      "epoch": 1.04,
-      "grad_norm": 0.005810865201056004,
-      "learning_rate": 0.00014895469887673483,
-      "loss": 0.0028,
-      "step": 520
-    },
-    {
-      "epoch": 1.06,
-      "grad_norm": 0.007626334670931101,
-      "learning_rate": 0.00014709286574032536,
-      "loss": 0.0036,
-      "step": 530
-    },
-    {
-      "epoch": 1.08,
-      "grad_norm": 0.012294676154851913,
-      "learning_rate": 0.00014520981408204574,
-      "loss": 0.0014,
-      "step": 540
-    },
-    {
-      "epoch": 1.1,
-      "grad_norm": 0.0394788458943367,
-      "learning_rate": 0.00014330639234405742,
-      "loss": 0.0032,
-      "step": 550
-    },
-    {
-      "epoch": 1.12,
-      "grad_norm": 0.006509778555482626,
-      "learning_rate": 0.00014138345814662068,
-      "loss": 0.0026,
-      "step": 560
-    },
-    {
-      "epoch": 1.1400000000000001,
-      "grad_norm": 0.12478422373533249,
-      "learning_rate": 0.0001394418779016789,
-      "loss": 0.0072,
-      "step": 570
-    },
-    {
-      "epoch": 1.16,
-      "grad_norm": 0.03920350596308708,
-      "learning_rate": 0.00013748252642248115,
-      "loss": 0.0034,
-      "step": 580
-    },
-    {
-      "epoch": 1.18,
-      "grad_norm": 0.06001276522874832,
-      "learning_rate": 0.00013550628652941985,
-      "loss": 0.003,
-      "step": 590
-    },
-    {
-      "epoch": 1.2,
-      "grad_norm": 0.016110895201563835,
-      "learning_rate": 0.0001335140486522604,
-      "loss": 0.0028,
-      "step": 600
-    },
-    {
-      "epoch": 1.22,
-      "grad_norm": 0.012471065856516361,
-      "learning_rate": 0.00013150671042894228,
-      "loss": 0.003,
-      "step": 610
-    },
-    {
-      "epoch": 1.24,
-      "grad_norm": 0.03785092383623123,
-      "learning_rate": 0.00012948517630113245,
-      "loss": 0.0036,
-      "step": 620
-    },
-    {
-      "epoch": 1.26,
-      "grad_norm": 0.06877022981643677,
-      "learning_rate": 0.0001274503571067131,
-      "loss": 0.0032,
-      "step": 630
-    },
-    {
-      "epoch": 1.28,
-      "grad_norm": 0.14263379573822021,
-      "learning_rate": 0.00012540316966938795,
-      "loss": 0.0038,
-      "step": 640
-    },
-    {
-      "epoch": 1.3,
-      "grad_norm": 0.011557388119399548,
-      "learning_rate": 0.00012334453638559057,
-      "loss": 0.0034,
-      "step": 650
-    },
-    {
-      "epoch": 1.32,
-      "grad_norm": 0.05995357036590576,
-      "learning_rate": 0.00012127538480888283,
-      "loss": 0.0034,
-      "step": 660
-    },
-    {
-      "epoch": 1.34,
-      "grad_norm": 0.06527257710695267,
-      "learning_rate": 0.00011919664723202906,
-      "loss": 0.0028,
-      "step": 670
-    },
-    {
-      "epoch": 1.3599999999999999,
-      "grad_norm": 0.12198451906442642,
-      "learning_rate": 0.00011710926026693525,
-      "loss": 0.003,
-      "step": 680
-    },
-    {
-      "epoch": 1.38,
-      "grad_norm": 0.005978007335215807,
-      "learning_rate": 0.00011501416442264184,
-      "loss": 0.0035,
-      "step": 690
-    },
-    {
-      "epoch": 1.4,
-      "grad_norm": 0.01665549911558628,
-      "learning_rate": 0.00011291230368156087,
-      "loss": 0.0065,
-      "step": 700
-    },
-    {
-      "epoch": 1.42,
-      "grad_norm": 0.24193237721920013,
-      "learning_rate": 0.00011080462507414806,
-      "loss": 0.0066,
-      "step": 710
-    },
-    {
-      "epoch": 1.44,
-      "grad_norm": 0.04041582718491554,
-      "learning_rate": 0.00010869207825220147,
-      "loss": 0.0025,
-      "step": 720
-    },
-    {
-      "epoch": 1.46,
-      "grad_norm": 0.0575215183198452,
-      "learning_rate": 0.0001065756150609792,
-      "loss": 0.0066,
-      "step": 730
-    },
-    {
-      "epoch": 1.48,
-      "grad_norm": 0.06933045387268066,
-      "learning_rate": 0.00010445618911032853,
-      "loss": 0.0031,
-      "step": 740
-    },
-    {
-      "epoch": 1.5,
-      "grad_norm": 0.08046724647283554,
-      "learning_rate": 0.00010233475534502042,
-      "loss": 0.0035,
-      "step": 750
-    },
-    {
-      "epoch": 1.52,
-      "grad_norm": 0.12715864181518555,
-      "learning_rate": 0.00010021226961448209,
-      "loss": 0.0031,
-      "step": 760
-    },
-    {
-      "epoch": 1.54,
-      "grad_norm": 0.05433020740747452,
-      "learning_rate": 9.808968824212234e-05,
-      "loss": 0.0016,
-      "step": 770
-    },
-    {
-      "epoch": 1.56,
-      "grad_norm": 0.005047277547419071,
-      "learning_rate": 9.596796759444293e-05,
-      "loss": 0.0023,
-      "step": 780
-    },
-    {
-      "epoch": 1.58,
-      "grad_norm": 0.06136553734540939,
-      "learning_rate": 9.384806365013113e-05,
-      "loss": 0.0037,
-      "step": 790
-    },
-    {
-      "epoch": 1.6,
-      "grad_norm": 0.07095402479171753,
-      "learning_rate": 9.173093156932623e-05,
-      "loss": 0.0032,
-      "step": 800
-    },
-    {
-      "epoch": 1.62,
-      "grad_norm": 0.007647352758795023,
-      "learning_rate": 8.961752526325565e-05,
-      "loss": 0.0031,
-      "step": 810
-    },
-    {
-      "epoch": 1.6400000000000001,
-      "grad_norm": 0.10909626632928848,
-      "learning_rate": 8.750879696443321e-05,
-      "loss": 0.0044,
-      "step": 820
-    },
-    {
-      "epoch": 1.6600000000000001,
-      "grad_norm": 0.005036857444792986,
-      "learning_rate": 8.540569679761391e-05,
-      "loss": 0.0017,
-      "step": 830
-    },
-    {
-      "epoch": 1.6800000000000002,
-      "grad_norm": 0.04456391558051109,
-      "learning_rate": 8.330917235169867e-05,
-      "loss": 0.0028,
-      "step": 840
-    },
-    {
-      "epoch": 1.7,
-      "grad_norm": 0.026686355471611023,
-      "learning_rate": 8.12201682527811e-05,
-      "loss": 0.0009,
-      "step": 850
-    },
-    {
-      "epoch": 1.72,
-      "grad_norm": 0.5429267883300781,
-      "learning_rate": 7.913962573852996e-05,
-      "loss": 0.0042,
-      "step": 860
-    },
-    {
-      "epoch": 1.74,
-      "grad_norm": 0.09535812586545944,
-      "learning_rate": 7.706848223409759e-05,
-      "loss": 0.003,
-      "step": 870
-    },
-    {
-      "epoch": 1.76,
-      "grad_norm": 0.004211663268506527,
-      "learning_rate": 7.500767092974647e-05,
-      "loss": 0.0034,
-      "step": 880
-    },
-    {
-      "epoch": 1.78,
-      "grad_norm": 0.007590270135551691,
-      "learning_rate": 7.295812036038407e-05,
-      "loss": 0.0023,
-      "step": 890
-    },
-    {
-      "epoch": 1.8,
-      "grad_norm": 0.09613944590091705,
-      "learning_rate": 7.092075398719502e-05,
-      "loss": 0.0029,
-      "step": 900
-    },
-    {
-      "epoch": 1.8199999999999998,
-      "grad_norm": 0.04118485003709793,
-      "learning_rate": 6.889648978155909e-05,
-      "loss": 0.0018,
-      "step": 910
-    },
-    {
-      "epoch": 1.8399999999999999,
-      "grad_norm": 0.03493022918701172,
-      "learning_rate": 6.688623981144339e-05,
-      "loss": 0.003,
-      "step": 920
-    },
-    {
-      "epoch": 1.8599999999999999,
-      "grad_norm": 0.05923795700073242,
-      "learning_rate": 6.489090983045379e-05,
-      "loss": 0.0023,
-      "step": 930
-    },
-    {
-      "epoch": 1.88,
-      "grad_norm": 0.004041542299091816,
-      "learning_rate": 6.291139886973169e-05,
-      "loss": 0.0019,
-      "step": 940
-    },
-    {
-      "epoch": 1.9,
-      "grad_norm": 0.058228544890880585,
-      "learning_rate": 6.094859883287977e-05,
-      "loss": 0.0027,
-      "step": 950
-    },
-    {
-      "epoch": 1.92,
-      "grad_norm": 0.0040581803768873215,
-      "learning_rate": 5.90033940940989e-05,
-      "loss": 0.0013,
-      "step": 960
-    },
-    {
-      "epoch": 1.94,
-      "grad_norm": 0.0043375324457883835,
-      "learning_rate": 5.7076661099717986e-05,
-      "loss": 0.0025,
-      "step": 970
-    },
-    {
-      "epoch": 1.96,
-      "grad_norm": 0.0034573073498904705,
-      "learning_rate": 5.5169267973295294e-05,
-      "loss": 0.002,
-      "step": 980
-    },
-    {
-      "epoch": 1.98,
-      "grad_norm": 0.03163556754589081,
-      "learning_rate": 5.3282074124470284e-05,
-      "loss": 0.0021,
-      "step": 990
-    },
-    {
-      "epoch": 2.0,
-      "grad_norm": 0.027402976527810097,
-      "learning_rate": 5.141592986174151e-05,
-      "loss": 0.0032,
-      "step": 1000
-    },
-    {
-      "epoch": 2.02,
-      "grad_norm": 0.03729909658432007,
-      "learning_rate": 4.957167600934474e-05,
-      "loss": 0.0027,
-      "step": 1010
-    },
-    {
-      "epoch": 2.04,
-      "grad_norm": 0.06650708615779877,
-      "learning_rate": 4.7750143528405126e-05,
-      "loss": 0.0031,
-      "step": 1020
-    },
-    {
-      "epoch": 2.06,
-      "grad_norm": 0.05407334491610527,
-      "learning_rate": 4.595215314253285e-05,
-      "loss": 0.0024,
-      "step": 1030
-    },
-    {
-      "epoch": 2.08,
-      "grad_norm": 0.06878269463777542,
-      "learning_rate": 4.417851496803164e-05,
-      "loss": 0.0031,
-      "step": 1040
-    },
-    {
-      "epoch": 2.1,
-      "grad_norm": 0.11301030218601227,
-      "learning_rate": 4.243002814888656e-05,
-      "loss": 0.0029,
-      "step": 1050
-    },
-    {
-      "epoch": 2.12,
-      "grad_norm": 0.0333506241440773,
-      "learning_rate": 4.0707480496695514e-05,
-      "loss": 0.0022,
-      "step": 1060
-    },
-    {
-      "epoch": 2.14,
-      "grad_norm": 0.07614877074956894,
-      "learning_rate": 3.9011648135706966e-05,
-      "loss": 0.0022,
-      "step": 1070
-    },
-    {
-      "epoch": 2.16,
-      "grad_norm": 0.0026465761475265026,
-      "learning_rate": 3.734329515312349e-05,
-      "loss": 0.0023,
-      "step": 1080
-    },
-    {
-      "epoch": 2.18,
-      "grad_norm": 0.003543775761500001,
-      "learning_rate": 3.570317325482847e-05,
-      "loss": 0.0017,
-      "step": 1090
-    },
-    {
-      "epoch": 2.2,
-      "grad_norm": 0.058600034564733505,
-      "learning_rate": 3.409202142669213e-05,
-      "loss": 0.0035,
-      "step": 1100
-    },
-    {
-      "epoch": 2.22,
-      "grad_norm": 0.04403044655919075,
-      "learning_rate": 3.251056560160821e-05,
-      "loss": 0.003,
-      "step": 1110
-    },
-    {
-      "epoch": 2.24,
-      "grad_norm": 0.12272568047046661,
-      "learning_rate": 3.095951833241213e-05,
-      "loss": 0.003,
-      "step": 1120
-    },
-    {
-      "epoch": 2.26,
-      "grad_norm": 0.003978225402534008,
-      "learning_rate": 2.9439578470827755e-05,
-      "loss": 0.0026,
-      "step": 1130
-    },
-    {
-      "epoch": 2.2800000000000002,
-      "grad_norm": 0.0032513344194740057,
-      "learning_rate": 2.7951430852587268e-05,
-      "loss": 0.0035,
-      "step": 1140
-    },
-    {
-      "epoch": 2.3,
-      "grad_norm": 0.0030118192080408335,
-      "learning_rate": 2.649574598886665e-05,
-      "loss": 0.0021,
-      "step": 1150
-    },
-    {
-      "epoch": 2.32,
-      "grad_norm": 0.050590354949235916,
-      "learning_rate": 2.507317976417475e-05,
-      "loss": 0.0031,
-      "step": 1160
-    },
-    {
-      "epoch": 2.34,
-      "grad_norm": 0.024627618491649628,
-      "learning_rate": 2.3684373140833016e-05,
-      "loss": 0.0029,
-      "step": 1170
-    },
-    {
-      "epoch": 2.36,
-      "grad_norm": 0.05296558514237404,
-      "learning_rate": 2.2329951870178655e-05,
-      "loss": 0.0041,
-      "step": 1180
-    },
-    {
-      "epoch": 2.38,
-      "grad_norm": 0.00513384910300374,
-      "learning_rate": 2.1010526210621406e-05,
-      "loss": 0.002,
-      "step": 1190
-    },
-    {
-      "epoch": 2.4,
-      "grad_norm": 0.008860021829605103,
-      "learning_rate": 1.9726690652680578e-05,
-      "loss": 0.0019,
-      "step": 1200
-    },
-    {
-      "epoch": 2.42,
-      "grad_norm": 0.0037229766603559256,
-      "learning_rate": 1.8479023651127115e-05,
-      "loss": 0.0023,
-      "step": 1210
-    },
-    {
-      "epoch": 2.44,
-      "grad_norm": 0.004817347973585129,
-      "learning_rate": 1.726808736435046e-05,
-      "loss": 0.0015,
-      "step": 1220
-    },
-    {
-      "epoch": 2.46,
-      "grad_norm": 0.05881744623184204,
-      "learning_rate": 1.6094427401068224e-05,
-      "loss": 0.0028,
-      "step": 1230
-    },
-    {
-      "epoch": 2.48,
-      "grad_norm": 0.00562276691198349,
-      "learning_rate": 1.4958572574492501e-05,
-      "loss": 0.0023,
-      "step": 1240
-    },
-    {
-      "epoch": 2.5,
-      "grad_norm": 0.0030358799267560244,
-      "learning_rate": 1.38610346640637e-05,
-      "loss": 0.0018,
-      "step": 1250
-    },
-    {
-      "epoch": 2.52,
-      "grad_norm": 0.003225122345611453,
-      "learning_rate": 1.2802308184859502e-05,
-      "loss": 0.0013,
-      "step": 1260
-    },
-    {
-      "epoch": 2.54,
-      "grad_norm": 0.054522693157196045,
-      "learning_rate": 1.1782870164782111e-05,
-      "loss": 0.0019,
-      "step": 1270
-    },
-    {
-      "epoch": 2.56,
-      "grad_norm": 0.041042644530534744,
-      "learning_rate": 1.0803179929624973e-05,
-      "loss": 0.0021,
-      "step": 1280
-    },
-    {
-      "epoch": 2.58,
-      "grad_norm": 0.00768931582570076,
-      "learning_rate": 9.863678896115559e-06,
-      "loss": 0.0022,
-      "step": 1290
-    },
-    {
-      "epoch": 2.6,
-      "grad_norm": 0.0033417909871786833,
-      "learning_rate": 8.964790373027132e-06,
-      "loss": 0.0017,
-      "step": 1300
-    },
-    {
-      "epoch": 2.62,
-      "grad_norm": 0.04406670480966568,
-      "learning_rate": 8.106919370449572e-06,
-      "loss": 0.0027,
-      "step": 1310
-    },
-    {
-      "epoch": 2.64,
-      "grad_norm": 0.043826743960380554,
-      "learning_rate": 7.290452417304916e-06,
-      "loss": 0.0024,
-      "step": 1320
-    },
-    {
-      "epoch": 2.66,
-      "grad_norm": 0.08563917130231857,
-      "learning_rate": 6.515757387189902e-06,
-      "loss": 0.0017,
-      "step": 1330
-    },
-    {
-      "epoch": 2.68,
-      "grad_norm": 0.003863748861476779,
-      "learning_rate": 5.783183332624098e-06,
-      "loss": 0.0028,
-      "step": 1340
-    },
-    {
-      "epoch": 2.7,
-      "grad_norm": 0.00339197413995862,
-      "learning_rate": 5.093060327778043e-06,
-      "loss": 0.0028,
-      "step": 1350
-    },
-    {
-      "epoch": 2.7199999999999998,
-      "grad_norm": 0.11382139474153519,
-      "learning_rate": 4.445699319752539e-06,
-      "loss": 0.0034,
-      "step": 1360
-    },
-    {
-      "epoch": 2.74,
-      "grad_norm": 0.0028220233507454395,
-      "learning_rate": 3.841391988476018e-06,
-      "loss": 0.0018,
-      "step": 1370
-    },
-    {
-      "epoch": 2.76,
-      "grad_norm": 0.058400608599185944,
-      "learning_rate": 3.2804106152828582e-06,
-      "loss": 0.0027,
-      "step": 1380
-    },
-    {
-      "epoch": 2.7800000000000002,
-      "grad_norm": 0.110735222697258,
-      "learning_rate": 2.7630079602323442e-06,
-      "loss": 0.0026,
-      "step": 1390
-    },
-    {
-      "epoch": 2.8,
-      "grad_norm": 0.0034612929448485374,
-      "learning_rate": 2.289417148223094e-06,
-      "loss": 0.0021,
-      "step": 1400
-    },
-    {
-      "epoch": 2.82,
-      "grad_norm": 0.04820137843489647,
-      "learning_rate": 1.8598515639545622e-06,
-      "loss": 0.0021,
-      "step": 1410
-    },
-    {
-      "epoch": 2.84,
-      "grad_norm": 0.08901210874319077,
-      "learning_rate": 1.4745047557827796e-06,
-      "loss": 0.0017,
-      "step": 1420
-    },
-    {
-      "epoch": 2.86,
-      "grad_norm": 0.052542563527822495,
-      "learning_rate": 1.133550348513701e-06,
-      "loss": 0.0017,
-      "step": 1430
-    },
-    {
-      "epoch": 2.88,
-      "grad_norm": 0.0500030443072319,
-      "learning_rate": 8.371419651735268e-07,
-      "loss": 0.0018,
-      "step": 1440
-    },
-    {
-      "epoch": 2.9,
-      "grad_norm": 0.05235590413212776,
-      "learning_rate": 5.854131577911259e-07,
-      "loss": 0.0025,
-      "step": 1450
-    },
-    {
-      "epoch": 2.92,
-      "grad_norm": 0.050380345433950424,
-      "learning_rate": 3.7847734722378234e-07,
-      "loss": 0.0021,
-      "step": 1460
-    },
-    {
-      "epoch": 2.94,
-      "grad_norm": 0.04665536433458328,
-      "learning_rate": 2.1642777205346242e-07,
-      "loss": 0.0021,
-      "step": 1470
-    },
-    {
-      "epoch": 2.96,
-      "grad_norm": 0.08257055282592773,
-      "learning_rate": 9.933744657651956e-08,
-      "loss": 0.0026,
-      "step": 1480
-    },
-    {
-      "epoch": 2.98,
-      "grad_norm": 0.04862203821539879,
-      "learning_rate": 2.7259127905776562e-08,
-      "loss": 0.0028,
-      "step": 1490
-    },
-    {
-      "epoch": 3.0,
-      "grad_norm": 0.05159607157111168,
-      "learning_rate": 2.252921999401636e-10,
-      "loss": 0.0029,
-      "step": 1500
     }
   ],
   "logging_steps": 10,
-  "max_steps": 1500,
+  "max_steps": 4689,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
@@ -1072,12 +372,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 2975560292163072.0,
+  "total_flos": 6424262344704000.0,
   "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:bad76c15491571a2b0d904f43b98d3ec2521c42abf54bc17c579eedfa7b8332a
+oid sha256:6df47478e677d9e0d8880cf9d4aa39fd45fc494558b25d955602aea050586dbf
 size 6353