Upload checkpoints

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "../pretrained/gemma-2b-it/",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": "gaussian",
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd2e4cac19ae4b0fed42f6c1a79458340bbf418d5ca0c2ada790f7109a4b99c5
+size 1852672

checkpoints/checkpoint-1000/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "../pretrained/gemma-2b-it/",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": "gaussian",
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoints/checkpoint-1000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b66fb9f2f5cac938c92dae467b1f565f6ab1725a86821c43b7e491b301e3ad0
+size 1852672

checkpoints/checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5279c692512f595c9f6046bb680937613509d66af5279a17b0c86a638c479c35
+size 3747194

checkpoints/checkpoint-1000/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74c0bbe13ba6abf11c8e74c819dd4812dcf1cd31a15084b5d9a67d92cffcd15a
+size 15024

checkpoints/checkpoint-1000/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4af53bdc297eb334ac93c2f0f17d63f14b6fde6ea4eab4e3168813ead2e95f2a
+size 15024

checkpoints/checkpoint-1000/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8113f7db0a254d0cdc384448069e86023fafbe13c1d2d6b23e47a02b4ae9dc99
+size 15024

checkpoints/checkpoint-1000/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:369be34e82f746d1ac1423468b34f53a5dfb7cd0bc6c2f70b663f6762401f7c5
+size 15024

checkpoints/checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a909cc86dc2bb25cb47b301da3b3473b0c55ea709e4a406e429c3b785d1ac94
+size 1064

checkpoints/checkpoint-1000/trainer_state.json

@@ -0,0 +1,721 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.07256367462448299,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0007256367462448298,
+      "grad_norm": 45.75,
+      "learning_rate": 5e-06,
+      "loss": 1.9641,
+      "step": 10
+    },
+    {
+      "epoch": 0.0014512734924896596,
+      "grad_norm": 46.5,
+      "learning_rate": 1e-05,
+      "loss": 1.7641,
+      "step": 20
+    },
+    {
+      "epoch": 0.0021769102387344894,
+      "grad_norm": 35.75,
+      "learning_rate": 1.5e-05,
+      "loss": 1.4723,
+      "step": 30
+    },
+    {
+      "epoch": 0.0029025469849793192,
+      "grad_norm": 31.0,
+      "learning_rate": 2e-05,
+      "loss": 1.0985,
+      "step": 40
+    },
+    {
+      "epoch": 0.003628183731224149,
+      "grad_norm": 28.875,
+      "learning_rate": 2.5e-05,
+      "loss": 1.0381,
+      "step": 50
+    },
+    {
+      "epoch": 0.004353820477468979,
+      "grad_norm": 26.625,
+      "learning_rate": 3e-05,
+      "loss": 0.6977,
+      "step": 60
+    },
+    {
+      "epoch": 0.005079457223713809,
+      "grad_norm": 23.75,
+      "learning_rate": 3.5e-05,
+      "loss": 0.6392,
+      "step": 70
+    },
+    {
+      "epoch": 0.0058050939699586385,
+      "grad_norm": 26.5,
+      "learning_rate": 4e-05,
+      "loss": 0.7459,
+      "step": 80
+    },
+    {
+      "epoch": 0.006530730716203468,
+      "grad_norm": 29.875,
+      "learning_rate": 4.5e-05,
+      "loss": 0.6155,
+      "step": 90
+    },
+    {
+      "epoch": 0.007256367462448298,
+      "grad_norm": 21.5,
+      "learning_rate": 5e-05,
+      "loss": 0.3941,
+      "step": 100
+    },
+    {
+      "epoch": 0.007982004208693128,
+      "grad_norm": 17.0,
+      "learning_rate": 4.9999934086574596e-05,
+      "loss": 0.4513,
+      "step": 110
+    },
+    {
+      "epoch": 0.008707640954937958,
+      "grad_norm": 23.875,
+      "learning_rate": 4.9999736346645943e-05,
+      "loss": 0.5292,
+      "step": 120
+    },
+    {
+      "epoch": 0.009433277701182788,
+      "grad_norm": 17.25,
+      "learning_rate": 4.999940678125673e-05,
+      "loss": 0.3869,
+      "step": 130
+    },
+    {
+      "epoch": 0.010158914447427617,
+      "grad_norm": 24.75,
+      "learning_rate": 4.9998945392144796e-05,
+      "loss": 0.4121,
+      "step": 140
+    },
+    {
+      "epoch": 0.010884551193672447,
+      "grad_norm": 16.625,
+      "learning_rate": 4.999835218174307e-05,
+      "loss": 0.4199,
+      "step": 150
+    },
+    {
+      "epoch": 0.011610187939917277,
+      "grad_norm": 11.8125,
+      "learning_rate": 4.99976271531796e-05,
+      "loss": 0.4694,
+      "step": 160
+    },
+    {
+      "epoch": 0.012335824686162107,
+      "grad_norm": 15.9375,
+      "learning_rate": 4.9996770310277506e-05,
+      "loss": 0.3736,
+      "step": 170
+    },
+    {
+      "epoch": 0.013061461432406937,
+      "grad_norm": 18.0,
+      "learning_rate": 4.9995781657555e-05,
+      "loss": 0.4224,
+      "step": 180
+    },
+    {
+      "epoch": 0.013787098178651766,
+      "grad_norm": 23.0,
+      "learning_rate": 4.99946612002253e-05,
+      "loss": 0.4307,
+      "step": 190
+    },
+    {
+      "epoch": 0.014512734924896596,
+      "grad_norm": 19.375,
+      "learning_rate": 4.9993408944196676e-05,
+      "loss": 0.3449,
+      "step": 200
+    },
+    {
+      "epoch": 0.015238371671141426,
+      "grad_norm": 11.0,
+      "learning_rate": 4.9992024896072364e-05,
+      "loss": 0.3243,
+      "step": 210
+    },
+    {
+      "epoch": 0.015964008417386256,
+      "grad_norm": 17.875,
+      "learning_rate": 4.999050906315055e-05,
+      "loss": 0.3002,
+      "step": 220
+    },
+    {
+      "epoch": 0.016689645163631087,
+      "grad_norm": 6.875,
+      "learning_rate": 4.998886145342434e-05,
+      "loss": 0.3882,
+      "step": 230
+    },
+    {
+      "epoch": 0.017415281909875915,
+      "grad_norm": 12.125,
+      "learning_rate": 4.9987082075581684e-05,
+      "loss": 0.4211,
+      "step": 240
+    },
+    {
+      "epoch": 0.018140918656120747,
+      "grad_norm": 16.875,
+      "learning_rate": 4.9985170939005386e-05,
+      "loss": 0.2967,
+      "step": 250
+    },
+    {
+      "epoch": 0.018866555402365575,
+      "grad_norm": 26.125,
+      "learning_rate": 4.998312805377302e-05,
+      "loss": 0.3283,
+      "step": 260
+    },
+    {
+      "epoch": 0.019592192148610407,
+      "grad_norm": 18.0,
+      "learning_rate": 4.998095343065685e-05,
+      "loss": 0.3455,
+      "step": 270
+    },
+    {
+      "epoch": 0.020317828894855235,
+      "grad_norm": 15.4375,
+      "learning_rate": 4.997864708112384e-05,
+      "loss": 0.2891,
+      "step": 280
+    },
+    {
+      "epoch": 0.021043465641100066,
+      "grad_norm": 30.25,
+      "learning_rate": 4.997620901733554e-05,
+      "loss": 0.3645,
+      "step": 290
+    },
+    {
+      "epoch": 0.021769102387344894,
+      "grad_norm": 9.875,
+      "learning_rate": 4.997363925214803e-05,
+      "loss": 0.3047,
+      "step": 300
+    },
+    {
+      "epoch": 0.022494739133589726,
+      "grad_norm": 18.625,
+      "learning_rate": 4.9970937799111896e-05,
+      "loss": 0.2943,
+      "step": 310
+    },
+    {
+      "epoch": 0.023220375879834554,
+      "grad_norm": 30.625,
+      "learning_rate": 4.996810467247207e-05,
+      "loss": 0.3315,
+      "step": 320
+    },
+    {
+      "epoch": 0.023946012626079385,
+      "grad_norm": 14.3125,
+      "learning_rate": 4.9965139887167856e-05,
+      "loss": 0.2473,
+      "step": 330
+    },
+    {
+      "epoch": 0.024671649372324213,
+      "grad_norm": 21.5,
+      "learning_rate": 4.996204345883278e-05,
+      "loss": 0.3173,
+      "step": 340
+    },
+    {
+      "epoch": 0.025397286118569045,
+      "grad_norm": 16.125,
+      "learning_rate": 4.9958815403794546e-05,
+      "loss": 0.3813,
+      "step": 350
+    },
+    {
+      "epoch": 0.026122922864813873,
+      "grad_norm": 15.0625,
+      "learning_rate": 4.995545573907492e-05,
+      "loss": 0.3366,
+      "step": 360
+    },
+    {
+      "epoch": 0.026848559611058705,
+      "grad_norm": 19.5,
+      "learning_rate": 4.995196448238966e-05,
+      "loss": 0.3188,
+      "step": 370
+    },
+    {
+      "epoch": 0.027574196357303533,
+      "grad_norm": 20.125,
+      "learning_rate": 4.9948341652148436e-05,
+      "loss": 0.2776,
+      "step": 380
+    },
+    {
+      "epoch": 0.028299833103548364,
+      "grad_norm": 17.25,
+      "learning_rate": 4.994458726745468e-05,
+      "loss": 0.3574,
+      "step": 390
+    },
+    {
+      "epoch": 0.029025469849793192,
+      "grad_norm": 5.375,
+      "learning_rate": 4.9940701348105554e-05,
+      "loss": 0.2566,
+      "step": 400
+    },
+    {
+      "epoch": 0.029751106596038024,
+      "grad_norm": 31.0,
+      "learning_rate": 4.99366839145918e-05,
+      "loss": 0.275,
+      "step": 410
+    },
+    {
+      "epoch": 0.030476743342282852,
+      "grad_norm": 21.75,
+      "learning_rate": 4.993253498809762e-05,
+      "loss": 0.2928,
+      "step": 420
+    },
+    {
+      "epoch": 0.031202380088527683,
+      "grad_norm": 21.25,
+      "learning_rate": 4.9928254590500646e-05,
+      "loss": 0.3466,
+      "step": 430
+    },
+    {
+      "epoch": 0.03192801683477251,
+      "grad_norm": 15.25,
+      "learning_rate": 4.9923842744371707e-05,
+      "loss": 0.2911,
+      "step": 440
+    },
+    {
+      "epoch": 0.03265365358101734,
+      "grad_norm": 8.9375,
+      "learning_rate": 4.99192994729748e-05,
+      "loss": 0.2153,
+      "step": 450
+    },
+    {
+      "epoch": 0.033379290327262175,
+      "grad_norm": 20.5,
+      "learning_rate": 4.991462480026693e-05,
+      "loss": 0.383,
+      "step": 460
+    },
+    {
+      "epoch": 0.034104927073507,
+      "grad_norm": 6.46875,
+      "learning_rate": 4.9909818750898e-05,
+      "loss": 0.3099,
+      "step": 470
+    },
+    {
+      "epoch": 0.03483056381975183,
+      "grad_norm": 34.0,
+      "learning_rate": 4.990488135021065e-05,
+      "loss": 0.2897,
+      "step": 480
+    },
+    {
+      "epoch": 0.03555620056599666,
+      "grad_norm": 7.78125,
+      "learning_rate": 4.989981262424017e-05,
+      "loss": 0.3098,
+      "step": 490
+    },
+    {
+      "epoch": 0.036281837312241494,
+      "grad_norm": 41.0,
+      "learning_rate": 4.989461259971432e-05,
+      "loss": 0.2428,
+      "step": 500
+    },
+    {
+      "epoch": 0.03700747405848632,
+      "grad_norm": 17.375,
+      "learning_rate": 4.988928130405323e-05,
+      "loss": 0.2485,
+      "step": 510
+    },
+    {
+      "epoch": 0.03773311080473115,
+      "grad_norm": 15.625,
+      "learning_rate": 4.9883818765369194e-05,
+      "loss": 0.2694,
+      "step": 520
+    },
+    {
+      "epoch": 0.03845874755097598,
+      "grad_norm": 17.75,
+      "learning_rate": 4.98782250124666e-05,
+      "loss": 0.2752,
+      "step": 530
+    },
+    {
+      "epoch": 0.03918438429722081,
+      "grad_norm": 9.8125,
+      "learning_rate": 4.987250007484172e-05,
+      "loss": 0.2687,
+      "step": 540
+    },
+    {
+      "epoch": 0.03991002104346564,
+      "grad_norm": 3.6875,
+      "learning_rate": 4.986664398268256e-05,
+      "loss": 0.268,
+      "step": 550
+    },
+    {
+      "epoch": 0.04063565778971047,
+      "grad_norm": 24.125,
+      "learning_rate": 4.986065676686874e-05,
+      "loss": 0.2602,
+      "step": 560
+    },
+    {
+      "epoch": 0.0413612945359553,
+      "grad_norm": 23.125,
+      "learning_rate": 4.98545384589713e-05,
+      "loss": 0.2731,
+      "step": 570
+    },
+    {
+      "epoch": 0.04208693128220013,
+      "grad_norm": 13.5625,
+      "learning_rate": 4.984828909125251e-05,
+      "loss": 0.2537,
+      "step": 580
+    },
+    {
+      "epoch": 0.042812568028444964,
+      "grad_norm": 6.15625,
+      "learning_rate": 4.9841908696665764e-05,
+      "loss": 0.1723,
+      "step": 590
+    },
+    {
+      "epoch": 0.04353820477468979,
+      "grad_norm": 5.03125,
+      "learning_rate": 4.9835397308855344e-05,
+      "loss": 0.2414,
+      "step": 600
+    },
+    {
+      "epoch": 0.04426384152093462,
+      "grad_norm": 24.0,
+      "learning_rate": 4.9828754962156286e-05,
+      "loss": 0.2811,
+      "step": 610
+    },
+    {
+      "epoch": 0.04498947826717945,
+      "grad_norm": 25.875,
+      "learning_rate": 4.9821981691594175e-05,
+      "loss": 0.2949,
+      "step": 620
+    },
+    {
+      "epoch": 0.04571511501342428,
+      "grad_norm": 12.875,
+      "learning_rate": 4.981507753288497e-05,
+      "loss": 0.2662,
+      "step": 630
+    },
+    {
+      "epoch": 0.04644075175966911,
+      "grad_norm": 19.375,
+      "learning_rate": 4.9808042522434814e-05,
+      "loss": 0.2659,
+      "step": 640
+    },
+    {
+      "epoch": 0.04716638850591394,
+      "grad_norm": 22.25,
+      "learning_rate": 4.9800876697339824e-05,
+      "loss": 0.3333,
+      "step": 650
+    },
+    {
+      "epoch": 0.04789202525215877,
+      "grad_norm": 18.875,
+      "learning_rate": 4.979358009538594e-05,
+      "loss": 0.3197,
+      "step": 660
+    },
+    {
+      "epoch": 0.0486176619984036,
+      "grad_norm": 24.0,
+      "learning_rate": 4.978615275504869e-05,
+      "loss": 0.2385,
+      "step": 670
+    },
+    {
+      "epoch": 0.04934329874464843,
+      "grad_norm": 19.5,
+      "learning_rate": 4.977859471549297e-05,
+      "loss": 0.2673,
+      "step": 680
+    },
+    {
+      "epoch": 0.05006893549089326,
+      "grad_norm": 11.1875,
+      "learning_rate": 4.977090601657289e-05,
+      "loss": 0.2107,
+      "step": 690
+    },
+    {
+      "epoch": 0.05079457223713809,
+      "grad_norm": 9.8125,
+      "learning_rate": 4.976308669883153e-05,
+      "loss": 0.2825,
+      "step": 700
+    },
+    {
+      "epoch": 0.05152020898338292,
+      "grad_norm": 12.6875,
+      "learning_rate": 4.975513680350073e-05,
+      "loss": 0.2604,
+      "step": 710
+    },
+    {
+      "epoch": 0.052245845729627746,
+      "grad_norm": 19.375,
+      "learning_rate": 4.974705637250089e-05,
+      "loss": 0.209,
+      "step": 720
+    },
+    {
+      "epoch": 0.05297148247587258,
+      "grad_norm": 20.625,
+      "learning_rate": 4.97388454484407e-05,
+      "loss": 0.255,
+      "step": 730
+    },
+    {
+      "epoch": 0.05369711922211741,
+      "grad_norm": 17.25,
+      "learning_rate": 4.973050407461698e-05,
+      "loss": 0.2526,
+      "step": 740
+    },
+    {
+      "epoch": 0.05442275596836224,
+      "grad_norm": 3.453125,
+      "learning_rate": 4.972203229501441e-05,
+      "loss": 0.2028,
+      "step": 750
+    },
+    {
+      "epoch": 0.055148392714607065,
+      "grad_norm": 18.625,
+      "learning_rate": 4.971343015430532e-05,
+      "loss": 0.2395,
+      "step": 760
+    },
+    {
+      "epoch": 0.0558740294608519,
+      "grad_norm": 27.5,
+      "learning_rate": 4.970469769784941e-05,
+      "loss": 0.218,
+      "step": 770
+    },
+    {
+      "epoch": 0.05659966620709673,
+      "grad_norm": 24.375,
+      "learning_rate": 4.96958349716936e-05,
+      "loss": 0.2264,
+      "step": 780
+    },
+    {
+      "epoch": 0.05732530295334156,
+      "grad_norm": 27.125,
+      "learning_rate": 4.968684202257169e-05,
+      "loss": 0.3467,
+      "step": 790
+    },
+    {
+      "epoch": 0.058050939699586385,
+      "grad_norm": 18.0,
+      "learning_rate": 4.967771889790416e-05,
+      "loss": 0.2894,
+      "step": 800
+    },
+    {
+      "epoch": 0.058776576445831216,
+      "grad_norm": 8.375,
+      "learning_rate": 4.966846564579792e-05,
+      "loss": 0.1818,
+      "step": 810
+    },
+    {
+      "epoch": 0.05950221319207605,
+      "grad_norm": 13.75,
+      "learning_rate": 4.965908231504607e-05,
+      "loss": 0.3376,
+      "step": 820
+    },
+    {
+      "epoch": 0.06022784993832088,
+      "grad_norm": 53.5,
+      "learning_rate": 4.964956895512759e-05,
+      "loss": 0.2843,
+      "step": 830
+    },
+    {
+      "epoch": 0.060953486684565704,
+      "grad_norm": 12.3125,
+      "learning_rate": 4.963992561620714e-05,
+      "loss": 0.2396,
+      "step": 840
+    },
+    {
+      "epoch": 0.061679123430810535,
+      "grad_norm": 16.0,
+      "learning_rate": 4.963015234913475e-05,
+      "loss": 0.255,
+      "step": 850
+    },
+    {
+      "epoch": 0.06240476017705537,
+      "grad_norm": 6.8125,
+      "learning_rate": 4.96202492054456e-05,
+      "loss": 0.2316,
+      "step": 860
+    },
+    {
+      "epoch": 0.06313039692330019,
+      "grad_norm": 22.875,
+      "learning_rate": 4.9610216237359684e-05,
+      "loss": 0.3816,
+      "step": 870
+    },
+    {
+      "epoch": 0.06385603366954502,
+      "grad_norm": 23.875,
+      "learning_rate": 4.960005349778159e-05,
+      "loss": 0.2203,
+      "step": 880
+    },
+    {
+      "epoch": 0.06458167041578985,
+      "grad_norm": 38.0,
+      "learning_rate": 4.95897610403002e-05,
+      "loss": 0.3093,
+      "step": 890
+    },
+    {
+      "epoch": 0.06530730716203469,
+      "grad_norm": 19.75,
+      "learning_rate": 4.95793389191884e-05,
+      "loss": 0.2255,
+      "step": 900
+    },
+    {
+      "epoch": 0.06603294390827952,
+      "grad_norm": 16.5,
+      "learning_rate": 4.95687871894028e-05,
+      "loss": 0.1937,
+      "step": 910
+    },
+    {
+      "epoch": 0.06675858065452435,
+      "grad_norm": 10.0,
+      "learning_rate": 4.9558105906583466e-05,
+      "loss": 0.2242,
+      "step": 920
+    },
+    {
+      "epoch": 0.06748421740076918,
+      "grad_norm": 21.0,
+      "learning_rate": 4.9547295127053586e-05,
+      "loss": 0.3581,
+      "step": 930
+    },
+    {
+      "epoch": 0.068209854147014,
+      "grad_norm": 17.125,
+      "learning_rate": 4.95363549078192e-05,
+      "loss": 0.2132,
+      "step": 940
+    },
+    {
+      "epoch": 0.06893549089325883,
+      "grad_norm": 17.25,
+      "learning_rate": 4.952528530656889e-05,
+      "loss": 0.2659,
+      "step": 950
+    },
+    {
+      "epoch": 0.06966112763950366,
+      "grad_norm": 19.5,
+      "learning_rate": 4.9514086381673496e-05,
+      "loss": 0.2169,
+      "step": 960
+    },
+    {
+      "epoch": 0.0703867643857485,
+      "grad_norm": 20.625,
+      "learning_rate": 4.9502758192185774e-05,
+      "loss": 0.3276,
+      "step": 970
+    },
+    {
+      "epoch": 0.07111240113199332,
+      "grad_norm": 23.125,
+      "learning_rate": 4.949130079784009e-05,
+      "loss": 0.2512,
+      "step": 980
+    },
+    {
+      "epoch": 0.07183803787823816,
+      "grad_norm": 18.125,
+      "learning_rate": 4.9479714259052143e-05,
+      "loss": 0.2827,
+      "step": 990
+    },
+    {
+      "epoch": 0.07256367462448299,
+      "grad_norm": 18.375,
+      "learning_rate": 4.946799863691862e-05,
+      "loss": 0.206,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 13781,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 0.0,
+  "train_batch_size": 5,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f13496797d6aaea4e21d2f2de24d7b2ec5d76cf72e27733fa08925121d91fd2
+size 4984

checkpoints/checkpoint-10000/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "../pretrained/gemma-2b-it/",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": "gaussian",
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoints/checkpoint-10000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f10ed520c32593411920a7e2c30f78a4266ffe079120828c412b95e76984802d
+size 1852672

checkpoints/checkpoint-10000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a6a1be165dc306ce5b3b668baef9b778ac20b5b5f2ae19306d94ffd230de365
+size 3747194

checkpoints/checkpoint-10000/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5196538849fc4b57e5c69e398a60829c8465469182ac1e69f09a5fb48b3798cf
+size 15024

checkpoints/checkpoint-10000/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd15a6bd7454f8c189b06fa762c372ae9cc5682fa0f46ddde7f79d145d4cb46d
+size 15024

checkpoints/checkpoint-10000/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:992e0a1de86b467a4abf3e98ebb4621f501cf572338e4337a4514da2c672595b
+size 15024

checkpoints/checkpoint-10000/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac66fd3489c14b9144d6c1720be3daec85894c96612ea8215bd7123b1d06ed66
+size 15024

checkpoints/checkpoint-10000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8cf818c444104efe80cf26c7920df0dab123d9b6903f4cd037c26d5d6bf3857
+size 1064

checkpoints/checkpoint-10000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f13496797d6aaea4e21d2f2de24d7b2ec5d76cf72e27733fa08925121d91fd2
+size 4984

checkpoints/checkpoint-10500/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "../pretrained/gemma-2b-it/",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": "gaussian",
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoints/checkpoint-10500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e985b1e393afa5b1c2175e4e37a29e9846a984ad711253061e2025fbf8b31d5
+size 1852672

checkpoints/checkpoint-10500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b38a54164462fba1d315c96f72a0717fb7126161809584d1726a65d0e4ccd979
+size 3747194

checkpoints/checkpoint-10500/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e062d4fc9e6248613cda746999ad8615f0777a42d3fb9ec4413fbd43ee2fa728
+size 15024

checkpoints/checkpoint-10500/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3d59d98a6fd2b151a5ce9152c3555640d1c8d54796e38202614a2372540f935
+size 15024

checkpoints/checkpoint-10500/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bca8f285433437fcf6b37a2afa5ddaf9e6334e8994540d10eae0a9ab782ffb7b
+size 15024

checkpoints/checkpoint-10500/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bc1d009dc00ad478ec7c3913cdee4328e8a526de9b434808dab406ac9b20fbc
+size 15024

checkpoints/checkpoint-10500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e416eeaa9dc4cbd14c09317ab177d36bed29ba9a0fc58f3c28a66906f926d68
+size 1064

checkpoints/checkpoint-10500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f13496797d6aaea4e21d2f2de24d7b2ec5d76cf72e27733fa08925121d91fd2
+size 4984

checkpoints/checkpoint-11000/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "../pretrained/gemma-2b-it/",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": "gaussian",
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoints/checkpoint-11000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c06998a1d5b5748f9202804e075eabfe8996899ea6acfef716653f51a88b36db
+size 1852672

checkpoints/checkpoint-11000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b182e899c8503d41c04283e8cb80c973bb58c9e6304871999e1ee98f28a28f87
+size 3747194

checkpoints/checkpoint-11000/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c325fa42d594c133ccf16f44fd732e88ede3398932e3e3d251debbb1aaed241
+size 15024

checkpoints/checkpoint-11000/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78b51388887e6e782b23d52cccd5e676ecfcd459c4cab9228d7428f985b7739e
+size 15024

checkpoints/checkpoint-11000/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a385fa14c6eb02a9061046f49cb2317b01193ad4ff4674245dbb09cda3b13a0b
+size 15024

checkpoints/checkpoint-11000/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d1dd53b00f31c3724f4c797c24f7d8dfb9828dc176c5848790b4488bc98c96c
+size 15024

checkpoints/checkpoint-11000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0d012a99c88d57e6f359e9b70583cd819536789f1d7ee2b6ff584c2ea8aff39
+size 1064

checkpoints/checkpoint-11000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f13496797d6aaea4e21d2f2de24d7b2ec5d76cf72e27733fa08925121d91fd2
+size 4984

checkpoints/checkpoint-11500/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "../pretrained/gemma-2b-it/",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": "gaussian",
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoints/checkpoint-11500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a206e0615e3136c9e0fd40bdd6991eb2ef046c5f177610b31dd37a9b1fcc582f
+size 1852672

checkpoints/checkpoint-11500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5214c3c95f8379de9a0a18731b32f0fc3dfb3d7f24d9704bf7f9dc89012e2c5b
+size 3747194

checkpoints/checkpoint-11500/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddcabcf8d784bd6eed0c017180c42a20b0a396f118b725c9ca61f3e770810388
+size 15024

checkpoints/checkpoint-11500/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d5db07447175b96d4db2f4e2c7c080cfc5b52cb33ad6419dab4ac39bc54168a
+size 15024

checkpoints/checkpoint-11500/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8b5cd74bd55ce6e337af66eefec1aac409dfeb673beeb2b066d0eb792d5d1f4
+size 15024