Training in progress, step 25, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "up_proj",
-    "down_proj",
-    "k_proj",
     "o_proj",
+    "down_proj",
+    "gate_proj",
     "q_proj",
-    "gate_proj"
+    "v_proj",
+    "up_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:162b3c6e7bc433daa4d14fba27d0bb1188a053ff9fe4695614d1c332b516ed7b
+oid sha256:f99bc2c659cbdb0992e1a6091af6809085d19bc2edf14ae50e83db113fa5fcb4
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fa1d14dbc34af276200a438a5689d521bdd756c1ec0d76f07e56c1bdb72accd
+oid sha256:8a69589c53894362eff20f58966ceb7c4fe896fd6b42431e73043324550d40fb
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f54a4529a8e6845ded0eda45072a4e815479439591a260f73506331363d14828
+oid sha256:080926b6fad49ee6b44ff32b6c88dcf1a54560ba5269dd472628f349a0e91734
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1122e23e5053dc11adc18506adea02f4afa189a4981884a78b8091004698e3c9
+oid sha256:97e6f18cc73c49e1b8ffd8c02656630b4c1ab425d84004ddab33c7d1ac32ba3f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9672115f995075c45b19e844719708bc3519b7f8900dabf0e3b2c0ab349455b1
+oid sha256:a884ce65b2106c5faada4bc542ca8806b383884d40a67a36a96d4d9a59de34ad
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f80273d0fe6205387d305a36fe3d9d7805a1c74392ec5a9b45ad7c4825c5914c
+oid sha256:1601b0f6af9e056067f5465ae47446902063858add4122d3355cea2b50d7a490
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
+oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
 size 1064

last-checkpoint/trainer_state.json

@@ -1,16 +1,16 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.013341894382228596,
+  "epoch": 0.006670947191114298,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.00026683788764457196,
-      "grad_norm": 21.58336067199707,
+      "grad_norm": 22.89421844482422,
       "learning_rate": 5e-05,
       "loss": 99.4744,
       "step": 1
@@ -18,369 +18,186 @@
     {
       "epoch": 0.00026683788764457196,
       "eval_loss": 3.534377336502075,
-      "eval_runtime": 2.9302,
-      "eval_samples_per_second": 17.063,
-      "eval_steps_per_second": 4.437,
+      "eval_runtime": 2.9106,
+      "eval_samples_per_second": 17.179,
+      "eval_steps_per_second": 4.466,
       "step": 1
     },
     {
       "epoch": 0.0005336757752891439,
-      "grad_norm": 22.419708251953125,
+      "grad_norm": 23.7343692779541,
       "learning_rate": 0.0001,
       "loss": 103.3411,
       "step": 2
     },
     {
       "epoch": 0.0008005136629337158,
-      "grad_norm": 44.11233901977539,
+      "grad_norm": 48.079044342041016,
       "learning_rate": 9.990365154573717e-05,
-      "loss": 101.998,
+      "loss": 101.9827,
       "step": 3
     },
     {
       "epoch": 0.0010673515505782878,
-      "grad_norm": 39.20323181152344,
+      "grad_norm": 38.11738967895508,
       "learning_rate": 9.961501876182148e-05,
-      "loss": 102.6876,
+      "loss": 102.6331,
       "step": 4
     },
     {
       "epoch": 0.0013341894382228596,
-      "grad_norm": 33.18415069580078,
+      "grad_norm": 32.43550109863281,
       "learning_rate": 9.913533761814537e-05,
-      "loss": 98.8706,
+      "loss": 98.8496,
       "step": 5
     },
     {
       "epoch": 0.0016010273258674317,
-      "grad_norm": 35.75772476196289,
+      "grad_norm": 36.24091339111328,
       "learning_rate": 9.846666218300807e-05,
-      "loss": 96.6055,
+      "loss": 96.6713,
       "step": 6
     },
     {
       "epoch": 0.0018678652135120035,
-      "grad_norm": 36.51875686645508,
+      "grad_norm": 37.49607467651367,
       "learning_rate": 9.761185582727977e-05,
-      "loss": 94.8261,
+      "loss": 94.9006,
       "step": 7
     },
     {
       "epoch": 0.0021347031011565757,
-      "grad_norm": 33.68272018432617,
+      "grad_norm": 34.56901931762695,
       "learning_rate": 9.657457896300791e-05,
-      "loss": 93.3615,
+      "loss": 93.4301,
       "step": 8
     },
     {
       "epoch": 0.0024015409888011475,
-      "grad_norm": 30.13109016418457,
+      "grad_norm": 31.850221633911133,
       "learning_rate": 9.535927336897098e-05,
-      "loss": 91.072,
+      "loss": 91.105,
       "step": 9
     },
     {
       "epoch": 0.0026683788764457193,
-      "grad_norm": 32.036537170410156,
+      "grad_norm": 43.924991607666016,
       "learning_rate": 9.397114317029975e-05,
-      "loss": 93.589,
+      "loss": 93.5747,
       "step": 10
     },
     {
       "epoch": 0.002935216764090291,
-      "grad_norm": 24.110986709594727,
+      "grad_norm": 33.07682800292969,
       "learning_rate": 9.241613255361455e-05,
-      "loss": 93.6183,
+      "loss": 93.5264,
       "step": 11
     },
     {
       "epoch": 0.0032020546517348633,
-      "grad_norm": 59.20383071899414,
+      "grad_norm": 52.70429992675781,
       "learning_rate": 9.070090031310558e-05,
-      "loss": 100.723,
+      "loss": 100.4311,
       "step": 12
     },
     {
       "epoch": 0.003468892539379435,
-      "grad_norm": 72.5294418334961,
+      "grad_norm": 91.30162048339844,
       "learning_rate": 8.883279133655399e-05,
-      "loss": 103.4235,
+      "loss": 103.5051,
       "step": 13
     },
     {
       "epoch": 0.003735730427024007,
-      "grad_norm": 49.615962982177734,
+      "grad_norm": 48.74945068359375,
       "learning_rate": 8.681980515339464e-05,
-      "loss": 90.5619,
+      "loss": 90.932,
       "step": 14
     },
     {
       "epoch": 0.004002568314668579,
-      "grad_norm": 36.85390853881836,
+      "grad_norm": 38.04246139526367,
       "learning_rate": 8.467056167950311e-05,
-      "loss": 90.9424,
+      "loss": 91.092,
       "step": 15
     },
     {
       "epoch": 0.004269406202313151,
-      "grad_norm": 28.41231346130371,
+      "grad_norm": 32.99767303466797,
       "learning_rate": 8.239426430539243e-05,
-      "loss": 86.9021,
+      "loss": 86.978,
       "step": 16
     },
     {
       "epoch": 0.004536244089957723,
-      "grad_norm": 19.181047439575195,
+      "grad_norm": 25.959495544433594,
       "learning_rate": 8.000066048588211e-05,
-      "loss": 87.2284,
+      "loss": 87.323,
       "step": 17
     },
     {
       "epoch": 0.004803081977602295,
-      "grad_norm": 16.206340789794922,
+      "grad_norm": 22.552183151245117,
       "learning_rate": 7.75e-05,
-      "loss": 87.68,
+      "loss": 87.7695,
       "step": 18
     },
     {
       "epoch": 0.005069919865246866,
-      "grad_norm": 13.560489654541016,
+      "grad_norm": 17.352420806884766,
       "learning_rate": 7.490299105985507e-05,
-      "loss": 87.0709,
+      "loss": 87.1552,
       "step": 19
     },
     {
       "epoch": 0.0053367577528914386,
-      "grad_norm": 13.36911678314209,
+      "grad_norm": 14.216341018676758,
       "learning_rate": 7.222075445642904e-05,
-      "loss": 87.0837,
+      "loss": 87.1521,
       "step": 20
     },
     {
       "epoch": 0.005603595640536011,
-      "grad_norm": 13.232701301574707,
+      "grad_norm": 13.55358600616455,
       "learning_rate": 6.946477593864228e-05,
-      "loss": 87.4922,
+      "loss": 87.6133,
       "step": 21
     },
     {
       "epoch": 0.005870433528180582,
-      "grad_norm": 19.99480438232422,
+      "grad_norm": 18.19391441345215,
       "learning_rate": 6.664685702961344e-05,
-      "loss": 86.7508,
+      "loss": 86.9043,
       "step": 22
     },
     {
       "epoch": 0.006137271415825154,
-      "grad_norm": 19.568359375,
+      "grad_norm": 20.173397064208984,
       "learning_rate": 6.377906449072578e-05,
-      "loss": 88.3357,
+      "loss": 88.4352,
       "step": 23
     },
     {
       "epoch": 0.006404109303469727,
-      "grad_norm": 30.02350425720215,
+      "grad_norm": 27.15044403076172,
       "learning_rate": 6.087367864990233e-05,
-      "loss": 89.6037,
+      "loss": 89.5455,
       "step": 24
     },
     {
       "epoch": 0.006670947191114298,
-      "grad_norm": 132.76075744628906,
+      "grad_norm": 77.1603012084961,
       "learning_rate": 5.794314081535644e-05,
-      "loss": 106.9513,
+      "loss": 105.756,
       "step": 25
     },
     {
       "epoch": 0.006670947191114298,
-      "eval_loss": 2.699881076812744,
-      "eval_runtime": 2.969,
-      "eval_samples_per_second": 16.841,
-      "eval_steps_per_second": 4.379,
+      "eval_loss": 2.6978037357330322,
+      "eval_runtime": 2.9516,
+      "eval_samples_per_second": 16.94,
+      "eval_steps_per_second": 4.404,
       "step": 25
-    },
-    {
-      "epoch": 0.00693778507875887,
-      "grad_norm": 11.069785118103027,
-      "learning_rate": 5.500000000000001e-05,
-      "loss": 85.2464,
-      "step": 26
-    },
-    {
-      "epoch": 0.0072046229664034424,
-      "grad_norm": 11.894067764282227,
-      "learning_rate": 5.205685918464356e-05,
-      "loss": 86.4133,
-      "step": 27
-    },
-    {
-      "epoch": 0.007471460854048014,
-      "grad_norm": 11.504545211791992,
-      "learning_rate": 4.912632135009769e-05,
-      "loss": 85.9424,
-      "step": 28
-    },
-    {
-      "epoch": 0.007738298741692586,
-      "grad_norm": 9.52103042602539,
-      "learning_rate": 4.6220935509274235e-05,
-      "loss": 85.5899,
-      "step": 29
-    },
-    {
-      "epoch": 0.008005136629337158,
-      "grad_norm": 8.053053855895996,
-      "learning_rate": 4.3353142970386564e-05,
-      "loss": 86.4908,
-      "step": 30
-    },
-    {
-      "epoch": 0.00827197451698173,
-      "grad_norm": 6.596405982971191,
-      "learning_rate": 4.053522406135775e-05,
-      "loss": 84.509,
-      "step": 31
-    },
-    {
-      "epoch": 0.008538812404626303,
-      "grad_norm": 12.154988288879395,
-      "learning_rate": 3.777924554357096e-05,
-      "loss": 85.5146,
-      "step": 32
-    },
-    {
-      "epoch": 0.008805650292270874,
-      "grad_norm": 12.631579399108887,
-      "learning_rate": 3.509700894014496e-05,
-      "loss": 84.0384,
-      "step": 33
-    },
-    {
-      "epoch": 0.009072488179915445,
-      "grad_norm": 14.187871932983398,
-      "learning_rate": 3.250000000000001e-05,
-      "loss": 85.3073,
-      "step": 34
-    },
-    {
-      "epoch": 0.009339326067560017,
-      "grad_norm": 17.819459915161133,
-      "learning_rate": 2.9999339514117912e-05,
-      "loss": 83.8787,
-      "step": 35
-    },
-    {
-      "epoch": 0.00960616395520459,
-      "grad_norm": 20.426162719726562,
-      "learning_rate": 2.760573569460757e-05,
-      "loss": 87.1894,
-      "step": 36
-    },
-    {
-      "epoch": 0.009873001842849161,
-      "grad_norm": 31.33350944519043,
-      "learning_rate": 2.53294383204969e-05,
-      "loss": 89.3437,
-      "step": 37
-    },
-    {
-      "epoch": 0.010139839730493733,
-      "grad_norm": 47.56151580810547,
-      "learning_rate": 2.3180194846605367e-05,
-      "loss": 100.6103,
-      "step": 38
-    },
-    {
-      "epoch": 0.010406677618138306,
-      "grad_norm": 6.464964866638184,
-      "learning_rate": 2.1167208663446025e-05,
-      "loss": 83.3005,
-      "step": 39
-    },
-    {
-      "epoch": 0.010673515505782877,
-      "grad_norm": 6.612872123718262,
-      "learning_rate": 1.9299099686894423e-05,
-      "loss": 84.2439,
-      "step": 40
-    },
-    {
-      "epoch": 0.010940353393427448,
-      "grad_norm": 6.869765758514404,
-      "learning_rate": 1.758386744638546e-05,
-      "loss": 84.894,
-      "step": 41
-    },
-    {
-      "epoch": 0.011207191281072022,
-      "grad_norm": 5.677627086639404,
-      "learning_rate": 1.602885682970026e-05,
-      "loss": 84.2743,
-      "step": 42
-    },
-    {
-      "epoch": 0.011474029168716593,
-      "grad_norm": 6.212136745452881,
-      "learning_rate": 1.464072663102903e-05,
-      "loss": 85.6072,
-      "step": 43
-    },
-    {
-      "epoch": 0.011740867056361164,
-      "grad_norm": 6.752817153930664,
-      "learning_rate": 1.3425421036992098e-05,
-      "loss": 84.6236,
-      "step": 44
-    },
-    {
-      "epoch": 0.012007704944005737,
-      "grad_norm": 7.166438102722168,
-      "learning_rate": 1.2388144172720251e-05,
-      "loss": 83.1906,
-      "step": 45
-    },
-    {
-      "epoch": 0.012274542831650309,
-      "grad_norm": 7.727652549743652,
-      "learning_rate": 1.1533337816991932e-05,
-      "loss": 83.4727,
-      "step": 46
-    },
-    {
-      "epoch": 0.01254138071929488,
-      "grad_norm": 8.032402038574219,
-      "learning_rate": 1.0864662381854632e-05,
-      "loss": 84.3546,
-      "step": 47
-    },
-    {
-      "epoch": 0.012808218606939453,
-      "grad_norm": 10.028108596801758,
-      "learning_rate": 1.0384981238178534e-05,
-      "loss": 84.996,
-      "step": 48
-    },
-    {
-      "epoch": 0.013075056494584025,
-      "grad_norm": 15.79798698425293,
-      "learning_rate": 1.0096348454262845e-05,
-      "loss": 87.5037,
-      "step": 49
-    },
-    {
-      "epoch": 0.013341894382228596,
-      "grad_norm": 68.88801574707031,
-      "learning_rate": 1e-05,
-      "loss": 99.1348,
-      "step": 50
-    },
-    {
-      "epoch": 0.013341894382228596,
-      "eval_loss": 2.6576178073883057,
-      "eval_runtime": 2.9174,
-      "eval_samples_per_second": 17.139,
-      "eval_steps_per_second": 4.456,
-      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -395,12 +212,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.259156315439104e+17,
+  "total_flos": 2.629578157719552e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bbcff46d73dbb696188a8406cebbd246e69bc502841896b8b531535d0bbbd1a
+oid sha256:daa6781a2b3f71155ea06bbf181fb9d6e5488ae8ac1598f881bc93f1a056095c
 size 6840