Training in progress, step 50, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "o_proj",
-    "up_proj",
-    "v_proj",
     "q_proj",
+    "gate_proj",
+    "k_proj",
     "down_proj",
-    "k_proj"
+    "v_proj",
+    "o_proj",
+    "up_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 sha256:6f97f42f718855e4d8fa458df3b67f585a5008107acd016298a8510d9593379c
+oid sha256:178fac03a4411b539417f05ec06474a83369a21718afd451e3cf446b37a936d1
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c10f96f94824ff813ac88d30e9c1057e14cbf6d57a95b43cd900c9340690db88
+oid sha256:45a6a35acde268acab35eb68df0888823ab8398fbc8f45827cc044ff840f59ec
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b728c891ef2f8923d3e4681b82d1bc97d910143212455a67e85bd1854f5fb629
+oid sha256:fea119597487640ad29269dafa272b6471f721484550fbf7c4d401510f554f60
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0fb1ce6ea0eb6b77f2f1698fca853726cd185a5fe81476f3350c8e16f115fb9
+oid sha256:b8bd978e1cca44154a5bd5edabe31be57a792ba511f70be71fe3f7ac096a655b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eea9df4de1b48a45ab4d05c850976cfdf23e58dc949331abad5daae7ea48ddf9
+oid sha256:9b114d88faa802892f5433666326c0b8687a3a1aa8c7874c45dc1b8c02cc0183
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca63b019ec5b8cb1f9b3323e8e8672afe71b02f2849101a5a04224c93b5a9574
+oid sha256:cf74a8ef1d7aa718cca8c25db0f83adeaec017d54b894eb91cd12b5dffc92494
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,16 +1,16 @@
 {
-  "best_metric": 0.506989598274231,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.1016483516483517,
+  "best_metric": 0.485868901014328,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.2032967032967035,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.04395604395604396,
-      "grad_norm": 1.6147027015686035,
+      "grad_norm": 1.5371962785720825,
       "learning_rate": 5e-05,
       "loss": 0.9245,
       "step": 1
@@ -18,186 +18,369 @@
     {
       "epoch": 0.04395604395604396,
       "eval_loss": 1.125306487083435,
-      "eval_runtime": 1.5098,
-      "eval_samples_per_second": 101.338,
-      "eval_steps_per_second": 13.247,
+      "eval_runtime": 1.5464,
+      "eval_samples_per_second": 98.942,
+      "eval_steps_per_second": 12.934,
       "step": 1
     },
     {
       "epoch": 0.08791208791208792,
-      "grad_norm": 1.9983218908309937,
+      "grad_norm": 1.9072893857955933,
       "learning_rate": 0.0001,
       "loss": 1.0253,
       "step": 2
     },
     {
       "epoch": 0.13186813186813187,
-      "grad_norm": 1.9161258935928345,
+      "grad_norm": 1.8387856483459473,
       "learning_rate": 9.989294616193017e-05,
-      "loss": 1.0749,
+      "loss": 1.0753,
       "step": 3
     },
     {
       "epoch": 0.17582417582417584,
-      "grad_norm": 1.3471875190734863,
+      "grad_norm": 1.3083786964416504,
       "learning_rate": 9.957224306869053e-05,
-      "loss": 0.9817,
+      "loss": 0.9815,
       "step": 4
     },
     {
       "epoch": 0.21978021978021978,
-      "grad_norm": 1.3092931509017944,
+      "grad_norm": 1.2645456790924072,
       "learning_rate": 9.903926402016153e-05,
       "loss": 0.9245,
       "step": 5
     },
     {
       "epoch": 0.26373626373626374,
-      "grad_norm": 0.8603388071060181,
+      "grad_norm": 0.8451499342918396,
       "learning_rate": 9.829629131445342e-05,
-      "loss": 0.6806,
+      "loss": 0.6823,
       "step": 6
     },
     {
       "epoch": 0.3076923076923077,
-      "grad_norm": 0.7902740240097046,
+      "grad_norm": 0.7806383371353149,
       "learning_rate": 9.73465064747553e-05,
-      "loss": 0.5908,
+      "loss": 0.5938,
       "step": 7
     },
     {
       "epoch": 0.3516483516483517,
-      "grad_norm": 0.7974825501441956,
+      "grad_norm": 0.7988596558570862,
       "learning_rate": 9.619397662556435e-05,
-      "loss": 0.6714,
+      "loss": 0.6745,
       "step": 8
     },
     {
       "epoch": 0.3956043956043956,
-      "grad_norm": 0.5884117484092712,
+      "grad_norm": 0.5786975622177124,
       "learning_rate": 9.484363707663442e-05,
-      "loss": 0.6504,
+      "loss": 0.6528,
       "step": 9
     },
     {
       "epoch": 0.43956043956043955,
-      "grad_norm": 0.7321068048477173,
+      "grad_norm": 0.7035933136940002,
       "learning_rate": 9.330127018922194e-05,
-      "loss": 0.6882,
+      "loss": 0.6902,
       "step": 10
     },
     {
       "epoch": 0.4835164835164835,
-      "grad_norm": 0.8219019174575806,
+      "grad_norm": 0.8232611417770386,
       "learning_rate": 9.157348061512727e-05,
-      "loss": 0.7878,
+      "loss": 0.79,
       "step": 11
     },
     {
       "epoch": 0.5274725274725275,
-      "grad_norm": 0.7585610151290894,
+      "grad_norm": 0.7220979928970337,
       "learning_rate": 8.966766701456177e-05,
-      "loss": 0.509,
+      "loss": 0.5096,
       "step": 12
     },
     {
       "epoch": 0.5714285714285714,
-      "grad_norm": 0.4833940267562866,
+      "grad_norm": 0.4586591422557831,
       "learning_rate": 8.759199037394887e-05,
-      "loss": 0.5126,
+      "loss": 0.5134,
       "step": 13
     },
     {
       "epoch": 0.6153846153846154,
-      "grad_norm": 0.5011129379272461,
+      "grad_norm": 0.48070022463798523,
       "learning_rate": 8.535533905932738e-05,
-      "loss": 0.5713,
+      "loss": 0.5731,
       "step": 14
     },
     {
       "epoch": 0.6593406593406593,
-      "grad_norm": 0.5959790945053101,
+      "grad_norm": 0.5730169415473938,
       "learning_rate": 8.296729075500344e-05,
-      "loss": 0.6383,
+      "loss": 0.6391,
       "step": 15
     },
     {
       "epoch": 0.7032967032967034,
-      "grad_norm": 0.45197582244873047,
+      "grad_norm": 0.4397137761116028,
       "learning_rate": 8.043807145043604e-05,
-      "loss": 0.6132,
+      "loss": 0.6148,
       "step": 16
     },
     {
       "epoch": 0.7472527472527473,
-      "grad_norm": 0.44793838262557983,
+      "grad_norm": 0.4415135085582733,
       "learning_rate": 7.777851165098012e-05,
-      "loss": 0.5253,
+      "loss": 0.527,
       "step": 17
     },
     {
       "epoch": 0.7912087912087912,
-      "grad_norm": 0.47516193985939026,
+      "grad_norm": 0.47121483087539673,
       "learning_rate": 7.500000000000001e-05,
-      "loss": 0.4624,
+      "loss": 0.4637,
       "step": 18
     },
     {
       "epoch": 0.8351648351648352,
-      "grad_norm": 0.3715343177318573,
+      "grad_norm": 0.35576266050338745,
       "learning_rate": 7.211443451095007e-05,
-      "loss": 0.4779,
+      "loss": 0.479,
       "step": 19
     },
     {
       "epoch": 0.8791208791208791,
-      "grad_norm": 0.3526500165462494,
+      "grad_norm": 0.3464816212654114,
       "learning_rate": 6.91341716182545e-05,
-      "loss": 0.5268,
+      "loss": 0.5275,
       "step": 20
     },
     {
       "epoch": 0.9230769230769231,
-      "grad_norm": 0.42601215839385986,
+      "grad_norm": 0.4190969169139862,
       "learning_rate": 6.607197326515808e-05,
-      "loss": 0.6127,
+      "loss": 0.613,
       "step": 21
     },
     {
       "epoch": 0.967032967032967,
-      "grad_norm": 0.5091745257377625,
+      "grad_norm": 0.5241257548332214,
       "learning_rate": 6.294095225512603e-05,
-      "loss": 0.6665,
+      "loss": 0.6681,
       "step": 22
     },
     {
       "epoch": 1.0137362637362637,
-      "grad_norm": 0.49048399925231934,
+      "grad_norm": 0.475443035364151,
       "learning_rate": 5.9754516100806423e-05,
-      "loss": 0.6154,
+      "loss": 0.6159,
       "step": 23
     },
     {
       "epoch": 1.0576923076923077,
-      "grad_norm": 0.3723498284816742,
+      "grad_norm": 0.36700522899627686,
       "learning_rate": 5.6526309611002594e-05,
-      "loss": 0.4186,
+      "loss": 0.4199,
       "step": 24
     },
     {
       "epoch": 1.1016483516483517,
-      "grad_norm": 0.33258843421936035,
+      "grad_norm": 0.32403191924095154,
       "learning_rate": 5.327015646150716e-05,
-      "loss": 0.4749,
+      "loss": 0.4759,
       "step": 25
     },
     {
       "epoch": 1.1016483516483517,
-      "eval_loss": 0.506989598274231,
-      "eval_runtime": 1.5047,
-      "eval_samples_per_second": 101.683,
-      "eval_steps_per_second": 13.292,
+      "eval_loss": 0.5078209638595581,
+      "eval_runtime": 1.5369,
+      "eval_samples_per_second": 99.554,
+      "eval_steps_per_second": 13.014,
       "step": 25
+    },
+    {
+      "epoch": 1.1456043956043955,
+      "grad_norm": 0.3684566020965576,
+      "learning_rate": 5e-05,
+      "loss": 0.5021,
+      "step": 26
+    },
+    {
+      "epoch": 1.1895604395604396,
+      "grad_norm": 0.4323870837688446,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.5825,
+      "step": 27
+    },
+    {
+      "epoch": 1.2335164835164836,
+      "grad_norm": 0.37133166193962097,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.5717,
+      "step": 28
+    },
+    {
+      "epoch": 1.2774725274725274,
+      "grad_norm": 0.43744349479675293,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.4423,
+      "step": 29
+    },
+    {
+      "epoch": 1.3214285714285714,
+      "grad_norm": 0.36784860491752625,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.4522,
+      "step": 30
+    },
+    {
+      "epoch": 1.3653846153846154,
+      "grad_norm": 0.42360466718673706,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.4478,
+      "step": 31
+    },
+    {
+      "epoch": 1.4093406593406592,
+      "grad_norm": 0.36743155121803284,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.5131,
+      "step": 32
+    },
+    {
+      "epoch": 1.4532967032967032,
+      "grad_norm": 0.4220162034034729,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.5558,
+      "step": 33
+    },
+    {
+      "epoch": 1.4972527472527473,
+      "grad_norm": 0.3486455976963043,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.5302,
+      "step": 34
+    },
+    {
+      "epoch": 1.541208791208791,
+      "grad_norm": 0.33336740732192993,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.386,
+      "step": 35
+    },
+    {
+      "epoch": 1.5851648351648353,
+      "grad_norm": 0.3811834752559662,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.4203,
+      "step": 36
+    },
+    {
+      "epoch": 1.629120879120879,
+      "grad_norm": 0.3623700737953186,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.4668,
+      "step": 37
+    },
+    {
+      "epoch": 1.6730769230769231,
+      "grad_norm": 0.42458808422088623,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.5424,
+      "step": 38
+    },
+    {
+      "epoch": 1.7170329670329672,
+      "grad_norm": 0.3512580692768097,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.5354,
+      "step": 39
+    },
+    {
+      "epoch": 1.760989010989011,
+      "grad_norm": 0.4050043225288391,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.4431,
+      "step": 40
+    },
+    {
+      "epoch": 1.804945054945055,
+      "grad_norm": 0.40043145418167114,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.4225,
+      "step": 41
+    },
+    {
+      "epoch": 1.848901098901099,
+      "grad_norm": 0.32833555340766907,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.4603,
+      "step": 42
+    },
+    {
+      "epoch": 1.8928571428571428,
+      "grad_norm": 0.37721043825149536,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.5131,
+      "step": 43
+    },
+    {
+      "epoch": 1.9368131868131868,
+      "grad_norm": 0.43689805269241333,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.592,
+      "step": 44
+    },
+    {
+      "epoch": 1.9807692307692308,
+      "grad_norm": 0.4466743767261505,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.5822,
+      "step": 45
+    },
+    {
+      "epoch": 2.0274725274725274,
+      "grad_norm": 0.41001924872398376,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.4933,
+      "step": 46
+    },
+    {
+      "epoch": 2.0714285714285716,
+      "grad_norm": 0.3849025070667267,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.4158,
+      "step": 47
+    },
+    {
+      "epoch": 2.1153846153846154,
+      "grad_norm": 0.44459646940231323,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.4408,
+      "step": 48
+    },
+    {
+      "epoch": 2.159340659340659,
+      "grad_norm": 0.449739545583725,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.4819,
+      "step": 49
+    },
+    {
+      "epoch": 2.2032967032967035,
+      "grad_norm": 0.4939447343349457,
+      "learning_rate": 0.0,
+      "loss": 0.5507,
+      "step": 50
+    },
+    {
+      "epoch": 2.2032967032967035,
+      "eval_loss": 0.485868901014328,
+      "eval_runtime": 1.5387,
+      "eval_samples_per_second": 99.437,
+      "eval_steps_per_second": 12.998,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.16708196040704e+16,
+  "total_flos": 8.33416392081408e+16,
   "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 sha256:4e4d513a4abdd668e3a6ca19a017616fa49a05ff1c07caf387c8770c410e006d
+oid sha256:2ab06be51039df455003f8feb3e74f379f65814e8310c29b4150b77286ba1778
 size 6776