Training in progress, step 25, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "gate_proj",
-    "v_proj",
-    "down_proj",
     "q_proj",
     "o_proj",
-    "up_proj"
+    "gate_proj",
+    "down_proj",
+    "up_proj",
+    "v_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 sha256:4ff964722b16dcf6066892ea2b2f5a1e7ed49803f147a3ae76528f150f428920
+oid sha256:60c768093d7e707272b88b8681161101482d91ff27d34707c835688cfb66a484
 size 1521616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be5dfd669994765dea55ab41fe132a2076884bc1bb67db1dd23426529c10b3ac
+oid sha256:6c83365661ca55181717555fd4f031c94bd9d3c0846378f0e848128d7cc2cd0b
 size 3108666

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39243204b56d431003e6e773c1c2d1cdb50080063a598d8fee14c9a88682118d
+oid sha256:9404daff786212647adae37fe2da75d552625d004cba5f320a9ff699d3d0fb10
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cf0609556c2eb01e8432f5b060fd30bf661a79eca117a47e8dd6bd7d407f244
+oid sha256:63012b6efda9d84cc4848e8b5ee45ce563a6507cd33a7c7a33274f0f09037e75
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7f9a7f8ef7e623c3305d1581a2cd933bab8261a9f9a3a65bc6a1b41de4c9766
+oid sha256:0eeb243c384ce8fc44c40f20541b6588764eeedc39cf6878e3a85acf147afd44
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04c83ecaac631b2612151829ef0e470dbcec9a75dcab8cc86455369697351366
+oid sha256:95e2056053203985537510bbda269726e6ee1a0a97ba52768c8acfddc716b54a
 size 15024

last-checkpoint/scheduler.pt

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

last-checkpoint/trainer_state.json

@@ -1,386 +1,203 @@
 {
-  "best_metric": 7.063704490661621,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.12886597938144329,
+  "best_metric": 7.125263214111328,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.06443298969072164,
   "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": 0.002577319587628866,
-      "grad_norm": 8.84896469116211,
+      "grad_norm": 8.932095527648926,
       "learning_rate": 5e-05,
       "loss": 8.769,
       "step": 1
     },
     {
       "epoch": 0.002577319587628866,
-      "eval_loss": 7.704258441925049,
-      "eval_runtime": 13.4583,
-      "eval_samples_per_second": 194.229,
-      "eval_steps_per_second": 24.297,
+      "eval_loss": 7.7042412757873535,
+      "eval_runtime": 27.296,
+      "eval_samples_per_second": 95.765,
+      "eval_steps_per_second": 11.98,
       "step": 1
     },
     {
       "epoch": 0.005154639175257732,
-      "grad_norm": 5.125444412231445,
+      "grad_norm": 5.1865434646606445,
       "learning_rate": 0.0001,
       "loss": 8.594,
       "step": 2
     },
     {
       "epoch": 0.007731958762886598,
-      "grad_norm": 4.254770755767822,
+      "grad_norm": 4.275647163391113,
       "learning_rate": 9.989294616193017e-05,
-      "loss": 8.2293,
+      "loss": 8.2291,
       "step": 3
     },
     {
       "epoch": 0.010309278350515464,
-      "grad_norm": 3.761096239089966,
+      "grad_norm": 3.744438409805298,
       "learning_rate": 9.957224306869053e-05,
-      "loss": 8.3432,
+      "loss": 8.3425,
       "step": 4
     },
     {
       "epoch": 0.01288659793814433,
-      "grad_norm": 2.6418516635894775,
+      "grad_norm": 2.634883403778076,
       "learning_rate": 9.903926402016153e-05,
-      "loss": 7.6389,
+      "loss": 7.6405,
       "step": 5
     },
     {
       "epoch": 0.015463917525773196,
-      "grad_norm": 2.60322642326355,
+      "grad_norm": 2.6033172607421875,
       "learning_rate": 9.829629131445342e-05,
-      "loss": 7.5408,
+      "loss": 7.5428,
       "step": 6
     },
     {
       "epoch": 0.01804123711340206,
-      "grad_norm": 2.4060311317443848,
+      "grad_norm": 2.397871255874634,
       "learning_rate": 9.73465064747553e-05,
-      "loss": 7.5405,
+      "loss": 7.5443,
       "step": 7
     },
     {
       "epoch": 0.020618556701030927,
-      "grad_norm": 2.1694252490997314,
+      "grad_norm": 2.1589975357055664,
       "learning_rate": 9.619397662556435e-05,
-      "loss": 7.2925,
+      "loss": 7.2973,
       "step": 8
     },
     {
       "epoch": 0.023195876288659795,
-      "grad_norm": 1.9732533693313599,
+      "grad_norm": 1.9659868478775024,
       "learning_rate": 9.484363707663442e-05,
-      "loss": 7.2964,
+      "loss": 7.2995,
       "step": 9
     },
     {
       "epoch": 0.02577319587628866,
-      "grad_norm": 1.90111243724823,
+      "grad_norm": 1.8988659381866455,
       "learning_rate": 9.330127018922194e-05,
-      "loss": 6.9977,
+      "loss": 6.9992,
       "step": 10
     },
     {
       "epoch": 0.028350515463917526,
-      "grad_norm": 1.7233860492706299,
+      "grad_norm": 1.7255256175994873,
       "learning_rate": 9.157348061512727e-05,
-      "loss": 7.0945,
+      "loss": 7.0953,
       "step": 11
     },
     {
       "epoch": 0.030927835051546393,
-      "grad_norm": 1.980125069618225,
+      "grad_norm": 1.986493706703186,
       "learning_rate": 8.966766701456177e-05,
-      "loss": 7.056,
+      "loss": 7.0552,
       "step": 12
     },
     {
       "epoch": 0.03350515463917526,
-      "grad_norm": 3.8307547569274902,
+      "grad_norm": 3.806684732437134,
       "learning_rate": 8.759199037394887e-05,
-      "loss": 7.6226,
+      "loss": 7.6275,
       "step": 13
     },
     {
       "epoch": 0.03608247422680412,
-      "grad_norm": 4.206315994262695,
+      "grad_norm": 4.209149360656738,
       "learning_rate": 8.535533905932738e-05,
-      "loss": 7.7023,
+      "loss": 7.7068,
       "step": 14
     },
     {
       "epoch": 0.03865979381443299,
-      "grad_norm": 2.2115254402160645,
+      "grad_norm": 2.2306342124938965,
       "learning_rate": 8.296729075500344e-05,
-      "loss": 7.7303,
+      "loss": 7.7352,
       "step": 15
     },
     {
       "epoch": 0.041237113402061855,
-      "grad_norm": 1.6303458213806152,
+      "grad_norm": 1.6664167642593384,
       "learning_rate": 8.043807145043604e-05,
-      "loss": 7.5333,
+      "loss": 7.5366,
       "step": 16
     },
     {
       "epoch": 0.04381443298969072,
-      "grad_norm": 1.4174168109893799,
+      "grad_norm": 1.4569931030273438,
       "learning_rate": 7.777851165098012e-05,
-      "loss": 7.4892,
+      "loss": 7.4936,
       "step": 17
     },
     {
       "epoch": 0.04639175257731959,
-      "grad_norm": 1.1928077936172485,
+      "grad_norm": 1.2213176488876343,
       "learning_rate": 7.500000000000001e-05,
-      "loss": 7.4843,
+      "loss": 7.4877,
       "step": 18
     },
     {
       "epoch": 0.04896907216494845,
-      "grad_norm": 1.2452458143234253,
+      "grad_norm": 1.2630321979522705,
       "learning_rate": 7.211443451095007e-05,
-      "loss": 7.3061,
+      "loss": 7.3076,
       "step": 19
     },
     {
       "epoch": 0.05154639175257732,
-      "grad_norm": 1.2192394733428955,
+      "grad_norm": 1.1982954740524292,
       "learning_rate": 6.91341716182545e-05,
-      "loss": 7.1825,
+      "loss": 7.1835,
       "step": 20
     },
     {
       "epoch": 0.05412371134020619,
-      "grad_norm": 1.2151198387145996,
+      "grad_norm": 1.179440975189209,
       "learning_rate": 6.607197326515808e-05,
-      "loss": 7.0109,
+      "loss": 7.0129,
       "step": 21
     },
     {
       "epoch": 0.05670103092783505,
-      "grad_norm": 1.2521761655807495,
+      "grad_norm": 1.2165639400482178,
       "learning_rate": 6.294095225512603e-05,
-      "loss": 6.8825,
+      "loss": 6.8845,
       "step": 22
     },
     {
       "epoch": 0.059278350515463915,
-      "grad_norm": 1.183918833732605,
+      "grad_norm": 1.1670974493026733,
       "learning_rate": 5.9754516100806423e-05,
-      "loss": 6.9443,
+      "loss": 6.9454,
       "step": 23
     },
     {
       "epoch": 0.061855670103092786,
-      "grad_norm": 1.1090588569641113,
+      "grad_norm": 1.096975326538086,
       "learning_rate": 5.6526309611002594e-05,
-      "loss": 6.9259,
+      "loss": 6.9278,
       "step": 24
     },
     {
       "epoch": 0.06443298969072164,
-      "grad_norm": 1.5472322702407837,
+      "grad_norm": 1.54706609249115,
       "learning_rate": 5.327015646150716e-05,
-      "loss": 6.5826,
+      "loss": 6.5843,
       "step": 25
     },
     {
       "epoch": 0.06443298969072164,
-      "eval_loss": 7.122404098510742,
-      "eval_runtime": 13.3389,
-      "eval_samples_per_second": 195.968,
-      "eval_steps_per_second": 24.515,
+      "eval_loss": 7.125263214111328,
+      "eval_runtime": 26.0926,
+      "eval_samples_per_second": 100.182,
+      "eval_steps_per_second": 12.532,
       "step": 25
-    },
-    {
-      "epoch": 0.06701030927835051,
-      "grad_norm": 2.843515634536743,
-      "learning_rate": 5e-05,
-      "loss": 7.2493,
-      "step": 26
-    },
-    {
-      "epoch": 0.06958762886597938,
-      "grad_norm": 1.6025389432907104,
-      "learning_rate": 4.6729843538492847e-05,
-      "loss": 7.8308,
-      "step": 27
-    },
-    {
-      "epoch": 0.07216494845360824,
-      "grad_norm": 1.3303579092025757,
-      "learning_rate": 4.347369038899744e-05,
-      "loss": 7.5161,
-      "step": 28
-    },
-    {
-      "epoch": 0.07474226804123711,
-      "grad_norm": 1.0986202955245972,
-      "learning_rate": 4.0245483899193595e-05,
-      "loss": 7.4137,
-      "step": 29
-    },
-    {
-      "epoch": 0.07731958762886598,
-      "grad_norm": 0.9372117519378662,
-      "learning_rate": 3.705904774487396e-05,
-      "loss": 7.3211,
-      "step": 30
-    },
-    {
-      "epoch": 0.07989690721649484,
-      "grad_norm": 1.0359989404678345,
-      "learning_rate": 3.392802673484193e-05,
-      "loss": 7.4251,
-      "step": 31
-    },
-    {
-      "epoch": 0.08247422680412371,
-      "grad_norm": 1.050330400466919,
-      "learning_rate": 3.086582838174551e-05,
-      "loss": 6.9601,
-      "step": 32
-    },
-    {
-      "epoch": 0.08505154639175258,
-      "grad_norm": 1.0149939060211182,
-      "learning_rate": 2.7885565489049946e-05,
-      "loss": 7.0997,
-      "step": 33
-    },
-    {
-      "epoch": 0.08762886597938144,
-      "grad_norm": 0.8797879815101624,
-      "learning_rate": 2.500000000000001e-05,
-      "loss": 6.8525,
-      "step": 34
-    },
-    {
-      "epoch": 0.09020618556701031,
-      "grad_norm": 0.9121543169021606,
-      "learning_rate": 2.2221488349019903e-05,
-      "loss": 6.8513,
-      "step": 35
-    },
-    {
-      "epoch": 0.09278350515463918,
-      "grad_norm": 0.9668096303939819,
-      "learning_rate": 1.9561928549563968e-05,
-      "loss": 6.7363,
-      "step": 36
-    },
-    {
-      "epoch": 0.09536082474226804,
-      "grad_norm": 1.13383150100708,
-      "learning_rate": 1.703270924499656e-05,
-      "loss": 6.6522,
-      "step": 37
-    },
-    {
-      "epoch": 0.0979381443298969,
-      "grad_norm": 1.455060601234436,
-      "learning_rate": 1.4644660940672627e-05,
-      "loss": 7.743,
-      "step": 38
-    },
-    {
-      "epoch": 0.10051546391752578,
-      "grad_norm": 1.4939161539077759,
-      "learning_rate": 1.2408009626051137e-05,
-      "loss": 7.6736,
-      "step": 39
-    },
-    {
-      "epoch": 0.10309278350515463,
-      "grad_norm": 1.1243243217468262,
-      "learning_rate": 1.0332332985438248e-05,
-      "loss": 7.5141,
-      "step": 40
-    },
-    {
-      "epoch": 0.1056701030927835,
-      "grad_norm": 1.0334477424621582,
-      "learning_rate": 8.426519384872733e-06,
-      "loss": 7.4467,
-      "step": 41
-    },
-    {
-      "epoch": 0.10824742268041238,
-      "grad_norm": 0.850965142250061,
-      "learning_rate": 6.698729810778065e-06,
-      "loss": 7.4166,
-      "step": 42
-    },
-    {
-      "epoch": 0.11082474226804123,
-      "grad_norm": 0.9271207451820374,
-      "learning_rate": 5.156362923365588e-06,
-      "loss": 7.2256,
-      "step": 43
-    },
-    {
-      "epoch": 0.1134020618556701,
-      "grad_norm": 0.924728512763977,
-      "learning_rate": 3.8060233744356633e-06,
-      "loss": 7.1742,
-      "step": 44
-    },
-    {
-      "epoch": 0.11597938144329897,
-      "grad_norm": 0.8596798777580261,
-      "learning_rate": 2.653493525244721e-06,
-      "loss": 7.0014,
-      "step": 45
-    },
-    {
-      "epoch": 0.11855670103092783,
-      "grad_norm": 0.9014486074447632,
-      "learning_rate": 1.70370868554659e-06,
-      "loss": 6.9507,
-      "step": 46
-    },
-    {
-      "epoch": 0.1211340206185567,
-      "grad_norm": 0.8988224267959595,
-      "learning_rate": 9.607359798384785e-07,
-      "loss": 6.8728,
-      "step": 47
-    },
-    {
-      "epoch": 0.12371134020618557,
-      "grad_norm": 0.8983946442604065,
-      "learning_rate": 4.277569313094809e-07,
-      "loss": 6.6614,
-      "step": 48
-    },
-    {
-      "epoch": 0.12628865979381443,
-      "grad_norm": 0.9872623085975647,
-      "learning_rate": 1.0705383806982606e-07,
-      "loss": 6.8147,
-      "step": 49
-    },
-    {
-      "epoch": 0.12886597938144329,
-      "grad_norm": 1.2063250541687012,
-      "learning_rate": 0.0,
-      "loss": 6.6433,
-      "step": 50
-    },
-    {
-      "epoch": 0.12886597938144329,
-      "eval_loss": 7.063704490661621,
-      "eval_runtime": 13.226,
-      "eval_samples_per_second": 197.64,
-      "eval_steps_per_second": 24.724,
-      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -404,12 +221,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 239916767772672.0,
+  "total_flos": 119559610171392.0,
   "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 sha256:66bf9ec9ddbf12dd719515e13707e33922360dd50872490ee350c666d3a23578
+oid sha256:9aa8a78e217473ef4dde9abd0449db4a3aeeaeba985aec38100e9a44af330002
 size 6776