Training in progress, step 25, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "o_proj",
+    "v_proj",
     "down_proj",
-    "gate_proj",
     "k_proj",
-    "v_proj",
-    "q_proj",
-    "up_proj"
+    "up_proj",
+    "gate_proj",
+    "q_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 sha256:18d08daf69bd77ed1bb70978d06f92f283cb3dfd5c0131a3a9f0552805e3a58b
+oid sha256:6e2623f5b52f366a3149ee5f94a2de76936d72603531cb4c40f79a5425c0f7e3
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad21280ec437b5c9fe85ecce69c562f704bea3d91915b62843100422242b06cb
+oid sha256:021b91241b0c0f56423e62e108eeef830a824e1a9313356165bd179a9c2565ed
 size 295765866

last-checkpoint/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.42539140582084656,
+  "best_metric": 0.4251263737678528,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
   "epoch": 1.217910447761194,
   "eval_steps": 25,
@@ -10,7 +10,7 @@
   "log_history": [
     {
       "epoch": 0.04776119402985075,
-      "grad_norm": 0.29185420274734497,
+      "grad_norm": 0.29309335350990295,
       "learning_rate": 5e-05,
       "loss": 0.551,
       "step": 1
@@ -18,185 +18,185 @@
     {
       "epoch": 0.04776119402985075,
       "eval_loss": 0.5565004348754883,
-      "eval_runtime": 1.6581,
-      "eval_samples_per_second": 85.038,
-      "eval_steps_per_second": 10.856,
+      "eval_runtime": 1.6321,
+      "eval_samples_per_second": 86.392,
+      "eval_steps_per_second": 11.029,
       "step": 1
     },
     {
       "epoch": 0.0955223880597015,
-      "grad_norm": 0.34828293323516846,
+      "grad_norm": 0.34882017970085144,
       "learning_rate": 0.0001,
       "loss": 0.5825,
       "step": 2
     },
     {
       "epoch": 0.14328358208955225,
-      "grad_norm": 0.33185914158821106,
+      "grad_norm": 0.33288702368736267,
       "learning_rate": 9.989294616193017e-05,
-      "loss": 0.5789,
+      "loss": 0.5791,
       "step": 3
     },
     {
       "epoch": 0.191044776119403,
-      "grad_norm": 0.3632985055446625,
+      "grad_norm": 0.36883237957954407,
       "learning_rate": 9.957224306869053e-05,
-      "loss": 0.5382,
+      "loss": 0.538,
       "step": 4
     },
     {
       "epoch": 0.23880597014925373,
-      "grad_norm": 0.3530183434486389,
+      "grad_norm": 0.3539741337299347,
       "learning_rate": 9.903926402016153e-05,
-      "loss": 0.5279,
+      "loss": 0.5281,
       "step": 5
     },
     {
       "epoch": 0.2865671641791045,
-      "grad_norm": 0.23330174386501312,
+      "grad_norm": 0.23581592738628387,
       "learning_rate": 9.829629131445342e-05,
-      "loss": 0.5199,
+      "loss": 0.5197,
       "step": 6
     },
     {
       "epoch": 0.33432835820895523,
-      "grad_norm": 0.278849333524704,
+      "grad_norm": 0.28109219670295715,
       "learning_rate": 9.73465064747553e-05,
-      "loss": 0.5065,
+      "loss": 0.5066,
       "step": 7
     },
     {
       "epoch": 0.382089552238806,
-      "grad_norm": 0.2901425361633301,
+      "grad_norm": 0.29403433203697205,
       "learning_rate": 9.619397662556435e-05,
-      "loss": 0.493,
+      "loss": 0.4929,
       "step": 8
     },
     {
       "epoch": 0.4298507462686567,
-      "grad_norm": 0.29416143894195557,
+      "grad_norm": 0.2939996123313904,
       "learning_rate": 9.484363707663442e-05,
-      "loss": 0.5316,
+      "loss": 0.5313,
       "step": 9
     },
     {
       "epoch": 0.47761194029850745,
-      "grad_norm": 0.3660103976726532,
+      "grad_norm": 0.363861083984375,
       "learning_rate": 9.330127018922194e-05,
-      "loss": 0.4523,
+      "loss": 0.4514,
       "step": 10
     },
     {
       "epoch": 0.5253731343283582,
-      "grad_norm": 0.19246715307235718,
+      "grad_norm": 0.19598151743412018,
       "learning_rate": 9.157348061512727e-05,
       "loss": 0.4927,
       "step": 11
     },
     {
       "epoch": 0.573134328358209,
-      "grad_norm": 0.20531879365444183,
+      "grad_norm": 0.20769856870174408,
       "learning_rate": 8.966766701456177e-05,
       "loss": 0.5076,
       "step": 12
     },
     {
       "epoch": 0.6208955223880597,
-      "grad_norm": 0.20391716063022614,
+      "grad_norm": 0.2053491175174713,
       "learning_rate": 8.759199037394887e-05,
-      "loss": 0.4657,
+      "loss": 0.4653,
       "step": 13
     },
     {
       "epoch": 0.6686567164179105,
-      "grad_norm": 0.22268980741500854,
+      "grad_norm": 0.22446739673614502,
       "learning_rate": 8.535533905932738e-05,
-      "loss": 0.4792,
+      "loss": 0.4791,
       "step": 14
     },
     {
       "epoch": 0.7164179104477612,
-      "grad_norm": 0.2864244878292084,
+      "grad_norm": 0.2886030972003937,
       "learning_rate": 8.296729075500344e-05,
-      "loss": 0.4274,
+      "loss": 0.4275,
       "step": 15
     },
     {
       "epoch": 0.764179104477612,
-      "grad_norm": 0.16762878000736237,
+      "grad_norm": 0.1693258434534073,
       "learning_rate": 8.043807145043604e-05,
-      "loss": 0.4894,
+      "loss": 0.4891,
       "step": 16
     },
     {
       "epoch": 0.8119402985074626,
-      "grad_norm": 0.18803684413433075,
+      "grad_norm": 0.18894262611865997,
       "learning_rate": 7.777851165098012e-05,
-      "loss": 0.4475,
+      "loss": 0.4471,
       "step": 17
     },
     {
       "epoch": 0.8597014925373134,
-      "grad_norm": 0.19906236231327057,
+      "grad_norm": 0.2001345455646515,
       "learning_rate": 7.500000000000001e-05,
       "loss": 0.4717,
       "step": 18
     },
     {
       "epoch": 0.9074626865671642,
-      "grad_norm": 0.24964551627635956,
+      "grad_norm": 0.25183868408203125,
       "learning_rate": 7.211443451095007e-05,
-      "loss": 0.4579,
+      "loss": 0.458,
       "step": 19
     },
     {
       "epoch": 0.9552238805970149,
-      "grad_norm": 0.29042649269104004,
+      "grad_norm": 0.29334449768066406,
       "learning_rate": 6.91341716182545e-05,
-      "loss": 0.3962,
+      "loss": 0.3965,
       "step": 20
     },
     {
       "epoch": 1.026865671641791,
-      "grad_norm": 0.28468796610832214,
+      "grad_norm": 0.28625965118408203,
       "learning_rate": 6.607197326515808e-05,
-      "loss": 0.7955,
+      "loss": 0.796,
       "step": 21
     },
     {
       "epoch": 1.0746268656716418,
-      "grad_norm": 0.16371072828769684,
+      "grad_norm": 0.16455918550491333,
       "learning_rate": 6.294095225512603e-05,
-      "loss": 0.4403,
+      "loss": 0.4404,
       "step": 22
     },
     {
       "epoch": 1.1223880597014926,
-      "grad_norm": 0.19278578460216522,
+      "grad_norm": 0.1942681223154068,
       "learning_rate": 5.9754516100806423e-05,
-      "loss": 0.4031,
+      "loss": 0.4026,
       "step": 23
     },
     {
       "epoch": 1.1701492537313434,
-      "grad_norm": 0.21322554349899292,
+      "grad_norm": 0.21410231292247772,
       "learning_rate": 5.6526309611002594e-05,
-      "loss": 0.4135,
+      "loss": 0.413,
       "step": 24
     },
     {
       "epoch": 1.217910447761194,
-      "grad_norm": 0.2575645446777344,
+      "grad_norm": 0.25955915451049805,
       "learning_rate": 5.327015646150716e-05,
       "loss": 0.4206,
       "step": 25
     },
     {
       "epoch": 1.217910447761194,
-      "eval_loss": 0.42539140582084656,
-      "eval_runtime": 1.6618,
-      "eval_samples_per_second": 84.848,
-      "eval_steps_per_second": 10.832,
+      "eval_loss": 0.4251263737678528,
+      "eval_runtime": 1.6332,
+      "eval_samples_per_second": 86.336,
+      "eval_steps_per_second": 11.022,
       "step": 25
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e94c1e826225abe88b190761b2645c6636cea2d7bee422d5c89d0033daed0be6
+oid sha256:c3dea4593a7a820a778fc84ba6e04d4471ebc30e6df1994d208d89710cfaf65d
 size 6776