Training in progress, step 25, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "down_proj",
-    "up_proj",
-    "v_proj",
-    "q_proj",
+    "gate_proj",
     "k_proj",
-    "gate_proj"
+    "q_proj",
+    "v_proj",
+    "down_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 sha256:9c06b98806979feff32215460fd4ee91585a1f3b6592cd2f849ae95df3caf9d8
+oid sha256:ae7790f6750cce5fb155b7082d134522fe9312e8e536a851652e2d551940ea8a
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:665bf55af6ba1f986af893be0eaeda3f7eaf0ecef7462f3bf465eead1dec19f1
+oid sha256:8944c9130cc0aa59b1d38ba554ac3c84d606f76602259d50dd3f66f13e86b3d6
 size 212298

last-checkpoint/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 10.370012283325195,
+  "best_metric": 10.369842529296875,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
   "epoch": 0.05670541536716756,
   "eval_steps": 25,
@@ -10,7 +10,7 @@
   "log_history": [
     {
       "epoch": 0.0022682166146867026,
-      "grad_norm": 0.13453303277492523,
+      "grad_norm": 0.14479899406433105,
       "learning_rate": 5e-05,
       "loss": 10.3842,
       "step": 1
@@ -18,185 +18,185 @@
     {
       "epoch": 0.0022682166146867026,
       "eval_loss": 10.386616706848145,
-      "eval_runtime": 3.0147,
-      "eval_samples_per_second": 985.168,
-      "eval_steps_per_second": 123.395,
+      "eval_runtime": 3.2554,
+      "eval_samples_per_second": 912.334,
+      "eval_steps_per_second": 114.272,
       "step": 1
     },
     {
       "epoch": 0.004536433229373405,
-      "grad_norm": 0.1353277713060379,
+      "grad_norm": 0.14807619154453278,
       "learning_rate": 0.0001,
       "loss": 10.3876,
       "step": 2
     },
     {
       "epoch": 0.006804649844060108,
-      "grad_norm": 0.14166195690631866,
+      "grad_norm": 0.15308985114097595,
       "learning_rate": 9.989294616193017e-05,
       "loss": 10.3875,
       "step": 3
     },
     {
       "epoch": 0.00907286645874681,
-      "grad_norm": 0.14265072345733643,
+      "grad_norm": 0.1542433798313141,
       "learning_rate": 9.957224306869053e-05,
-      "loss": 10.3854,
+      "loss": 10.3853,
       "step": 4
     },
     {
       "epoch": 0.011341083073433513,
-      "grad_norm": 0.1489330232143402,
+      "grad_norm": 0.161626935005188,
       "learning_rate": 9.903926402016153e-05,
-      "loss": 10.3863,
+      "loss": 10.3862,
       "step": 5
     },
     {
       "epoch": 0.013609299688120215,
-      "grad_norm": 0.14977039396762848,
+      "grad_norm": 0.16123023629188538,
       "learning_rate": 9.829629131445342e-05,
-      "loss": 10.3842,
+      "loss": 10.3841,
       "step": 6
     },
     {
       "epoch": 0.01587751630280692,
-      "grad_norm": 0.15355272591114044,
+      "grad_norm": 0.1623682677745819,
       "learning_rate": 9.73465064747553e-05,
-      "loss": 10.3833,
+      "loss": 10.3832,
       "step": 7
     },
     {
       "epoch": 0.01814573291749362,
-      "grad_norm": 0.1444183886051178,
+      "grad_norm": 0.15166254341602325,
       "learning_rate": 9.619397662556435e-05,
-      "loss": 10.3862,
+      "loss": 10.3861,
       "step": 8
     },
     {
       "epoch": 0.020413949532180325,
-      "grad_norm": 0.15106390416622162,
+      "grad_norm": 0.16110487282276154,
       "learning_rate": 9.484363707663442e-05,
-      "loss": 10.3849,
+      "loss": 10.3847,
       "step": 9
     },
     {
       "epoch": 0.022682166146867026,
-      "grad_norm": 0.154390349984169,
+      "grad_norm": 0.15980345010757446,
       "learning_rate": 9.330127018922194e-05,
       "loss": 10.3838,
       "step": 10
     },
     {
       "epoch": 0.02495038276155373,
-      "grad_norm": 0.14189912378787994,
+      "grad_norm": 0.146297425031662,
       "learning_rate": 9.157348061512727e-05,
-      "loss": 10.3832,
+      "loss": 10.3831,
       "step": 11
     },
     {
       "epoch": 0.02721859937624043,
-      "grad_norm": 0.16048261523246765,
+      "grad_norm": 0.16222330927848816,
       "learning_rate": 8.966766701456177e-05,
-      "loss": 10.3848,
+      "loss": 10.3847,
       "step": 12
     },
     {
       "epoch": 0.029486815990927135,
-      "grad_norm": 0.18116344511508942,
+      "grad_norm": 0.1891157180070877,
       "learning_rate": 8.759199037394887e-05,
-      "loss": 10.3773,
+      "loss": 10.377,
       "step": 13
     },
     {
       "epoch": 0.03175503260561384,
-      "grad_norm": 0.1787891834974289,
+      "grad_norm": 0.19309911131858826,
       "learning_rate": 8.535533905932738e-05,
-      "loss": 10.3796,
+      "loss": 10.3792,
       "step": 14
     },
     {
       "epoch": 0.03402324922030054,
-      "grad_norm": 0.19100786745548248,
+      "grad_norm": 0.202869713306427,
       "learning_rate": 8.296729075500344e-05,
-      "loss": 10.3789,
+      "loss": 10.3785,
       "step": 15
     },
     {
       "epoch": 0.03629146583498724,
-      "grad_norm": 0.19920316338539124,
+      "grad_norm": 0.2117149531841278,
       "learning_rate": 8.043807145043604e-05,
-      "loss": 10.3765,
+      "loss": 10.3761,
       "step": 16
     },
     {
       "epoch": 0.03855968244967394,
-      "grad_norm": 0.19364210963249207,
+      "grad_norm": 0.20285949110984802,
       "learning_rate": 7.777851165098012e-05,
-      "loss": 10.3789,
+      "loss": 10.3787,
       "step": 17
     },
     {
       "epoch": 0.04082789906436065,
-      "grad_norm": 0.1934957504272461,
+      "grad_norm": 0.202358677983284,
       "learning_rate": 7.500000000000001e-05,
-      "loss": 10.3758,
+      "loss": 10.3756,
       "step": 18
     },
     {
       "epoch": 0.04309611567904735,
-      "grad_norm": 0.19975155591964722,
+      "grad_norm": 0.20665286481380463,
       "learning_rate": 7.211443451095007e-05,
-      "loss": 10.3772,
+      "loss": 10.3771,
       "step": 19
     },
     {
       "epoch": 0.04536433229373405,
-      "grad_norm": 0.20424290001392365,
+      "grad_norm": 0.21152782440185547,
       "learning_rate": 6.91341716182545e-05,
-      "loss": 10.3748,
+      "loss": 10.3745,
       "step": 20
     },
     {
       "epoch": 0.04763254890842075,
-      "grad_norm": 0.21936988830566406,
+      "grad_norm": 0.22421160340309143,
       "learning_rate": 6.607197326515808e-05,
-      "loss": 10.3752,
+      "loss": 10.3751,
       "step": 21
     },
     {
       "epoch": 0.04990076552310746,
-      "grad_norm": 0.19495096802711487,
+      "grad_norm": 0.19612239301204681,
       "learning_rate": 6.294095225512603e-05,
       "loss": 10.3742,
       "step": 22
     },
     {
       "epoch": 0.05216898213779416,
-      "grad_norm": 0.1962108314037323,
+      "grad_norm": 0.19813410937786102,
       "learning_rate": 5.9754516100806423e-05,
       "loss": 10.3749,
       "step": 23
     },
     {
       "epoch": 0.05443719875248086,
-      "grad_norm": 0.21276497840881348,
+      "grad_norm": 0.20711098611354828,
       "learning_rate": 5.6526309611002594e-05,
-      "loss": 10.3741,
+      "loss": 10.3744,
       "step": 24
     },
     {
       "epoch": 0.05670541536716756,
-      "grad_norm": 0.22711583971977234,
+      "grad_norm": 0.2224423587322235,
       "learning_rate": 5.327015646150716e-05,
-      "loss": 10.3694,
+      "loss": 10.3696,
       "step": 25
     },
     {
       "epoch": 0.05670541536716756,
-      "eval_loss": 10.370012283325195,
-      "eval_runtime": 3.012,
-      "eval_samples_per_second": 986.057,
-      "eval_steps_per_second": 123.506,
+      "eval_loss": 10.369842529296875,
+      "eval_runtime": 3.2494,
+      "eval_samples_per_second": 914.016,
+      "eval_steps_per_second": 114.483,
       "step": 25
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7438df3680029d1b3ebd8cda75f93f924b03e7e0482eee806cb9cb7640a2209c
+oid sha256:7a177b60e693dc813e8f3df7a2d42c94f1117dfde37b89347c189b46762472d4
 size 6776