Training in progress, step 25, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
     "up_proj",
+    "o_proj",
     "k_proj",
-    "q_proj",
-    "down_proj",
+    "gate_proj",
     "v_proj",
-    "gate_proj"
+    "down_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:f66cc7c9356f946f1cecb4e5eed0f69b9df6eeebe213ff2a442450cf672e57b1
+oid sha256:76de05868119282f294c4308e929d8fa397ec95c43bc7f58c1ae41679447a18c
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb379e2cbab516fd19e8398b965ea61ca3bf59818ec77fd66eefda96a999d3fc
+oid sha256:5ab42fb37e0f6cb0b7d3950ebd7defaf7f347e00dee828de8975012f6a8142a5
 size 141053442

last-checkpoint/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 3.267420530319214,
+  "best_metric": 3.268176555633545,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
   "epoch": 0.09918175055789735,
   "eval_steps": 25,
@@ -10,7 +10,7 @@
   "log_history": [
     {
       "epoch": 0.003967270022315894,
-      "grad_norm": 0.8241645097732544,
+      "grad_norm": 0.8100353479385376,
       "learning_rate": 5e-05,
       "loss": 3.4866,
       "step": 1
@@ -18,185 +18,185 @@
     {
       "epoch": 0.003967270022315894,
       "eval_loss": 3.7426881790161133,
-      "eval_runtime": 11.7309,
-      "eval_samples_per_second": 144.831,
-      "eval_steps_per_second": 18.157,
+      "eval_runtime": 11.5565,
+      "eval_samples_per_second": 147.016,
+      "eval_steps_per_second": 18.431,
       "step": 1
     },
     {
       "epoch": 0.007934540044631788,
-      "grad_norm": 0.8499454855918884,
+      "grad_norm": 0.8411345481872559,
       "learning_rate": 0.0001,
       "loss": 3.4657,
       "step": 2
     },
     {
       "epoch": 0.011901810066947682,
-      "grad_norm": 0.9072771072387695,
+      "grad_norm": 0.9052443504333496,
       "learning_rate": 9.989294616193017e-05,
-      "loss": 3.5394,
+      "loss": 3.5402,
       "step": 3
     },
     {
       "epoch": 0.015869080089263576,
-      "grad_norm": 0.7632107138633728,
+      "grad_norm": 0.7589433789253235,
       "learning_rate": 9.957224306869053e-05,
-      "loss": 3.4564,
+      "loss": 3.4572,
       "step": 4
     },
     {
       "epoch": 0.01983635011157947,
-      "grad_norm": 0.8594216704368591,
+      "grad_norm": 0.8587386608123779,
       "learning_rate": 9.903926402016153e-05,
-      "loss": 3.5266,
+      "loss": 3.5274,
       "step": 5
     },
     {
       "epoch": 0.023803620133895365,
-      "grad_norm": 0.9645074009895325,
+      "grad_norm": 0.9426459074020386,
       "learning_rate": 9.829629131445342e-05,
-      "loss": 3.512,
+      "loss": 3.5125,
       "step": 6
     },
     {
       "epoch": 0.02777089015621126,
-      "grad_norm": 0.9713271260261536,
+      "grad_norm": 0.9467688798904419,
       "learning_rate": 9.73465064747553e-05,
-      "loss": 3.5646,
+      "loss": 3.5663,
       "step": 7
     },
     {
       "epoch": 0.03173816017852715,
-      "grad_norm": 1.0277541875839233,
+      "grad_norm": 1.0104401111602783,
       "learning_rate": 9.619397662556435e-05,
-      "loss": 3.4512,
+      "loss": 3.4531,
       "step": 8
     },
     {
       "epoch": 0.03570543020084305,
-      "grad_norm": 1.0516093969345093,
+      "grad_norm": 1.0469218492507935,
       "learning_rate": 9.484363707663442e-05,
-      "loss": 3.4789,
+      "loss": 3.4803,
       "step": 9
     },
     {
       "epoch": 0.03967270022315894,
-      "grad_norm": 1.1022090911865234,
+      "grad_norm": 1.096985936164856,
       "learning_rate": 9.330127018922194e-05,
-      "loss": 3.5343,
+      "loss": 3.5365,
       "step": 10
     },
     {
       "epoch": 0.043639970245474835,
-      "grad_norm": 1.0738914012908936,
+      "grad_norm": 1.0697236061096191,
       "learning_rate": 9.157348061512727e-05,
-      "loss": 3.5085,
+      "loss": 3.5104,
       "step": 11
     },
     {
       "epoch": 0.04760724026779073,
-      "grad_norm": 1.1916122436523438,
+      "grad_norm": 1.215027928352356,
       "learning_rate": 8.966766701456177e-05,
-      "loss": 3.4677,
+      "loss": 3.472,
       "step": 12
     },
     {
       "epoch": 0.05157451029010662,
-      "grad_norm": 1.1183475255966187,
+      "grad_norm": 1.1256529092788696,
       "learning_rate": 8.759199037394887e-05,
-      "loss": 3.4107,
+      "loss": 3.4123,
       "step": 13
     },
     {
       "epoch": 0.05554178031242252,
-      "grad_norm": 1.0498988628387451,
+      "grad_norm": 1.0637106895446777,
       "learning_rate": 8.535533905932738e-05,
-      "loss": 3.3009,
+      "loss": 3.3022,
       "step": 14
     },
     {
       "epoch": 0.05950905033473841,
-      "grad_norm": 1.125704288482666,
+      "grad_norm": 1.1305065155029297,
       "learning_rate": 8.296729075500344e-05,
-      "loss": 3.332,
+      "loss": 3.3346,
       "step": 15
     },
     {
       "epoch": 0.0634763203570543,
-      "grad_norm": 0.8547013998031616,
+      "grad_norm": 0.8763689994812012,
       "learning_rate": 8.043807145043604e-05,
-      "loss": 3.2555,
+      "loss": 3.2566,
       "step": 16
     },
     {
       "epoch": 0.0674435903793702,
-      "grad_norm": 0.7742959260940552,
+      "grad_norm": 0.7871897220611572,
       "learning_rate": 7.777851165098012e-05,
-      "loss": 3.3036,
+      "loss": 3.3037,
       "step": 17
     },
     {
       "epoch": 0.0714108604016861,
-      "grad_norm": 0.8887235522270203,
+      "grad_norm": 0.8707305192947388,
       "learning_rate": 7.500000000000001e-05,
-      "loss": 3.3385,
+      "loss": 3.3393,
       "step": 18
     },
     {
       "epoch": 0.07537813042400199,
-      "grad_norm": 0.8906424641609192,
+      "grad_norm": 0.8883684873580933,
       "learning_rate": 7.211443451095007e-05,
-      "loss": 3.2767,
+      "loss": 3.2778,
       "step": 19
     },
     {
       "epoch": 0.07934540044631788,
-      "grad_norm": 1.0381428003311157,
+      "grad_norm": 1.0402384996414185,
       "learning_rate": 6.91341716182545e-05,
-      "loss": 3.2897,
+      "loss": 3.2926,
       "step": 20
     },
     {
       "epoch": 0.08331267046863378,
-      "grad_norm": 1.2209287881851196,
+      "grad_norm": 1.2061767578125,
       "learning_rate": 6.607197326515808e-05,
-      "loss": 3.4663,
+      "loss": 3.4678,
       "step": 21
     },
     {
       "epoch": 0.08727994049094967,
-      "grad_norm": 1.1723295450210571,
+      "grad_norm": 1.1715914011001587,
       "learning_rate": 6.294095225512603e-05,
-      "loss": 3.3431,
+      "loss": 3.3448,
       "step": 22
     },
     {
       "epoch": 0.09124721051326556,
-      "grad_norm": 1.0842334032058716,
+      "grad_norm": 1.2525004148483276,
       "learning_rate": 5.9754516100806423e-05,
-      "loss": 3.314,
+      "loss": 3.3168,
       "step": 23
     },
     {
       "epoch": 0.09521448053558146,
-      "grad_norm": 1.0503602027893066,
+      "grad_norm": 1.1802704334259033,
       "learning_rate": 5.6526309611002594e-05,
-      "loss": 3.2195,
+      "loss": 3.2211,
       "step": 24
     },
     {
       "epoch": 0.09918175055789735,
-      "grad_norm": 1.2791979312896729,
+      "grad_norm": 1.308222770690918,
       "learning_rate": 5.327015646150716e-05,
-      "loss": 3.2802,
+      "loss": 3.2855,
       "step": 25
     },
     {
       "epoch": 0.09918175055789735,
-      "eval_loss": 3.267420530319214,
-      "eval_runtime": 11.7144,
-      "eval_samples_per_second": 145.035,
-      "eval_steps_per_second": 18.183,
+      "eval_loss": 3.268176555633545,
+      "eval_runtime": 11.5559,
+      "eval_samples_per_second": 147.024,
+      "eval_steps_per_second": 18.432,
       "step": 25
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41423001aa5ceb2d23235d9dee62fad89e061cbc43f5e3a09904fb106ff3b870
+oid sha256:870dfab1563a1ea9b9c6847f153d550987da1ab2c43fc66f0f15ea702901d060
 size 6776