Training in progress, step 25, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "up_proj",
+    "q_proj",
+    "gate_proj",
     "o_proj",
     "down_proj",
-    "gate_proj",
-    "k_proj",
-    "up_proj",
     "v_proj",
-    "q_proj"
+    "k_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:dca099686a593bcd03c2b57fa38b6a9fa460b533dd8ff5ee9ef475c9ea1dbabf
+oid sha256:0aecb923fb0e532c6129fae6d8d65b0e42c75564a2ef3e2534b3007cc79cd758
 size 859909312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0eea0ba8198ea197447508a529936dd59bfc6916901c2ffd24d380d7eabdf074
+oid sha256:8963bcee51704fc930d5ee8cba7fccbebb9e7ee3bbbf1fbcc54ebbaad4746fe4
 size 671466706

last-checkpoint/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 1.7508697509765625,
+  "best_metric": 1.753453016281128,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
   "epoch": 0.02689437235258522,
   "eval_steps": 25,
@@ -10,193 +10,193 @@
   "log_history": [
     {
       "epoch": 0.0010757748941034088,
-      "grad_norm": 1.6709057092666626,
+      "grad_norm": 2.889035224914551,
       "learning_rate": 5e-05,
-      "loss": 1.707,
+      "loss": 1.7307,
       "step": 1
     },
     {
       "epoch": 0.0010757748941034088,
-      "eval_loss": 2.019153356552124,
-      "eval_runtime": 186.2275,
-      "eval_samples_per_second": 33.631,
-      "eval_steps_per_second": 4.205,
+      "eval_loss": 2.065730094909668,
+      "eval_runtime": 186.3032,
+      "eval_samples_per_second": 33.617,
+      "eval_steps_per_second": 4.203,
       "step": 1
     },
     {
       "epoch": 0.0021515497882068175,
-      "grad_norm": 1.8899304866790771,
+      "grad_norm": 2.8928565979003906,
       "learning_rate": 0.0001,
-      "loss": 1.8408,
+      "loss": 1.8653,
       "step": 2
     },
     {
       "epoch": 0.0032273246823102267,
-      "grad_norm": 1.4666272401809692,
+      "grad_norm": 1.6839524507522583,
       "learning_rate": 9.989294616193017e-05,
-      "loss": 1.7696,
+      "loss": 1.756,
       "step": 3
     },
     {
       "epoch": 0.004303099576413635,
-      "grad_norm": 0.9372745752334595,
+      "grad_norm": 0.8242851495742798,
       "learning_rate": 9.957224306869053e-05,
-      "loss": 1.7414,
+      "loss": 1.7457,
       "step": 4
     },
     {
       "epoch": 0.005378874470517044,
-      "grad_norm": 0.8082295656204224,
+      "grad_norm": 1.0334848165512085,
       "learning_rate": 9.903926402016153e-05,
-      "loss": 1.7415,
+      "loss": 1.7532,
       "step": 5
     },
     {
       "epoch": 0.006454649364620453,
-      "grad_norm": 0.9279489517211914,
+      "grad_norm": 0.7117134928703308,
       "learning_rate": 9.829629131445342e-05,
-      "loss": 1.7757,
+      "loss": 1.7827,
       "step": 6
     },
     {
       "epoch": 0.007530424258723862,
-      "grad_norm": 0.701418936252594,
+      "grad_norm": 0.7202480435371399,
       "learning_rate": 9.73465064747553e-05,
-      "loss": 1.8196,
+      "loss": 1.8289,
       "step": 7
     },
     {
       "epoch": 0.00860619915282727,
-      "grad_norm": 0.688548743724823,
+      "grad_norm": 0.6732454299926758,
       "learning_rate": 9.619397662556435e-05,
-      "loss": 1.7341,
+      "loss": 1.7357,
       "step": 8
     },
     {
       "epoch": 0.00968197404693068,
-      "grad_norm": 0.6612863540649414,
+      "grad_norm": 0.6462610960006714,
       "learning_rate": 9.484363707663442e-05,
-      "loss": 1.7848,
+      "loss": 1.7847,
       "step": 9
     },
     {
       "epoch": 0.010757748941034088,
-      "grad_norm": 0.6995035409927368,
+      "grad_norm": 0.7184572815895081,
       "learning_rate": 9.330127018922194e-05,
-      "loss": 1.8447,
+      "loss": 1.8445,
       "step": 10
     },
     {
       "epoch": 0.011833523835137498,
-      "grad_norm": 0.7706447243690491,
+      "grad_norm": 0.7928162813186646,
       "learning_rate": 9.157348061512727e-05,
-      "loss": 1.8312,
+      "loss": 1.8327,
       "step": 11
     },
     {
       "epoch": 0.012909298729240907,
-      "grad_norm": 0.9608161449432373,
+      "grad_norm": 0.9331445693969727,
       "learning_rate": 8.966766701456177e-05,
-      "loss": 2.0029,
+      "loss": 2.0023,
       "step": 12
     },
     {
       "epoch": 0.013985073623344316,
-      "grad_norm": 1.8199213743209839,
+      "grad_norm": 1.8583245277404785,
       "learning_rate": 8.759199037394887e-05,
-      "loss": 1.6517,
+      "loss": 1.6557,
       "step": 13
     },
     {
       "epoch": 0.015060848517447724,
-      "grad_norm": 1.3464016914367676,
+      "grad_norm": 1.4030020236968994,
       "learning_rate": 8.535533905932738e-05,
-      "loss": 1.6332,
+      "loss": 1.6399,
       "step": 14
     },
     {
       "epoch": 0.016136623411551133,
-      "grad_norm": 0.96041339635849,
+      "grad_norm": 1.2228798866271973,
       "learning_rate": 8.296729075500344e-05,
-      "loss": 1.6261,
+      "loss": 1.637,
       "step": 15
     },
     {
       "epoch": 0.01721239830565454,
-      "grad_norm": 0.7431668043136597,
+      "grad_norm": 0.8515083193778992,
       "learning_rate": 8.043807145043604e-05,
-      "loss": 1.6273,
+      "loss": 1.6325,
       "step": 16
     },
     {
       "epoch": 0.01828817319975795,
-      "grad_norm": 0.560585618019104,
+      "grad_norm": 0.6020737290382385,
       "learning_rate": 7.777851165098012e-05,
-      "loss": 1.6822,
+      "loss": 1.6861,
       "step": 17
     },
     {
       "epoch": 0.01936394809386136,
-      "grad_norm": 0.5964136123657227,
+      "grad_norm": 0.658804714679718,
       "learning_rate": 7.500000000000001e-05,
-      "loss": 1.7219,
+      "loss": 1.7261,
       "step": 18
     },
     {
       "epoch": 0.02043972298796477,
-      "grad_norm": 0.6002236604690552,
+      "grad_norm": 0.6308284997940063,
       "learning_rate": 7.211443451095007e-05,
-      "loss": 1.7398,
+      "loss": 1.7423,
       "step": 19
     },
     {
       "epoch": 0.021515497882068177,
-      "grad_norm": 0.6054794788360596,
+      "grad_norm": 0.6279967427253723,
       "learning_rate": 6.91341716182545e-05,
-      "loss": 1.778,
+      "loss": 1.7781,
       "step": 20
     },
     {
       "epoch": 0.022591272776171584,
-      "grad_norm": 0.6320491433143616,
+      "grad_norm": 0.6446429491043091,
       "learning_rate": 6.607197326515808e-05,
-      "loss": 1.7474,
+      "loss": 1.747,
       "step": 21
     },
     {
       "epoch": 0.023667047670274995,
-      "grad_norm": 0.6241698265075684,
+      "grad_norm": 0.6265982985496521,
       "learning_rate": 6.294095225512603e-05,
-      "loss": 1.8189,
+      "loss": 1.8178,
       "step": 22
     },
     {
       "epoch": 0.024742822564378403,
-      "grad_norm": 0.7055386304855347,
+      "grad_norm": 0.695231556892395,
       "learning_rate": 5.9754516100806423e-05,
-      "loss": 1.7957,
+      "loss": 1.7954,
       "step": 23
     },
     {
       "epoch": 0.025818597458481814,
-      "grad_norm": 0.8027210235595703,
+      "grad_norm": 0.7961277365684509,
       "learning_rate": 5.6526309611002594e-05,
-      "loss": 1.9507,
+      "loss": 1.9499,
       "step": 24
     },
     {
       "epoch": 0.02689437235258522,
-      "grad_norm": 1.0420467853546143,
+      "grad_norm": 1.026402235031128,
       "learning_rate": 5.327015646150716e-05,
-      "loss": 2.1519,
+      "loss": 2.1511,
       "step": 25
     },
     {
       "epoch": 0.02689437235258522,
-      "eval_loss": 1.7508697509765625,
-      "eval_runtime": 186.2853,
-      "eval_samples_per_second": 33.62,
-      "eval_steps_per_second": 4.203,
+      "eval_loss": 1.753453016281128,
+      "eval_runtime": 186.4029,
+      "eval_samples_per_second": 33.599,
+      "eval_steps_per_second": 4.201,
       "step": 25
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:987fd07a10c7dc3d0202f3fd844ca5c32e5eda76cf15397ae30934c49a3acd1e
+oid sha256:cde298347aefb5569ecda1d0ffbfc1f74fe5a8aad71a508769958efdcaf21bdf
 size 6776