Training in progress, step 50, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "gate_proj",
     "v_proj",
+    "down_proj",
     "q_proj",
-    "up_proj",
-    "o_proj",
-    "gate_proj",
     "k_proj",
-    "down_proj"
+    "up_proj",
+    "o_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 sha256:7a829be7644d0ec5af406234253c5e8cd38537f14042abbd43de80eb6b503016
+oid sha256:7e5a0b95359ef08bb75ad0c2fa48434aff777e65083a2ce6d910d1f38e9fd3a2
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8b22e8ffa504f140661607dd087d05425ab6ac33e5989fc707f68b47fdc62c3
+oid sha256:43c118531e736264508e1ff932747e9d1f59407b72b9d4e5a789b1ee888d0d95
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74132bf0139d3e5b481fb29b3a85a584240164d592e50763a22e6c2b3a5dbbce
+oid sha256:e8563d054598c7466a892db4bd998a020db56a361014f4e363a1eb9a06268883
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35b9101ba0cbcd853dd8eed444121e7a47b8114b5a4ff4103330049e8a22a651
+oid sha256:99317a4914824202abd1e0aed2608c4375f5054fa89c279a824a669482ad9ece
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b016a48c5eb7ef9d2087cf52f71edd50116978c75a6fe55271bf32d6a4c994dd
+oid sha256:271510b906facb6d3207512c40c2a600a375095ea28b9f83b14efad29ff27eba
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:288cb1f4fdcb08b7226c88c3b3671c1e073a122d22c17562c1a1ada3ef936630
+oid sha256:3c1ccc0d6df59cd5b409c57081c5d5aba71850ff87096eee3081481bd2906ce1
 size 15024

last-checkpoint/scheduler.pt

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

last-checkpoint/trainer_state.json

@@ -1,16 +1,16 @@
 {
-  "best_metric": 0.5865195989608765,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.11299435028248588,
+  "best_metric": 0.47305500507354736,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.22598870056497175,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.004519774011299435,
-      "grad_norm": 8.21904182434082,
+      "grad_norm": 8.245755195617676,
       "learning_rate": 5e-05,
       "loss": 4.4381,
       "step": 1
@@ -18,186 +18,369 @@
     {
       "epoch": 0.004519774011299435,
       "eval_loss": 5.951687812805176,
-      "eval_runtime": 45.6763,
-      "eval_samples_per_second": 32.643,
-      "eval_steps_per_second": 4.094,
+      "eval_runtime": 45.2943,
+      "eval_samples_per_second": 32.918,
+      "eval_steps_per_second": 4.129,
       "step": 1
     },
     {
       "epoch": 0.00903954802259887,
-      "grad_norm": 13.002219200134277,
+      "grad_norm": 13.019776344299316,
       "learning_rate": 0.0001,
       "loss": 5.023,
       "step": 2
     },
     {
       "epoch": 0.013559322033898305,
-      "grad_norm": 10.776192665100098,
+      "grad_norm": 10.667777061462402,
       "learning_rate": 9.989294616193017e-05,
-      "loss": 4.5764,
+      "loss": 4.5686,
       "step": 3
     },
     {
       "epoch": 0.01807909604519774,
-      "grad_norm": 8.736804962158203,
+      "grad_norm": 8.833765029907227,
       "learning_rate": 9.957224306869053e-05,
-      "loss": 2.4086,
+      "loss": 2.4012,
       "step": 4
     },
     {
       "epoch": 0.022598870056497175,
-      "grad_norm": 8.48847770690918,
+      "grad_norm": 8.338103294372559,
       "learning_rate": 9.903926402016153e-05,
-      "loss": 1.912,
+      "loss": 1.897,
       "step": 5
     },
     {
       "epoch": 0.02711864406779661,
-      "grad_norm": 4.094654560089111,
+      "grad_norm": 4.107762336730957,
       "learning_rate": 9.829629131445342e-05,
-      "loss": 1.2446,
+      "loss": 1.2431,
       "step": 6
     },
     {
       "epoch": 0.031638418079096044,
-      "grad_norm": 3.8300228118896484,
+      "grad_norm": 3.792584180831909,
       "learning_rate": 9.73465064747553e-05,
-      "loss": 1.078,
+      "loss": 1.0827,
       "step": 7
     },
     {
       "epoch": 0.03615819209039548,
-      "grad_norm": 3.783612012863159,
+      "grad_norm": 3.8542394638061523,
       "learning_rate": 9.619397662556435e-05,
-      "loss": 0.9286,
+      "loss": 0.9385,
       "step": 8
     },
     {
       "epoch": 0.04067796610169491,
-      "grad_norm": 2.466135025024414,
+      "grad_norm": 2.4101271629333496,
       "learning_rate": 9.484363707663442e-05,
-      "loss": 0.6932,
+      "loss": 0.6988,
       "step": 9
     },
     {
       "epoch": 0.04519774011299435,
-      "grad_norm": 2.876997947692871,
+      "grad_norm": 2.7800371646881104,
       "learning_rate": 9.330127018922194e-05,
-      "loss": 0.689,
+      "loss": 0.6884,
       "step": 10
     },
     {
       "epoch": 0.04971751412429379,
-      "grad_norm": 4.741170406341553,
+      "grad_norm": 4.559901237487793,
       "learning_rate": 9.157348061512727e-05,
-      "loss": 1.017,
+      "loss": 1.0093,
       "step": 11
     },
     {
       "epoch": 0.05423728813559322,
-      "grad_norm": 5.207798957824707,
+      "grad_norm": 5.051866054534912,
       "learning_rate": 8.966766701456177e-05,
-      "loss": 1.227,
+      "loss": 1.2123,
       "step": 12
     },
     {
       "epoch": 0.05875706214689266,
-      "grad_norm": 3.274278163909912,
+      "grad_norm": 3.2915573120117188,
       "learning_rate": 8.759199037394887e-05,
-      "loss": 0.8698,
+      "loss": 0.8697,
       "step": 13
     },
     {
       "epoch": 0.06327683615819209,
-      "grad_norm": 3.666516065597534,
+      "grad_norm": 3.6477880477905273,
       "learning_rate": 8.535533905932738e-05,
-      "loss": 0.6803,
+      "loss": 0.6802,
       "step": 14
     },
     {
       "epoch": 0.06779661016949153,
-      "grad_norm": 3.6715118885040283,
+      "grad_norm": 3.735508918762207,
       "learning_rate": 8.296729075500344e-05,
-      "loss": 0.3187,
+      "loss": 0.3182,
       "step": 15
     },
     {
       "epoch": 0.07231638418079096,
-      "grad_norm": 4.110116958618164,
+      "grad_norm": 4.027164459228516,
       "learning_rate": 8.043807145043604e-05,
-      "loss": 0.4916,
+      "loss": 0.4919,
       "step": 16
     },
     {
       "epoch": 0.0768361581920904,
-      "grad_norm": 3.0237069129943848,
+      "grad_norm": 3.0156490802764893,
       "learning_rate": 7.777851165098012e-05,
-      "loss": 0.472,
+      "loss": 0.4742,
       "step": 17
     },
     {
       "epoch": 0.08135593220338982,
-      "grad_norm": 2.0605337619781494,
+      "grad_norm": 2.0789873600006104,
       "learning_rate": 7.500000000000001e-05,
-      "loss": 0.4241,
+      "loss": 0.4244,
       "step": 18
     },
     {
       "epoch": 0.08587570621468926,
-      "grad_norm": 2.0675086975097656,
+      "grad_norm": 2.032916307449341,
       "learning_rate": 7.211443451095007e-05,
-      "loss": 0.4192,
+      "loss": 0.4205,
       "step": 19
     },
     {
       "epoch": 0.0903954802259887,
-      "grad_norm": 2.2563467025756836,
+      "grad_norm": 2.061422109603882,
       "learning_rate": 6.91341716182545e-05,
-      "loss": 0.5129,
+      "loss": 0.5139,
       "step": 20
     },
     {
       "epoch": 0.09491525423728814,
-      "grad_norm": 1.2747396230697632,
+      "grad_norm": 1.2431901693344116,
       "learning_rate": 6.607197326515808e-05,
-      "loss": 0.3892,
+      "loss": 0.3889,
       "step": 21
     },
     {
       "epoch": 0.09943502824858758,
-      "grad_norm": 1.0977623462677002,
+      "grad_norm": 1.081494927406311,
       "learning_rate": 6.294095225512603e-05,
-      "loss": 0.3669,
+      "loss": 0.3668,
       "step": 22
     },
     {
       "epoch": 0.103954802259887,
-      "grad_norm": 1.2149648666381836,
+      "grad_norm": 1.202134609222412,
       "learning_rate": 5.9754516100806423e-05,
       "loss": 0.4668,
       "step": 23
     },
     {
       "epoch": 0.10847457627118644,
-      "grad_norm": 2.5276224613189697,
+      "grad_norm": 2.6347382068634033,
       "learning_rate": 5.6526309611002594e-05,
-      "loss": 0.7854,
+      "loss": 0.7842,
       "step": 24
     },
     {
       "epoch": 0.11299435028248588,
-      "grad_norm": 3.073773145675659,
+      "grad_norm": 3.069671392440796,
       "learning_rate": 5.327015646150716e-05,
-      "loss": 1.2577,
+      "loss": 1.2538,
       "step": 25
     },
     {
       "epoch": 0.11299435028248588,
-      "eval_loss": 0.5865195989608765,
-      "eval_runtime": 45.7222,
-      "eval_samples_per_second": 32.61,
-      "eval_steps_per_second": 4.09,
+      "eval_loss": 0.5836127400398254,
+      "eval_runtime": 45.3631,
+      "eval_samples_per_second": 32.868,
+      "eval_steps_per_second": 4.122,
       "step": 25
+    },
+    {
+      "epoch": 0.11751412429378531,
+      "grad_norm": 1.8646646738052368,
+      "learning_rate": 5e-05,
+      "loss": 0.3976,
+      "step": 26
+    },
+    {
+      "epoch": 0.12203389830508475,
+      "grad_norm": 2.8463048934936523,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.3272,
+      "step": 27
+    },
+    {
+      "epoch": 0.12655367231638417,
+      "grad_norm": 2.0846760272979736,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.2659,
+      "step": 28
+    },
+    {
+      "epoch": 0.1310734463276836,
+      "grad_norm": 1.9920246601104736,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.3545,
+      "step": 29
+    },
+    {
+      "epoch": 0.13559322033898305,
+      "grad_norm": 1.6598093509674072,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.333,
+      "step": 30
+    },
+    {
+      "epoch": 0.1401129943502825,
+      "grad_norm": 1.9548112154006958,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.3401,
+      "step": 31
+    },
+    {
+      "epoch": 0.14463276836158193,
+      "grad_norm": 1.3660253286361694,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.3923,
+      "step": 32
+    },
+    {
+      "epoch": 0.14915254237288136,
+      "grad_norm": 1.0274734497070312,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.3103,
+      "step": 33
+    },
+    {
+      "epoch": 0.1536723163841808,
+      "grad_norm": 1.0455907583236694,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.3284,
+      "step": 34
+    },
+    {
+      "epoch": 0.15819209039548024,
+      "grad_norm": 1.3953438997268677,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.4766,
+      "step": 35
+    },
+    {
+      "epoch": 0.16271186440677965,
+      "grad_norm": 1.57585871219635,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.6664,
+      "step": 36
+    },
+    {
+      "epoch": 0.1672316384180791,
+      "grad_norm": 2.2962615489959717,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.9099,
+      "step": 37
+    },
+    {
+      "epoch": 0.17175141242937852,
+      "grad_norm": 1.8049850463867188,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.6687,
+      "step": 38
+    },
+    {
+      "epoch": 0.17627118644067796,
+      "grad_norm": 1.97812020778656,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.3072,
+      "step": 39
+    },
+    {
+      "epoch": 0.1807909604519774,
+      "grad_norm": 1.8491371870040894,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.2785,
+      "step": 40
+    },
+    {
+      "epoch": 0.18531073446327684,
+      "grad_norm": 1.9048553705215454,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.2691,
+      "step": 41
+    },
+    {
+      "epoch": 0.18983050847457628,
+      "grad_norm": 1.4539384841918945,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.3034,
+      "step": 42
+    },
+    {
+      "epoch": 0.1943502824858757,
+      "grad_norm": 1.4105565547943115,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.2899,
+      "step": 43
+    },
+    {
+      "epoch": 0.19887005649717515,
+      "grad_norm": 1.3086694478988647,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.2916,
+      "step": 44
+    },
+    {
+      "epoch": 0.2033898305084746,
+      "grad_norm": 1.1233580112457275,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.2939,
+      "step": 45
+    },
+    {
+      "epoch": 0.207909604519774,
+      "grad_norm": 1.1091269254684448,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.3259,
+      "step": 46
+    },
+    {
+      "epoch": 0.21242937853107344,
+      "grad_norm": 0.8711087107658386,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.316,
+      "step": 47
+    },
+    {
+      "epoch": 0.21694915254237288,
+      "grad_norm": 1.4373799562454224,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.6382,
+      "step": 48
+    },
+    {
+      "epoch": 0.2214689265536723,
+      "grad_norm": 2.089608669281006,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.755,
+      "step": 49
+    },
+    {
+      "epoch": 0.22598870056497175,
+      "grad_norm": 2.9072964191436768,
+      "learning_rate": 0.0,
+      "loss": 1.1494,
+      "step": 50
+    },
+    {
+      "epoch": 0.22598870056497175,
+      "eval_loss": 0.47305500507354736,
+      "eval_runtime": 45.3425,
+      "eval_samples_per_second": 32.883,
+      "eval_steps_per_second": 4.124,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.9859068337822106e+17,
+  "total_flos": 5.9736786926882e+17,
   "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:b0afb748b58c0b9ce3e85a2547829320a38677356c8a89e965a722aa1104d447
+oid sha256:5b1ed99eafc3aa4e5c1234fbb3f8fea5495f15776a8fad9e6bcf523c30127ac1
 size 6776