Training in progress, step 50, checkpoint

last-checkpoint/adapter_config.json

@@ -20,11 +20,11 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
     "dense",
+    "fc2",
+    "q_proj",
     "v_proj",
     "k_proj",
-    "fc2",
     "fc1"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c0bff069eccbcc3f252ace5c4116139501f4e6e8ef3fe15020dfea281dc4a02
+oid sha256:37fcd80437072c4a9d5d645a7515b0a3920a8019ed1ad18088bbb863fedeb6ea
 size 237402

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9ef67a92001a8ebc3a739b8d545e5a52e4205d57c8d0a84e1e5c15fba5ebe1b
+oid sha256:cbdf5fffdc9c305ce0eeea2e3f8a4ef7f54d296c32298a2d2dad56e954b01e80
 size 222294

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2a5707a52fe5b5f8b86ab291e3142e958ef7e137e54d9e507371a434e24174a
+oid sha256:76e61ab2bf9e586958859f6421fd73d184220125a752e20b2e4f398d44149919
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c89c7ab52964b97feedfebf9d647c0a6e4f201fa464f763d847bb87132850dd
+oid sha256:081f8e5490e2bdd42269262324fbd7a7aa639bd8462d2209dcc5d43f0a91d8e0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0808f1aef8f8356f326607f1a4813faf2b7d7f3c98ec4cb26d3ef01d511fc82
+oid sha256:5cee113d9e4fc9ed2b02c4749ef8d4ddc70315acb4d1be57fef1fe6747c3113e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68800ef5e3fd2426a85a7e0e349f1d736fa92dcec6f0c9d73e1fcdfa605b8f16
+oid sha256:100f0aa0a28d9b7b5cca0864b7cb5d70edd4d5e3d4e1a317610f9ee5e85da24b
 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

@@ -1,203 +1,386 @@
 {
-  "best_metric": 6.907079696655273,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.1764705882352942,
+  "best_metric": 6.901896953582764,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.3529411764705883,
   "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": 0.047058823529411764,
-      "grad_norm": 0.2197900116443634,
+      "grad_norm": 0.21819724142551422,
       "learning_rate": 5e-05,
       "loss": 6.9356,
       "step": 1
     },
     {
       "epoch": 0.047058823529411764,
-      "eval_loss": 6.93379020690918,
-      "eval_runtime": 0.1173,
-      "eval_samples_per_second": 1227.778,
-      "eval_steps_per_second": 153.472,
+      "eval_loss": 6.933749675750732,
+      "eval_runtime": 0.1253,
+      "eval_samples_per_second": 1149.197,
+      "eval_steps_per_second": 143.65,
       "step": 1
     },
     {
       "epoch": 0.09411764705882353,
-      "grad_norm": 0.23598474264144897,
+      "grad_norm": 0.23392507433891296,
       "learning_rate": 0.0001,
       "loss": 6.9345,
       "step": 2
     },
     {
       "epoch": 0.1411764705882353,
-      "grad_norm": 0.22106465697288513,
+      "grad_norm": 0.21760986745357513,
       "learning_rate": 9.989294616193017e-05,
       "loss": 6.9338,
       "step": 3
     },
     {
       "epoch": 0.18823529411764706,
-      "grad_norm": 0.2562369108200073,
+      "grad_norm": 0.2519800364971161,
       "learning_rate": 9.957224306869053e-05,
       "loss": 6.9328,
       "step": 4
     },
     {
       "epoch": 0.23529411764705882,
-      "grad_norm": 0.27944687008857727,
+      "grad_norm": 0.2736882269382477,
       "learning_rate": 9.903926402016153e-05,
-      "loss": 6.9285,
+      "loss": 6.9286,
       "step": 5
     },
     {
       "epoch": 0.2823529411764706,
-      "grad_norm": 0.2180635929107666,
+      "grad_norm": 0.21310661733150482,
       "learning_rate": 9.829629131445342e-05,
       "loss": 6.9316,
       "step": 6
     },
     {
       "epoch": 0.32941176470588235,
-      "grad_norm": 0.21152342855930328,
+      "grad_norm": 0.20439282059669495,
       "learning_rate": 9.73465064747553e-05,
-      "loss": 6.9271,
+      "loss": 6.9272,
       "step": 7
     },
     {
       "epoch": 0.3764705882352941,
-      "grad_norm": 0.23825813829898834,
+      "grad_norm": 0.23206020891666412,
       "learning_rate": 9.619397662556435e-05,
-      "loss": 6.9263,
+      "loss": 6.9267,
       "step": 8
     },
     {
       "epoch": 0.4235294117647059,
-      "grad_norm": 0.24669218063354492,
+      "grad_norm": 0.23456871509552002,
       "learning_rate": 9.484363707663442e-05,
-      "loss": 6.9238,
+      "loss": 6.9244,
       "step": 9
     },
     {
       "epoch": 0.47058823529411764,
-      "grad_norm": 0.259551465511322,
+      "grad_norm": 0.24816955626010895,
       "learning_rate": 9.330127018922194e-05,
-      "loss": 6.9223,
+      "loss": 6.9231,
       "step": 10
     },
     {
       "epoch": 0.5176470588235295,
-      "grad_norm": 0.23696023225784302,
+      "grad_norm": 0.22822989523410797,
       "learning_rate": 9.157348061512727e-05,
-      "loss": 6.9223,
+      "loss": 6.9228,
       "step": 11
     },
     {
       "epoch": 0.5647058823529412,
-      "grad_norm": 0.2057735174894333,
+      "grad_norm": 0.1995086669921875,
       "learning_rate": 8.966766701456177e-05,
-      "loss": 6.9238,
+      "loss": 6.9243,
       "step": 12
     },
     {
       "epoch": 0.611764705882353,
-      "grad_norm": 0.23521941900253296,
+      "grad_norm": 0.22449171543121338,
       "learning_rate": 8.759199037394887e-05,
-      "loss": 6.9205,
+      "loss": 6.9212,
       "step": 13
     },
     {
       "epoch": 0.6588235294117647,
-      "grad_norm": 0.26085859537124634,
+      "grad_norm": 0.2463487982749939,
       "learning_rate": 8.535533905932738e-05,
-      "loss": 6.9158,
+      "loss": 6.917,
       "step": 14
     },
     {
       "epoch": 0.7058823529411765,
-      "grad_norm": 0.2542021572589874,
+      "grad_norm": 0.23512305319309235,
       "learning_rate": 8.296729075500344e-05,
-      "loss": 6.9166,
+      "loss": 6.9182,
       "step": 15
     },
     {
       "epoch": 0.7529411764705882,
-      "grad_norm": 0.26281988620758057,
+      "grad_norm": 0.24918068945407867,
       "learning_rate": 8.043807145043604e-05,
-      "loss": 6.9112,
+      "loss": 6.9125,
       "step": 16
     },
     {
       "epoch": 0.8,
-      "grad_norm": 0.20492899417877197,
+      "grad_norm": 0.19672776758670807,
       "learning_rate": 7.777851165098012e-05,
-      "loss": 6.9214,
+      "loss": 6.922,
       "step": 17
     },
     {
       "epoch": 0.8470588235294118,
-      "grad_norm": 0.2326112985610962,
+      "grad_norm": 0.22348777949810028,
       "learning_rate": 7.500000000000001e-05,
-      "loss": 6.9162,
+      "loss": 6.917,
       "step": 18
     },
     {
       "epoch": 0.8941176470588236,
-      "grad_norm": 0.25904643535614014,
+      "grad_norm": 0.24797621369361877,
       "learning_rate": 7.211443451095007e-05,
-      "loss": 6.9117,
+      "loss": 6.9131,
       "step": 19
     },
     {
       "epoch": 0.9411764705882353,
-      "grad_norm": 0.28032180666923523,
+      "grad_norm": 0.2576676607131958,
       "learning_rate": 6.91341716182545e-05,
-      "loss": 6.9061,
+      "loss": 6.9083,
       "step": 20
     },
     {
       "epoch": 0.9882352941176471,
-      "grad_norm": 0.2956153154373169,
+      "grad_norm": 0.2767176330089569,
       "learning_rate": 6.607197326515808e-05,
-      "loss": 6.9017,
+      "loss": 6.9037,
       "step": 21
     },
     {
       "epoch": 1.035294117647059,
-      "grad_norm": 0.43831008672714233,
+      "grad_norm": 0.41804033517837524,
       "learning_rate": 6.294095225512603e-05,
-      "loss": 12.1913,
+      "loss": 12.1933,
       "step": 22
     },
     {
       "epoch": 1.0823529411764705,
-      "grad_norm": 0.24661988019943237,
+      "grad_norm": 0.23595315217971802,
       "learning_rate": 5.9754516100806423e-05,
-      "loss": 6.7906,
+      "loss": 6.7918,
       "step": 23
     },
     {
       "epoch": 1.1294117647058823,
-      "grad_norm": 0.26080018281936646,
+      "grad_norm": 0.2416248470544815,
       "learning_rate": 5.6526309611002594e-05,
-      "loss": 6.9653,
+      "loss": 6.9668,
       "step": 24
     },
     {
       "epoch": 1.1764705882352942,
-      "grad_norm": 0.29405051469802856,
+      "grad_norm": 0.27485209703445435,
       "learning_rate": 5.327015646150716e-05,
-      "loss": 6.7342,
+      "loss": 6.7366,
       "step": 25
     },
     {
       "epoch": 1.1764705882352942,
-      "eval_loss": 6.907079696655273,
-      "eval_runtime": 0.1147,
-      "eval_samples_per_second": 1255.072,
-      "eval_steps_per_second": 156.884,
+      "eval_loss": 6.90932035446167,
+      "eval_runtime": 0.1329,
+      "eval_samples_per_second": 1083.523,
+      "eval_steps_per_second": 135.44,
       "step": 25
+    },
+    {
+      "epoch": 1.223529411764706,
+      "grad_norm": 0.28666388988494873,
+      "learning_rate": 5e-05,
+      "loss": 7.1573,
+      "step": 26
+    },
+    {
+      "epoch": 1.2705882352941176,
+      "grad_norm": 0.2689034640789032,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 6.7631,
+      "step": 27
+    },
+    {
+      "epoch": 1.3176470588235294,
+      "grad_norm": 0.2453760802745819,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 6.9962,
+      "step": 28
+    },
+    {
+      "epoch": 1.3647058823529412,
+      "grad_norm": 0.2651669979095459,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 6.9206,
+      "step": 29
+    },
+    {
+      "epoch": 1.4117647058823528,
+      "grad_norm": 0.2966490685939789,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 6.9026,
+      "step": 30
+    },
+    {
+      "epoch": 1.4588235294117646,
+      "grad_norm": 0.2592300474643707,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 6.9306,
+      "step": 31
+    },
+    {
+      "epoch": 1.5058823529411764,
+      "grad_norm": 0.29443129897117615,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 6.6774,
+      "step": 32
+    },
+    {
+      "epoch": 1.5529411764705883,
+      "grad_norm": 0.22758440673351288,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 7.078,
+      "step": 33
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.25598350167274475,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 6.8498,
+      "step": 34
+    },
+    {
+      "epoch": 1.6470588235294117,
+      "grad_norm": 0.2687520980834961,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 7.0786,
+      "step": 35
+    },
+    {
+      "epoch": 1.6941176470588235,
+      "grad_norm": 0.27907800674438477,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 6.7001,
+      "step": 36
+    },
+    {
+      "epoch": 1.7411764705882353,
+      "grad_norm": 0.272887647151947,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 6.7109,
+      "step": 37
+    },
+    {
+      "epoch": 1.788235294117647,
+      "grad_norm": 0.2443215399980545,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 7.2548,
+      "step": 38
+    },
+    {
+      "epoch": 1.835294117647059,
+      "grad_norm": 0.2575581669807434,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 6.8001,
+      "step": 39
+    },
+    {
+      "epoch": 1.8823529411764706,
+      "grad_norm": 0.2523963451385498,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 6.9903,
+      "step": 40
+    },
+    {
+      "epoch": 1.9294117647058824,
+      "grad_norm": 0.2883269786834717,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 6.7648,
+      "step": 41
+    },
+    {
+      "epoch": 1.9764705882352942,
+      "grad_norm": 0.27604395151138306,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 7.0528,
+      "step": 42
+    },
+    {
+      "epoch": 2.023529411764706,
+      "grad_norm": 0.44379091262817383,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 11.9826,
+      "step": 43
+    },
+    {
+      "epoch": 2.070588235294118,
+      "grad_norm": 0.2380973845720291,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 7.017,
+      "step": 44
+    },
+    {
+      "epoch": 2.1176470588235294,
+      "grad_norm": 0.22482647001743317,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 6.7619,
+      "step": 45
+    },
+    {
+      "epoch": 2.164705882352941,
+      "grad_norm": 0.23828120529651642,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 6.8802,
+      "step": 46
+    },
+    {
+      "epoch": 2.211764705882353,
+      "grad_norm": 0.2840559780597687,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 6.9007,
+      "step": 47
+    },
+    {
+      "epoch": 2.2588235294117647,
+      "grad_norm": 0.25946393609046936,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 6.7099,
+      "step": 48
+    },
+    {
+      "epoch": 2.3058823529411763,
+      "grad_norm": 0.22958962619304657,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 7.1588,
+      "step": 49
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "grad_norm": 0.23301947116851807,
+      "learning_rate": 0.0,
+      "loss": 6.9713,
+      "step": 50
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "eval_loss": 6.901896953582764,
+      "eval_runtime": 0.1267,
+      "eval_samples_per_second": 1136.61,
+      "eval_steps_per_second": 142.076,
+      "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": 2920736931840.0,
+  "total_flos": 5830775193600.0,
   "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 sha256:2f84aa723924298c428cfc079f9bc73e01baed2fb1275230b50fa001c00d4943
+oid sha256:ac40a2a8dba01c5dfec735379b0d6aaafc1124d9f51e774c8273efc8e6fc7714
 size 6776