Training in progress, step 50, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "o_proj",
+    "gate_proj",
     "up_proj",
+    "v_proj",
     "down_proj",
-    "o_proj",
     "k_proj",
-    "q_proj",
-    "gate_proj",
-    "v_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 sha256:7d33328486c0c790a2b2f71e30b319fe03bc029fe847e7337c9281d90e77ad09
+oid sha256:1d3d8d9a3a0f44ae4040f21527eb964f8d6315ab5bba51e7e24d37d6a3bec0ee
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cb0496a8361bb87e84f9764b68231d32cd92ac3283e08fb926c5bf5740a5143
+oid sha256:974c09014133cee91e9cf291a8b4c4e9d74b800563037fba27cef9b5f9ef543d
 size 113994

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:788b9590928f2382b594e5175a4b13c7449d30c5a69db4c6188c004e6d36ad65
-size 14960
+oid sha256:b539fa5b0bccdf4b05a6d43118df02a5b8d4ca2672eaa1d4550a5a39c893cc90
+size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7bd295bb9eb2b4447feb8e88034e07dec714797cb0c938948724e55ce978154
+oid sha256:5bf979eb34032480c1694be2dd61219a9a8c1213fcec198ecf671580a91b7dd8
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4cbd9a4f3c2ffff8ab81ca8194a07a4515433be3cf91c11ff795c788e91e80b
+oid sha256:8ecf1cd84eca1c5cf716bdedbc75b082bfe1e3293d02e6edaa7e836c98f4de2b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:776f157b9782b4dcf5d918131ef5313c31323c3735df0e9390d199135423c0bc
+oid sha256:6dce7b4ffbc54485b37f3d6968e739c4a4668585da5bf3d1862f61e568f8c490
 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": 11.914839744567871,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.1145475372279496,
+  "best_metric": 11.911612510681152,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.2290950744558992,
   "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": 0.004581901489117984,
-      "grad_norm": 0.07584026455879211,
+      "grad_norm": 0.07477667927742004,
       "learning_rate": 5e-05,
       "loss": 11.9187,
       "step": 1
@@ -18,186 +18,369 @@
     {
       "epoch": 0.004581901489117984,
       "eval_loss": 11.921486854553223,
-      "eval_runtime": 2.8768,
-      "eval_samples_per_second": 510.988,
-      "eval_steps_per_second": 63.96,
+      "eval_runtime": 3.0089,
+      "eval_samples_per_second": 488.552,
+      "eval_steps_per_second": 61.152,
       "step": 1
     },
     {
       "epoch": 0.009163802978235968,
-      "grad_norm": 0.0752248540520668,
+      "grad_norm": 0.07550952583551407,
       "learning_rate": 0.0001,
       "loss": 11.9227,
       "step": 2
     },
     {
       "epoch": 0.013745704467353952,
-      "grad_norm": 0.07713150978088379,
+      "grad_norm": 0.07710909843444824,
       "learning_rate": 9.989294616193017e-05,
       "loss": 11.9223,
       "step": 3
     },
     {
       "epoch": 0.018327605956471937,
-      "grad_norm": 0.07691174745559692,
+      "grad_norm": 0.07666952162981033,
       "learning_rate": 9.957224306869053e-05,
       "loss": 11.9244,
       "step": 4
     },
     {
       "epoch": 0.022909507445589918,
-      "grad_norm": 0.08752486854791641,
+      "grad_norm": 0.08762763440608978,
       "learning_rate": 9.903926402016153e-05,
       "loss": 11.9218,
       "step": 5
     },
     {
       "epoch": 0.027491408934707903,
-      "grad_norm": 0.0786953940987587,
+      "grad_norm": 0.07745254784822464,
       "learning_rate": 9.829629131445342e-05,
-      "loss": 11.9259,
+      "loss": 11.9258,
       "step": 6
     },
     {
       "epoch": 0.032073310423825885,
-      "grad_norm": 0.08299648016691208,
+      "grad_norm": 0.08356379717588425,
       "learning_rate": 9.73465064747553e-05,
       "loss": 11.9239,
       "step": 7
     },
     {
       "epoch": 0.03665521191294387,
-      "grad_norm": 0.09089986234903336,
+      "grad_norm": 0.09062787890434265,
       "learning_rate": 9.619397662556435e-05,
-      "loss": 11.9184,
+      "loss": 11.9183,
       "step": 8
     },
     {
       "epoch": 0.041237113402061855,
-      "grad_norm": 0.09789414703845978,
+      "grad_norm": 0.10249368101358414,
       "learning_rate": 9.484363707663442e-05,
-      "loss": 11.9226,
+      "loss": 11.9225,
       "step": 9
     },
     {
       "epoch": 0.045819014891179836,
-      "grad_norm": 0.0758046805858612,
+      "grad_norm": 0.07912520319223404,
       "learning_rate": 9.330127018922194e-05,
-      "loss": 11.9194,
+      "loss": 11.9193,
       "step": 10
     },
     {
       "epoch": 0.050400916380297825,
-      "grad_norm": 0.11443702131509781,
+      "grad_norm": 0.11746184527873993,
       "learning_rate": 9.157348061512727e-05,
-      "loss": 11.9188,
+      "loss": 11.9186,
       "step": 11
     },
     {
       "epoch": 0.054982817869415807,
-      "grad_norm": 0.1439603716135025,
+      "grad_norm": 0.1475147157907486,
       "learning_rate": 8.966766701456177e-05,
-      "loss": 11.9181,
+      "loss": 11.9178,
       "step": 12
     },
     {
       "epoch": 0.05956471935853379,
-      "grad_norm": 0.12971708178520203,
+      "grad_norm": 0.13204821944236755,
       "learning_rate": 8.759199037394887e-05,
-      "loss": 11.9198,
+      "loss": 11.9195,
       "step": 13
     },
     {
       "epoch": 0.06414662084765177,
-      "grad_norm": 0.12059250473976135,
+      "grad_norm": 0.11282403767108917,
       "learning_rate": 8.535533905932738e-05,
-      "loss": 11.9241,
+      "loss": 11.924,
       "step": 14
     },
     {
       "epoch": 0.06872852233676977,
-      "grad_norm": 0.11569193750619888,
+      "grad_norm": 0.10892879962921143,
       "learning_rate": 8.296729075500344e-05,
       "loss": 11.9231,
       "step": 15
     },
     {
       "epoch": 0.07331042382588775,
-      "grad_norm": 0.11735488474369049,
+      "grad_norm": 0.11177431792020798,
       "learning_rate": 8.043807145043604e-05,
-      "loss": 11.9209,
+      "loss": 11.9208,
       "step": 16
     },
     {
       "epoch": 0.07789232531500573,
-      "grad_norm": 0.11398056894540787,
+      "grad_norm": 0.10788976401090622,
       "learning_rate": 7.777851165098012e-05,
-      "loss": 11.9175,
+      "loss": 11.9174,
       "step": 17
     },
     {
       "epoch": 0.08247422680412371,
-      "grad_norm": 0.11920252442359924,
+      "grad_norm": 0.11661273241043091,
       "learning_rate": 7.500000000000001e-05,
-      "loss": 11.9221,
+      "loss": 11.922,
       "step": 18
     },
     {
       "epoch": 0.08705612829324169,
-      "grad_norm": 0.12020166218280792,
+      "grad_norm": 0.1152161955833435,
       "learning_rate": 7.211443451095007e-05,
       "loss": 11.9225,
       "step": 19
     },
     {
       "epoch": 0.09163802978235967,
-      "grad_norm": 0.1328224092721939,
+      "grad_norm": 0.1280968338251114,
       "learning_rate": 6.91341716182545e-05,
-      "loss": 11.9192,
+      "loss": 11.9191,
       "step": 20
     },
     {
       "epoch": 0.09621993127147767,
-      "grad_norm": 0.12654143571853638,
+      "grad_norm": 0.12400449812412262,
       "learning_rate": 6.607197326515808e-05,
-      "loss": 11.9227,
+      "loss": 11.9226,
       "step": 21
     },
     {
       "epoch": 0.10080183276059565,
-      "grad_norm": 0.12327836453914642,
+      "grad_norm": 0.1292697936296463,
       "learning_rate": 6.294095225512603e-05,
-      "loss": 11.9178,
+      "loss": 11.9175,
       "step": 22
     },
     {
       "epoch": 0.10538373424971363,
-      "grad_norm": 0.1363614797592163,
+      "grad_norm": 0.13122570514678955,
       "learning_rate": 5.9754516100806423e-05,
-      "loss": 11.9215,
+      "loss": 11.9213,
       "step": 23
     },
     {
       "epoch": 0.10996563573883161,
-      "grad_norm": 0.16435925662517548,
+      "grad_norm": 0.16571535170078278,
       "learning_rate": 5.6526309611002594e-05,
-      "loss": 11.9148,
+      "loss": 11.9144,
       "step": 24
     },
     {
       "epoch": 0.1145475372279496,
-      "grad_norm": 0.23081736266613007,
+      "grad_norm": 0.23065273463726044,
       "learning_rate": 5.327015646150716e-05,
-      "loss": 11.9124,
+      "loss": 11.9115,
       "step": 25
     },
     {
       "epoch": 0.1145475372279496,
-      "eval_loss": 11.914839744567871,
-      "eval_runtime": 2.8732,
-      "eval_samples_per_second": 511.624,
-      "eval_steps_per_second": 64.04,
+      "eval_loss": 11.914542198181152,
+      "eval_runtime": 3.0079,
+      "eval_samples_per_second": 488.718,
+      "eval_steps_per_second": 61.173,
       "step": 25
+    },
+    {
+      "epoch": 0.11912943871706758,
+      "grad_norm": 0.15202878415584564,
+      "learning_rate": 5e-05,
+      "loss": 11.9195,
+      "step": 26
+    },
+    {
+      "epoch": 0.12371134020618557,
+      "grad_norm": 0.15219835937023163,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 11.9135,
+      "step": 27
+    },
+    {
+      "epoch": 0.12829324169530354,
+      "grad_norm": 0.15144570171833038,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 11.9195,
+      "step": 28
+    },
+    {
+      "epoch": 0.13287514318442153,
+      "grad_norm": 0.14890512824058533,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 11.9185,
+      "step": 29
+    },
+    {
+      "epoch": 0.13745704467353953,
+      "grad_norm": 0.14553137123584747,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 11.9198,
+      "step": 30
+    },
+    {
+      "epoch": 0.1420389461626575,
+      "grad_norm": 0.15993446111679077,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 11.9195,
+      "step": 31
+    },
+    {
+      "epoch": 0.1466208476517755,
+      "grad_norm": 0.1511160433292389,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 11.9167,
+      "step": 32
+    },
+    {
+      "epoch": 0.15120274914089346,
+      "grad_norm": 0.16765907406806946,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 11.912,
+      "step": 33
+    },
+    {
+      "epoch": 0.15578465063001146,
+      "grad_norm": 0.1600809097290039,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 11.9175,
+      "step": 34
+    },
+    {
+      "epoch": 0.16036655211912945,
+      "grad_norm": 0.1679549217224121,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 11.911,
+      "step": 35
+    },
+    {
+      "epoch": 0.16494845360824742,
+      "grad_norm": 0.18338091671466827,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 11.9202,
+      "step": 36
+    },
+    {
+      "epoch": 0.16953035509736541,
+      "grad_norm": 0.2111843377351761,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 11.9153,
+      "step": 37
+    },
+    {
+      "epoch": 0.17411225658648338,
+      "grad_norm": 0.19835293292999268,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.9097,
+      "step": 38
+    },
+    {
+      "epoch": 0.17869415807560138,
+      "grad_norm": 0.1626400351524353,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 11.9121,
+      "step": 39
+    },
+    {
+      "epoch": 0.18327605956471935,
+      "grad_norm": 0.17144474387168884,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 11.914,
+      "step": 40
+    },
+    {
+      "epoch": 0.18785796105383734,
+      "grad_norm": 0.16358080506324768,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 11.9206,
+      "step": 41
+    },
+    {
+      "epoch": 0.19243986254295534,
+      "grad_norm": 0.16735625267028809,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 11.9166,
+      "step": 42
+    },
+    {
+      "epoch": 0.1970217640320733,
+      "grad_norm": 0.1590489000082016,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 11.9162,
+      "step": 43
+    },
+    {
+      "epoch": 0.2016036655211913,
+      "grad_norm": 0.1775287389755249,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 11.9136,
+      "step": 44
+    },
+    {
+      "epoch": 0.20618556701030927,
+      "grad_norm": 0.17324328422546387,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 11.9096,
+      "step": 45
+    },
+    {
+      "epoch": 0.21076746849942726,
+      "grad_norm": 0.16713465750217438,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 11.9114,
+      "step": 46
+    },
+    {
+      "epoch": 0.21534936998854526,
+      "grad_norm": 0.1729106605052948,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 11.9082,
+      "step": 47
+    },
+    {
+      "epoch": 0.21993127147766323,
+      "grad_norm": 0.19260583817958832,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 11.9143,
+      "step": 48
+    },
+    {
+      "epoch": 0.22451317296678122,
+      "grad_norm": 0.20485623180866241,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 11.9131,
+      "step": 49
+    },
+    {
+      "epoch": 0.2290950744558992,
+      "grad_norm": 0.26112306118011475,
+      "learning_rate": 0.0,
+      "loss": 11.9099,
+      "step": 50
+    },
+    {
+      "epoch": 0.2290950744558992,
+      "eval_loss": 11.911612510681152,
+      "eval_runtime": 3.0168,
+      "eval_samples_per_second": 487.275,
+      "eval_steps_per_second": 60.992,
+      "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": 521247129600.0,
+  "total_flos": 1042494259200.0,
   "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 sha256:4a0ca69705321df7b0e5a0bdc3c1d6cdc29331dfe2481dc357ed7765385307fe
+oid sha256:3262710446ff9ff68245cf6ba0902cdcc99422923d55ef7f36f77e4f2dad21a7
 size 6776