Training in progress, step 50, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
+    "k_proj",
     "q_proj",
-    "o_proj",
     "up_proj",
-    "k_proj",
-    "gate_proj",
     "down_proj",
-    "v_proj"
+    "gate_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 sha256:8b07d0035b63e15a9ef6776f170bb16af15771537fcf6f262d9daa35c43c2bf2
+oid sha256:b4447adce46cb77a561b944694fa131f2d9adc068cfb8070b211d06f309899ab
 size 2436967616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:138dd4dd89d95b56ade77900540e0042650ced2ad86a4b5b92a1ee393f424be1
+oid sha256:04f7a5859cc85b49d3db541e439cfea99881d75deef2b31744fa838d6f6c17a4
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b670e67b1c6dc39525309c030a3fe09e65ba0facc1bcb34601a7f280682c1dd
+oid sha256:8b30f9a2737458acbc09bfff0b2a70024793b53d9dab10d508333870d421400b
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8ba4b856df2155d1d79bbcd8e847c6ea745ea7e4faa578a20dcaee63997f4dc
+oid sha256:d7bd2dc89acabe1ce9bf688cc6f55ca645bb9ad899605dd1246fc1d8ff7c6a14
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c6e89e005ddc72031b2384abcb6727c4bfcb3d5322f22186f2a76f43b12a491
+oid sha256:c7a8f36e8a9e59fc00939274ae574d204fe8c28107afed0b802efafef7b5334a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82abc5c9027e1e86886ac4dd85c644729216051bb973ac24ee890cddc13edb8a
+oid sha256:681ce776e55432ff2f5898d768ab4d96d0e4f9ced052e7518af6ea7677b91186
 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": 1.2989970445632935,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.014217672567000782,
+  "best_metric": 1.2906832695007324,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.028435345134001564,
   "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": 0.0005687069026800313,
-      "grad_norm": 0.7424452900886536,
+      "grad_norm": 0.7920084595680237,
       "learning_rate": 5e-05,
       "loss": 1.3163,
       "step": 1
     },
     {
       "epoch": 0.0005687069026800313,
-      "eval_loss": 1.9984076023101807,
-      "eval_runtime": 778.1587,
-      "eval_samples_per_second": 15.223,
-      "eval_steps_per_second": 1.903,
+      "eval_loss": 1.998407244682312,
+      "eval_runtime": 794.9463,
+      "eval_samples_per_second": 14.902,
+      "eval_steps_per_second": 1.863,
       "step": 1
     },
     {
       "epoch": 0.0011374138053600626,
-      "grad_norm": 1.080130934715271,
+      "grad_norm": 1.1490403413772583,
       "learning_rate": 0.0001,
       "loss": 1.6109,
       "step": 2
     },
     {
       "epoch": 0.0017061207080400938,
-      "grad_norm": 1.0433323383331299,
+      "grad_norm": 1.101967215538025,
       "learning_rate": 9.989294616193017e-05,
-      "loss": 1.6837,
+      "loss": 1.6819,
       "step": 3
     },
     {
       "epoch": 0.002274827610720125,
-      "grad_norm": 0.8534478545188904,
+      "grad_norm": 0.8798887133598328,
       "learning_rate": 9.957224306869053e-05,
-      "loss": 1.5771,
+      "loss": 1.5748,
       "step": 4
     },
     {
       "epoch": 0.0028435345134001566,
-      "grad_norm": 0.8350222706794739,
+      "grad_norm": 0.8839192390441895,
       "learning_rate": 9.903926402016153e-05,
-      "loss": 1.5236,
+      "loss": 1.5231,
       "step": 5
     },
     {
       "epoch": 0.0034122414160801876,
-      "grad_norm": 1.1145470142364502,
+      "grad_norm": 1.1184871196746826,
       "learning_rate": 9.829629131445342e-05,
-      "loss": 1.4151,
+      "loss": 1.4134,
       "step": 6
     },
     {
       "epoch": 0.0039809483187602185,
-      "grad_norm": 0.8083653450012207,
+      "grad_norm": 0.8189905881881714,
       "learning_rate": 9.73465064747553e-05,
-      "loss": 1.3308,
+      "loss": 1.3303,
       "step": 7
     },
     {
       "epoch": 0.00454965522144025,
-      "grad_norm": 0.5271626114845276,
+      "grad_norm": 0.5400599837303162,
       "learning_rate": 9.619397662556435e-05,
-      "loss": 1.4133,
+      "loss": 1.4132,
       "step": 8
     },
     {
       "epoch": 0.005118362124120281,
-      "grad_norm": 0.43272873759269714,
+      "grad_norm": 0.4432584345340729,
       "learning_rate": 9.484363707663442e-05,
-      "loss": 1.3583,
+      "loss": 1.358,
       "step": 9
     },
     {
       "epoch": 0.005687069026800313,
-      "grad_norm": 0.4580666124820709,
+      "grad_norm": 0.4731869697570801,
       "learning_rate": 9.330127018922194e-05,
-      "loss": 1.382,
+      "loss": 1.3826,
       "step": 10
     },
     {
       "epoch": 0.006255775929480344,
-      "grad_norm": 0.4700775146484375,
+      "grad_norm": 0.46975958347320557,
       "learning_rate": 9.157348061512727e-05,
-      "loss": 1.3653,
+      "loss": 1.3652,
       "step": 11
     },
     {
       "epoch": 0.006824482832160375,
-      "grad_norm": 0.46370092034339905,
+      "grad_norm": 0.46591511368751526,
       "learning_rate": 8.966766701456177e-05,
       "loss": 1.3269,
       "step": 12
     },
     {
       "epoch": 0.007393189734840407,
-      "grad_norm": 0.32641956210136414,
+      "grad_norm": 0.33101505041122437,
       "learning_rate": 8.759199037394887e-05,
-      "loss": 1.2265,
+      "loss": 1.2263,
       "step": 13
     },
     {
       "epoch": 0.007961896637520437,
-      "grad_norm": 0.33604350686073303,
+      "grad_norm": 0.3445747196674347,
       "learning_rate": 8.535533905932738e-05,
-      "loss": 1.2166,
+      "loss": 1.2159,
       "step": 14
     },
     {
       "epoch": 0.008530603540200469,
-      "grad_norm": 0.3082321584224701,
+      "grad_norm": 0.3120119273662567,
       "learning_rate": 8.296729075500344e-05,
-      "loss": 1.265,
+      "loss": 1.2639,
       "step": 15
     },
     {
       "epoch": 0.0090993104428805,
-      "grad_norm": 0.3127622902393341,
+      "grad_norm": 0.3253304958343506,
       "learning_rate": 8.043807145043604e-05,
-      "loss": 1.3054,
+      "loss": 1.3055,
       "step": 16
     },
     {
       "epoch": 0.009668017345560533,
-      "grad_norm": 0.31797119975090027,
+      "grad_norm": 0.3255867063999176,
       "learning_rate": 7.777851165098012e-05,
-      "loss": 1.3548,
+      "loss": 1.3549,
       "step": 17
     },
     {
       "epoch": 0.010236724248240563,
-      "grad_norm": 0.3794986605644226,
+      "grad_norm": 0.40002158284187317,
       "learning_rate": 7.500000000000001e-05,
-      "loss": 1.3261,
+      "loss": 1.3257,
       "step": 18
     },
     {
       "epoch": 0.010805431150920594,
-      "grad_norm": 0.3182049095630646,
+      "grad_norm": 0.3267786204814911,
       "learning_rate": 7.211443451095007e-05,
-      "loss": 1.3253,
+      "loss": 1.3248,
       "step": 19
     },
     {
       "epoch": 0.011374138053600626,
-      "grad_norm": 0.33693861961364746,
+      "grad_norm": 0.3477204740047455,
       "learning_rate": 6.91341716182545e-05,
-      "loss": 1.2528,
+      "loss": 1.2534,
       "step": 20
     },
     {
       "epoch": 0.011942844956280656,
-      "grad_norm": 0.37158411741256714,
+      "grad_norm": 0.3819933235645294,
       "learning_rate": 6.607197326515808e-05,
-      "loss": 1.3638,
+      "loss": 1.3634,
       "step": 21
     },
     {
       "epoch": 0.012511551858960688,
-      "grad_norm": 0.3820987343788147,
+      "grad_norm": 0.3762705326080322,
       "learning_rate": 6.294095225512603e-05,
-      "loss": 1.3177,
+      "loss": 1.3172,
       "step": 22
     },
     {
       "epoch": 0.01308025876164072,
-      "grad_norm": 0.35295188426971436,
+      "grad_norm": 0.3576708436012268,
       "learning_rate": 5.9754516100806423e-05,
-      "loss": 1.3014,
+      "loss": 1.3016,
       "step": 23
     },
     {
       "epoch": 0.01364896566432075,
-      "grad_norm": 0.3680730164051056,
+      "grad_norm": 0.36908817291259766,
       "learning_rate": 5.6526309611002594e-05,
-      "loss": 1.3506,
+      "loss": 1.3512,
       "step": 24
     },
     {
       "epoch": 0.014217672567000782,
-      "grad_norm": 0.3996667265892029,
+      "grad_norm": 0.40242210030555725,
       "learning_rate": 5.327015646150716e-05,
-      "loss": 1.4373,
+      "loss": 1.4365,
       "step": 25
     },
     {
       "epoch": 0.014217672567000782,
-      "eval_loss": 1.2989970445632935,
-      "eval_runtime": 786.3656,
-      "eval_samples_per_second": 15.064,
-      "eval_steps_per_second": 1.883,
+      "eval_loss": 1.2991729974746704,
+      "eval_runtime": 812.2277,
+      "eval_samples_per_second": 14.585,
+      "eval_steps_per_second": 1.823,
       "step": 25
+    },
+    {
+      "epoch": 0.014786379469680814,
+      "grad_norm": 0.2276502102613449,
+      "learning_rate": 5e-05,
+      "loss": 1.196,
+      "step": 26
+    },
+    {
+      "epoch": 0.015355086372360844,
+      "grad_norm": 0.29533135890960693,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.2832,
+      "step": 27
+    },
+    {
+      "epoch": 0.015923793275040874,
+      "grad_norm": 0.27309319376945496,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.212,
+      "step": 28
+    },
+    {
+      "epoch": 0.016492500177720908,
+      "grad_norm": 0.2874334454536438,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.2621,
+      "step": 29
+    },
+    {
+      "epoch": 0.017061207080400938,
+      "grad_norm": 0.2680829167366028,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.2315,
+      "step": 30
+    },
+    {
+      "epoch": 0.01762991398308097,
+      "grad_norm": 0.2749057114124298,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.2588,
+      "step": 31
+    },
+    {
+      "epoch": 0.018198620885761,
+      "grad_norm": 0.28463682532310486,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.2278,
+      "step": 32
+    },
+    {
+      "epoch": 0.01876732778844103,
+      "grad_norm": 0.2854940593242645,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.2905,
+      "step": 33
+    },
+    {
+      "epoch": 0.019336034691121065,
+      "grad_norm": 0.29728013277053833,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.2704,
+      "step": 34
+    },
+    {
+      "epoch": 0.019904741593801095,
+      "grad_norm": 0.3585110008716583,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.3124,
+      "step": 35
+    },
+    {
+      "epoch": 0.020473448496481125,
+      "grad_norm": 0.3859107792377472,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.3913,
+      "step": 36
+    },
+    {
+      "epoch": 0.02104215539916116,
+      "grad_norm": 0.3689042627811432,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.382,
+      "step": 37
+    },
+    {
+      "epoch": 0.02161086230184119,
+      "grad_norm": 0.2268395721912384,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.1896,
+      "step": 38
+    },
+    {
+      "epoch": 0.02217956920452122,
+      "grad_norm": 0.24586619436740875,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.2113,
+      "step": 39
+    },
+    {
+      "epoch": 0.022748276107201253,
+      "grad_norm": 0.3258395791053772,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.357,
+      "step": 40
+    },
+    {
+      "epoch": 0.023316983009881283,
+      "grad_norm": 0.28051960468292236,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.2672,
+      "step": 41
+    },
+    {
+      "epoch": 0.023885689912561313,
+      "grad_norm": 0.2582094371318817,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.2189,
+      "step": 42
+    },
+    {
+      "epoch": 0.024454396815241346,
+      "grad_norm": 0.2934226393699646,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.2993,
+      "step": 43
+    },
+    {
+      "epoch": 0.025023103717921377,
+      "grad_norm": 0.2840765118598938,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.2292,
+      "step": 44
+    },
+    {
+      "epoch": 0.025591810620601407,
+      "grad_norm": 0.30331429839134216,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.2672,
+      "step": 45
+    },
+    {
+      "epoch": 0.02616051752328144,
+      "grad_norm": 0.3395172953605652,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.3429,
+      "step": 46
+    },
+    {
+      "epoch": 0.02672922442596147,
+      "grad_norm": 0.2982619106769562,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.2531,
+      "step": 47
+    },
+    {
+      "epoch": 0.0272979313286415,
+      "grad_norm": 0.33072540163993835,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.3625,
+      "step": 48
+    },
+    {
+      "epoch": 0.027866638231321534,
+      "grad_norm": 0.35359904170036316,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.3332,
+      "step": 49
+    },
+    {
+      "epoch": 0.028435345134001564,
+      "grad_norm": 0.38723939657211304,
+      "learning_rate": 0.0,
+      "loss": 1.3448,
+      "step": 50
+    },
+    {
+      "epoch": 0.028435345134001564,
+      "eval_loss": 1.2906832695007324,
+      "eval_runtime": 798.5665,
+      "eval_samples_per_second": 14.834,
+      "eval_steps_per_second": 1.855,
+      "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": 3.0474543379041485e+17,
+  "total_flos": 6.070663327724339e+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:c951cd4a0722076bcba4d7642a1320ca1cb05f0311d133c4a956acec6f56c9e6
+oid sha256:378ea3940743bef80c44bec8bbb72471739e09761ee030e9dda9ec6f231e1e85
 size 6776