Training in progress, step 50, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "up_proj",
     "k_proj",
-    "gate_proj",
-    "down_proj",
     "q_proj",
-    "o_proj"
+    "up_proj",
+    "o_proj",
+    "gate_proj",
+    "v_proj",
+    "down_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 sha256:094e333c9c5cfcd505faf72551d3f39fedb2ef60357479428201b309885de0e2
+oid sha256:5704821e9918d31c0d0acaa3815aadbaec64194cb9aad364d12dbb02f99aef36
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a9e6bded1c7da156b16bde042270e95e61471d8ecf1c676eed91229f4cb40f9
+oid sha256:b2332cffe23ee88c1d3cefa50ea29d481f27885266c5ef72af09f95b8ea88330
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ef8fefe4373919b6945c60cafc96dcd70de895c6939a7f9a3915d677f57f7da
+oid sha256:21fc3e1214f1a054edc86d54ac17152d56087755a650502c28ff44b0afe02838
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9cc8ac4b97aeccaa9056b4131591a8fb27e7335ca6d20e2d090fd63e7d915ce
+oid sha256:cf49e13838770f2543b06ada91734af73e0d8b84ea37494eb08cef5e8524dfeb
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:957e5f49359d86e8265b54790e6f0cf1a7bf97efb38166c0b6ecd5a63faa99f3
+oid sha256:e8339809ee687dd7fc50f4a310c530ef1946bcfd894f057ca7209af302e8224d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad8da19b4ab1f7ebf148fbf344b69e384ff4448e83ffff0ebcb8ecebeca7d2c6
+oid sha256:df1149f6a7ed3ad33f0d9ac4a71a894426248796df6565a4dcc40e6db4a83b6a
 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": 2.11344051361084,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.07662835249042145,
+  "best_metric": 2.0885050296783447,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.1532567049808429,
   "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": 0.0030651340996168583,
-      "grad_norm": 27.896610260009766,
+      "grad_norm": 25.439905166625977,
       "learning_rate": 5e-05,
       "loss": 1.8825,
       "step": 1
@@ -18,186 +18,369 @@
     {
       "epoch": 0.0030651340996168583,
       "eval_loss": 2.378786563873291,
-      "eval_runtime": 64.153,
-      "eval_samples_per_second": 34.262,
-      "eval_steps_per_second": 4.287,
+      "eval_runtime": 63.9032,
+      "eval_samples_per_second": 34.396,
+      "eval_steps_per_second": 4.303,
       "step": 1
     },
     {
       "epoch": 0.006130268199233717,
-      "grad_norm": 32.84800720214844,
+      "grad_norm": 31.6901798248291,
       "learning_rate": 0.0001,
       "loss": 2.1452,
       "step": 2
     },
     {
       "epoch": 0.009195402298850575,
-      "grad_norm": 25.192340850830078,
+      "grad_norm": 23.759477615356445,
       "learning_rate": 9.989294616193017e-05,
-      "loss": 2.2998,
+      "loss": 2.3008,
       "step": 3
     },
     {
       "epoch": 0.012260536398467433,
-      "grad_norm": 15.766855239868164,
+      "grad_norm": 15.432135581970215,
       "learning_rate": 9.957224306869053e-05,
-      "loss": 2.2404,
+      "loss": 2.2418,
       "step": 4
     },
     {
       "epoch": 0.01532567049808429,
-      "grad_norm": 14.772031784057617,
+      "grad_norm": 14.17938232421875,
       "learning_rate": 9.903926402016153e-05,
-      "loss": 2.1976,
+      "loss": 2.2003,
       "step": 5
     },
     {
       "epoch": 0.01839080459770115,
-      "grad_norm": 14.457837104797363,
+      "grad_norm": 14.198993682861328,
       "learning_rate": 9.829629131445342e-05,
-      "loss": 2.1336,
+      "loss": 2.1383,
       "step": 6
     },
     {
       "epoch": 0.021455938697318006,
-      "grad_norm": 13.174428939819336,
+      "grad_norm": 17.084095001220703,
       "learning_rate": 9.73465064747553e-05,
-      "loss": 2.1395,
+      "loss": 2.144,
       "step": 7
     },
     {
       "epoch": 0.024521072796934867,
-      "grad_norm": 9.743951797485352,
+      "grad_norm": 10.210630416870117,
       "learning_rate": 9.619397662556435e-05,
-      "loss": 2.1148,
+      "loss": 2.1158,
       "step": 8
     },
     {
       "epoch": 0.027586206896551724,
-      "grad_norm": 10.328970909118652,
+      "grad_norm": 10.326088905334473,
       "learning_rate": 9.484363707663442e-05,
-      "loss": 2.116,
+      "loss": 2.1171,
       "step": 9
     },
     {
       "epoch": 0.03065134099616858,
-      "grad_norm": 10.842561721801758,
+      "grad_norm": 10.55210018157959,
       "learning_rate": 9.330127018922194e-05,
-      "loss": 2.2137,
+      "loss": 2.2147,
       "step": 10
     },
     {
       "epoch": 0.03371647509578544,
-      "grad_norm": 12.265542030334473,
+      "grad_norm": 12.33423137664795,
       "learning_rate": 9.157348061512727e-05,
-      "loss": 2.2578,
+      "loss": 2.2588,
       "step": 11
     },
     {
       "epoch": 0.0367816091954023,
-      "grad_norm": 15.659526824951172,
+      "grad_norm": 15.611214637756348,
       "learning_rate": 8.966766701456177e-05,
-      "loss": 2.178,
+      "loss": 2.1785,
       "step": 12
     },
     {
       "epoch": 0.03984674329501916,
-      "grad_norm": 21.36080551147461,
+      "grad_norm": 20.73734474182129,
       "learning_rate": 8.759199037394887e-05,
-      "loss": 2.0713,
+      "loss": 2.0699,
       "step": 13
     },
     {
       "epoch": 0.04291187739463601,
-      "grad_norm": 29.808998107910156,
+      "grad_norm": 29.948902130126953,
       "learning_rate": 8.535533905932738e-05,
-      "loss": 1.9459,
+      "loss": 1.9448,
       "step": 14
     },
     {
       "epoch": 0.04597701149425287,
-      "grad_norm": 15.340879440307617,
+      "grad_norm": 15.843214988708496,
       "learning_rate": 8.296729075500344e-05,
-      "loss": 2.0594,
+      "loss": 2.0613,
       "step": 15
     },
     {
       "epoch": 0.04904214559386973,
-      "grad_norm": 10.302526473999023,
+      "grad_norm": 10.421913146972656,
       "learning_rate": 8.043807145043604e-05,
-      "loss": 2.2324,
+      "loss": 2.2328,
       "step": 16
     },
     {
       "epoch": 0.05210727969348659,
-      "grad_norm": 8.83031940460205,
+      "grad_norm": 8.803328514099121,
       "learning_rate": 7.777851165098012e-05,
-      "loss": 2.1758,
+      "loss": 2.1753,
       "step": 17
     },
     {
       "epoch": 0.05517241379310345,
-      "grad_norm": 9.309374809265137,
+      "grad_norm": 9.167197227478027,
       "learning_rate": 7.500000000000001e-05,
-      "loss": 2.1735,
+      "loss": 2.172,
       "step": 18
     },
     {
       "epoch": 0.05823754789272031,
-      "grad_norm": 11.40832233428955,
+      "grad_norm": 11.16010570526123,
       "learning_rate": 7.211443451095007e-05,
-      "loss": 2.0792,
+      "loss": 2.0787,
       "step": 19
     },
     {
       "epoch": 0.06130268199233716,
-      "grad_norm": 10.577889442443848,
+      "grad_norm": 10.55145263671875,
       "learning_rate": 6.91341716182545e-05,
       "loss": 2.1069,
       "step": 20
     },
     {
       "epoch": 0.06436781609195402,
-      "grad_norm": 10.584429740905762,
+      "grad_norm": 10.890008926391602,
       "learning_rate": 6.607197326515808e-05,
-      "loss": 2.1862,
+      "loss": 2.186,
       "step": 21
     },
     {
       "epoch": 0.06743295019157088,
-      "grad_norm": 11.981637001037598,
+      "grad_norm": 11.844358444213867,
       "learning_rate": 6.294095225512603e-05,
-      "loss": 2.1701,
+      "loss": 2.1697,
       "step": 22
     },
     {
       "epoch": 0.07049808429118774,
-      "grad_norm": 10.353193283081055,
+      "grad_norm": 10.25471019744873,
       "learning_rate": 5.9754516100806423e-05,
-      "loss": 2.1409,
+      "loss": 2.1411,
       "step": 23
     },
     {
       "epoch": 0.0735632183908046,
-      "grad_norm": 11.31971263885498,
+      "grad_norm": 11.452219009399414,
       "learning_rate": 5.6526309611002594e-05,
-      "loss": 2.1658,
+      "loss": 2.1668,
       "step": 24
     },
     {
       "epoch": 0.07662835249042145,
-      "grad_norm": 31.334794998168945,
+      "grad_norm": 30.90408706665039,
       "learning_rate": 5.327015646150716e-05,
-      "loss": 2.2213,
+      "loss": 2.2226,
       "step": 25
     },
     {
       "epoch": 0.07662835249042145,
-      "eval_loss": 2.11344051361084,
-      "eval_runtime": 64.1924,
-      "eval_samples_per_second": 34.241,
-      "eval_steps_per_second": 4.284,
+      "eval_loss": 2.1118111610412598,
+      "eval_runtime": 63.7959,
+      "eval_samples_per_second": 34.454,
+      "eval_steps_per_second": 4.311,
       "step": 25
+    },
+    {
+      "epoch": 0.07969348659003832,
+      "grad_norm": 9.518340110778809,
+      "learning_rate": 5e-05,
+      "loss": 1.7877,
+      "step": 26
+    },
+    {
+      "epoch": 0.08275862068965517,
+      "grad_norm": 11.724231719970703,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.9382,
+      "step": 27
+    },
+    {
+      "epoch": 0.08582375478927202,
+      "grad_norm": 9.176469802856445,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.0916,
+      "step": 28
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 7.557352066040039,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 2.2222,
+      "step": 29
+    },
+    {
+      "epoch": 0.09195402298850575,
+      "grad_norm": 7.389097690582275,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 2.1794,
+      "step": 30
+    },
+    {
+      "epoch": 0.0950191570881226,
+      "grad_norm": 7.5071611404418945,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 2.0615,
+      "step": 31
+    },
+    {
+      "epoch": 0.09808429118773947,
+      "grad_norm": 8.351806640625,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.0811,
+      "step": 32
+    },
+    {
+      "epoch": 0.10114942528735632,
+      "grad_norm": 9.072479248046875,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 2.1266,
+      "step": 33
+    },
+    {
+      "epoch": 0.10421455938697317,
+      "grad_norm": 9.68136978149414,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.0953,
+      "step": 34
+    },
+    {
+      "epoch": 0.10727969348659004,
+      "grad_norm": 10.606045722961426,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 2.1535,
+      "step": 35
+    },
+    {
+      "epoch": 0.1103448275862069,
+      "grad_norm": 11.27554988861084,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 2.1858,
+      "step": 36
+    },
+    {
+      "epoch": 0.11340996168582375,
+      "grad_norm": 13.031153678894043,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 2.0847,
+      "step": 37
+    },
+    {
+      "epoch": 0.11647509578544062,
+      "grad_norm": 17.304210662841797,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.0854,
+      "step": 38
+    },
+    {
+      "epoch": 0.11954022988505747,
+      "grad_norm": 5.835628986358643,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.8834,
+      "step": 39
+    },
+    {
+      "epoch": 0.12260536398467432,
+      "grad_norm": 5.742768287658691,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.9978,
+      "step": 40
+    },
+    {
+      "epoch": 0.12567049808429118,
+      "grad_norm": 5.689572811126709,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 2.1699,
+      "step": 41
+    },
+    {
+      "epoch": 0.12873563218390804,
+      "grad_norm": 6.36193323135376,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.1757,
+      "step": 42
+    },
+    {
+      "epoch": 0.1318007662835249,
+      "grad_norm": 6.675713539123535,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.1663,
+      "step": 43
+    },
+    {
+      "epoch": 0.13486590038314175,
+      "grad_norm": 7.151950836181641,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.1499,
+      "step": 44
+    },
+    {
+      "epoch": 0.13793103448275862,
+      "grad_norm": 8.27146053314209,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 2.0725,
+      "step": 45
+    },
+    {
+      "epoch": 0.1409961685823755,
+      "grad_norm": 8.100248336791992,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 2.1781,
+      "step": 46
+    },
+    {
+      "epoch": 0.14406130268199233,
+      "grad_norm": 9.346924781799316,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 2.1817,
+      "step": 47
+    },
+    {
+      "epoch": 0.1471264367816092,
+      "grad_norm": 9.631771087646484,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 2.1805,
+      "step": 48
+    },
+    {
+      "epoch": 0.15019157088122606,
+      "grad_norm": 11.957242012023926,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 2.1351,
+      "step": 49
+    },
+    {
+      "epoch": 0.1532567049808429,
+      "grad_norm": 18.1830997467041,
+      "learning_rate": 0.0,
+      "loss": 2.0586,
+      "step": 50
+    },
+    {
+      "epoch": 0.1532567049808429,
+      "eval_loss": 2.0885050296783447,
+      "eval_runtime": 63.7935,
+      "eval_samples_per_second": 34.455,
+      "eval_steps_per_second": 4.311,
+      "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": 2.829013890367488e+17,
+  "total_flos": 5.658027780734976e+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 sha256:1baeee59f7debef1f8d94258da455d503cad8cc40f091043441d3366e0216a96
+oid sha256:b2ed31e570494779bd86d653ae545f1873d662b7f560837aac5f1782bcac42cc
 size 6776