Training in progress, step 25, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
+    "up_proj",
+    "q_proj",
     "v_proj",
-    "gate_proj",
+    "o_proj",
     "down_proj",
-    "up_proj",
     "k_proj",
-    "q_proj"
+    "gate_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 sha256:1d4e18070f1fbb323ff7ff66736dbb195610e6b5ce5e81b24898f35e97a06abc
+oid sha256:27ea72c3fef81e660c61caf875f657fc3522ea93174492ce188ba45643557473
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39f29dcc78510dc497cd6eee55d10960c256b53fccec8fb8f066642446661b29
+oid sha256:b2d7b3b44effdefdd96a1c4f3c20120ee3d7bd2811acdd3d73aeba990d9c6ff2
 size 170920084

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b628271795a824ff26c9ba2c9328f6e4104a7f47aab89bc3ae57b145971748ed
+oid sha256:5537e910b76a6f610d3778b948cabe4cd17467c9f407942be9530729a5c41a5a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
+oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
 size 1064

last-checkpoint/trainer_state.json

@@ -1,16 +1,16 @@
 {
-  "best_metric": 1.06325101852417,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.15464913976416006,
+  "best_metric": 1.0824270248413086,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.07732456988208003,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.003092982795283201,
-      "grad_norm": 62.20377731323242,
+      "grad_norm": 63.227630615234375,
       "learning_rate": 1e-05,
       "loss": 25.075,
       "step": 1
@@ -18,369 +18,186 @@
     {
       "epoch": 0.003092982795283201,
       "eval_loss": 1.5490102767944336,
-      "eval_runtime": 149.2461,
-      "eval_samples_per_second": 3.652,
+      "eval_runtime": 149.2754,
+      "eval_samples_per_second": 3.651,
       "eval_steps_per_second": 1.829,
       "step": 1
     },
     {
       "epoch": 0.006185965590566402,
-      "grad_norm": 66.19660949707031,
+      "grad_norm": 66.90909576416016,
       "learning_rate": 2e-05,
       "loss": 23.6882,
       "step": 2
     },
     {
       "epoch": 0.009278948385849604,
-      "grad_norm": 63.24820327758789,
+      "grad_norm": 63.644508361816406,
       "learning_rate": 3e-05,
       "loss": 23.8152,
       "step": 3
     },
     {
       "epoch": 0.012371931181132804,
-      "grad_norm": 65.91133880615234,
+      "grad_norm": 66.12242126464844,
       "learning_rate": 4e-05,
-      "loss": 24.4938,
+      "loss": 24.5011,
       "step": 4
     },
     {
       "epoch": 0.015464913976416006,
-      "grad_norm": 37.1609001159668,
+      "grad_norm": 37.521697998046875,
       "learning_rate": 5e-05,
-      "loss": 20.4001,
+      "loss": 20.4137,
       "step": 5
     },
     {
       "epoch": 0.01855789677169921,
-      "grad_norm": 37.836673736572266,
+      "grad_norm": 36.76587677001953,
       "learning_rate": 6e-05,
-      "loss": 21.0493,
+      "loss": 21.0439,
       "step": 6
     },
     {
       "epoch": 0.02165087956698241,
-      "grad_norm": 35.000755310058594,
+      "grad_norm": 35.1934928894043,
       "learning_rate": 7e-05,
-      "loss": 19.5046,
+      "loss": 19.4824,
       "step": 7
     },
     {
       "epoch": 0.02474386236226561,
-      "grad_norm": 31.371307373046875,
+      "grad_norm": 34.91908645629883,
       "learning_rate": 8e-05,
-      "loss": 18.7178,
+      "loss": 18.7023,
       "step": 8
     },
     {
       "epoch": 0.02783684515754881,
-      "grad_norm": 36.98615264892578,
+      "grad_norm": 37.3280143737793,
       "learning_rate": 9e-05,
-      "loss": 19.6468,
+      "loss": 19.6331,
       "step": 9
     },
     {
       "epoch": 0.03092982795283201,
-      "grad_norm": 33.72000503540039,
+      "grad_norm": 33.82084655761719,
       "learning_rate": 0.0001,
-      "loss": 19.1595,
+      "loss": 19.1644,
       "step": 10
     },
     {
       "epoch": 0.034022810748115216,
-      "grad_norm": 32.670860290527344,
+      "grad_norm": 28.904260635375977,
       "learning_rate": 9.98458666866564e-05,
-      "loss": 18.3969,
+      "loss": 18.3894,
       "step": 11
     },
     {
       "epoch": 0.03711579354339842,
-      "grad_norm": 35.979820251464844,
+      "grad_norm": 33.33706283569336,
       "learning_rate": 9.938441702975689e-05,
-      "loss": 19.4862,
+      "loss": 19.5411,
       "step": 12
     },
     {
       "epoch": 0.04020877633868162,
-      "grad_norm": 28.703033447265625,
+      "grad_norm": 28.71995735168457,
       "learning_rate": 9.861849601988383e-05,
-      "loss": 17.8546,
+      "loss": 17.7854,
       "step": 13
     },
     {
       "epoch": 0.04330175913396482,
-      "grad_norm": 24.526432037353516,
+      "grad_norm": 24.508121490478516,
       "learning_rate": 9.755282581475769e-05,
-      "loss": 17.7441,
+      "loss": 17.7444,
       "step": 14
     },
     {
       "epoch": 0.046394741929248015,
-      "grad_norm": 25.215848922729492,
+      "grad_norm": 25.298206329345703,
       "learning_rate": 9.619397662556435e-05,
-      "loss": 17.3959,
+      "loss": 17.419,
       "step": 15
     },
     {
       "epoch": 0.04948772472453122,
-      "grad_norm": 26.21254539489746,
+      "grad_norm": 26.203685760498047,
       "learning_rate": 9.45503262094184e-05,
-      "loss": 17.1178,
+      "loss": 17.0621,
       "step": 16
     },
     {
       "epoch": 0.05258070751981442,
-      "grad_norm": 27.829181671142578,
+      "grad_norm": 28.71617889404297,
       "learning_rate": 9.263200821770461e-05,
-      "loss": 19.3058,
+      "loss": 19.3019,
       "step": 17
     },
     {
       "epoch": 0.05567369031509762,
-      "grad_norm": 25.054349899291992,
+      "grad_norm": 24.17940902709961,
       "learning_rate": 9.045084971874738e-05,
-      "loss": 17.6997,
+      "loss": 17.6426,
       "step": 18
     },
     {
       "epoch": 0.05876667311038082,
-      "grad_norm": 25.53619384765625,
+      "grad_norm": 25.524850845336914,
       "learning_rate": 8.802029828000156e-05,
-      "loss": 17.6693,
+      "loss": 17.6575,
       "step": 19
     },
     {
       "epoch": 0.06185965590566402,
-      "grad_norm": 29.731338500976562,
+      "grad_norm": 30.970611572265625,
       "learning_rate": 8.535533905932738e-05,
-      "loss": 18.1907,
+      "loss": 18.1651,
       "step": 20
     },
     {
       "epoch": 0.06495263870094722,
-      "grad_norm": 27.52916145324707,
+      "grad_norm": 26.73845100402832,
       "learning_rate": 8.247240241650918e-05,
-      "loss": 17.7958,
+      "loss": 17.7731,
       "step": 21
     },
     {
       "epoch": 0.06804562149623043,
-      "grad_norm": 27.228439331054688,
+      "grad_norm": 27.083934783935547,
       "learning_rate": 7.938926261462366e-05,
-      "loss": 18.8158,
+      "loss": 18.8107,
       "step": 22
     },
     {
       "epoch": 0.07113860429151363,
-      "grad_norm": 26.449893951416016,
+      "grad_norm": 26.337148666381836,
       "learning_rate": 7.612492823579745e-05,
-      "loss": 17.0907,
+      "loss": 17.086,
       "step": 23
     },
     {
       "epoch": 0.07423158708679684,
-      "grad_norm": 26.7717227935791,
+      "grad_norm": 24.6472225189209,
       "learning_rate": 7.269952498697734e-05,
-      "loss": 19.3673,
+      "loss": 19.3557,
       "step": 24
     },
     {
       "epoch": 0.07732456988208003,
-      "grad_norm": 24.446931838989258,
+      "grad_norm": 24.704971313476562,
       "learning_rate": 6.91341716182545e-05,
-      "loss": 17.9268,
+      "loss": 17.915,
       "step": 25
     },
     {
       "epoch": 0.07732456988208003,
-      "eval_loss": 1.0832998752593994,
-      "eval_runtime": 150.2298,
-      "eval_samples_per_second": 3.628,
-      "eval_steps_per_second": 1.817,
+      "eval_loss": 1.0824270248413086,
+      "eval_runtime": 150.1751,
+      "eval_samples_per_second": 3.629,
+      "eval_steps_per_second": 1.818,
       "step": 25
-    },
-    {
-      "epoch": 0.08041755267736324,
-      "grad_norm": 24.669111251831055,
-      "learning_rate": 6.545084971874738e-05,
-      "loss": 17.5459,
-      "step": 26
-    },
-    {
-      "epoch": 0.08351053547264643,
-      "grad_norm": 23.340457916259766,
-      "learning_rate": 6.167226819279528e-05,
-      "loss": 16.5561,
-      "step": 27
-    },
-    {
-      "epoch": 0.08660351826792964,
-      "grad_norm": 25.84408950805664,
-      "learning_rate": 5.782172325201155e-05,
-      "loss": 17.3012,
-      "step": 28
-    },
-    {
-      "epoch": 0.08969650106321284,
-      "grad_norm": 25.935504913330078,
-      "learning_rate": 5.392295478639225e-05,
-      "loss": 18.7042,
-      "step": 29
-    },
-    {
-      "epoch": 0.09278948385849603,
-      "grad_norm": 23.08302879333496,
-      "learning_rate": 5e-05,
-      "loss": 16.2506,
-      "step": 30
-    },
-    {
-      "epoch": 0.09588246665377924,
-      "grad_norm": 24.507280349731445,
-      "learning_rate": 4.607704521360776e-05,
-      "loss": 18.5361,
-      "step": 31
-    },
-    {
-      "epoch": 0.09897544944906243,
-      "grad_norm": 22.492021560668945,
-      "learning_rate": 4.2178276747988446e-05,
-      "loss": 16.9076,
-      "step": 32
-    },
-    {
-      "epoch": 0.10206843224434564,
-      "grad_norm": 24.12836456298828,
-      "learning_rate": 3.832773180720475e-05,
-      "loss": 18.5358,
-      "step": 33
-    },
-    {
-      "epoch": 0.10516141503962884,
-      "grad_norm": 22.608657836914062,
-      "learning_rate": 3.4549150281252636e-05,
-      "loss": 16.6398,
-      "step": 34
-    },
-    {
-      "epoch": 0.10825439783491204,
-      "grad_norm": 21.76448631286621,
-      "learning_rate": 3.086582838174551e-05,
-      "loss": 16.4674,
-      "step": 35
-    },
-    {
-      "epoch": 0.11134738063019524,
-      "grad_norm": 24.399173736572266,
-      "learning_rate": 2.7300475013022663e-05,
-      "loss": 16.219,
-      "step": 36
-    },
-    {
-      "epoch": 0.11444036342547845,
-      "grad_norm": 21.240434646606445,
-      "learning_rate": 2.3875071764202563e-05,
-      "loss": 14.7258,
-      "step": 37
-    },
-    {
-      "epoch": 0.11753334622076164,
-      "grad_norm": 23.667985916137695,
-      "learning_rate": 2.061073738537635e-05,
-      "loss": 17.4903,
-      "step": 38
-    },
-    {
-      "epoch": 0.12062632901604485,
-      "grad_norm": 24.75313377380371,
-      "learning_rate": 1.7527597583490822e-05,
-      "loss": 18.4833,
-      "step": 39
-    },
-    {
-      "epoch": 0.12371931181132804,
-      "grad_norm": 28.104583740234375,
-      "learning_rate": 1.4644660940672627e-05,
-      "loss": 16.1857,
-      "step": 40
-    },
-    {
-      "epoch": 0.12681229460661125,
-      "grad_norm": 24.995805740356445,
-      "learning_rate": 1.1979701719998453e-05,
-      "loss": 16.9785,
-      "step": 41
-    },
-    {
-      "epoch": 0.12990527740189445,
-      "grad_norm": 26.10293197631836,
-      "learning_rate": 9.549150281252633e-06,
-      "loss": 17.8392,
-      "step": 42
-    },
-    {
-      "epoch": 0.13299826019717764,
-      "grad_norm": 22.538623809814453,
-      "learning_rate": 7.367991782295391e-06,
-      "loss": 16.8663,
-      "step": 43
-    },
-    {
-      "epoch": 0.13609124299246086,
-      "grad_norm": 23.371549606323242,
-      "learning_rate": 5.449673790581611e-06,
-      "loss": 17.0096,
-      "step": 44
-    },
-    {
-      "epoch": 0.13918422578774406,
-      "grad_norm": 22.70631980895996,
-      "learning_rate": 3.8060233744356633e-06,
-      "loss": 16.9947,
-      "step": 45
-    },
-    {
-      "epoch": 0.14227720858302725,
-      "grad_norm": 26.935110092163086,
-      "learning_rate": 2.4471741852423237e-06,
-      "loss": 17.6166,
-      "step": 46
-    },
-    {
-      "epoch": 0.14537019137831045,
-      "grad_norm": 24.898109436035156,
-      "learning_rate": 1.3815039801161721e-06,
-      "loss": 17.4678,
-      "step": 47
-    },
-    {
-      "epoch": 0.14846317417359367,
-      "grad_norm": 23.253236770629883,
-      "learning_rate": 6.15582970243117e-07,
-      "loss": 17.145,
-      "step": 48
-    },
-    {
-      "epoch": 0.15155615696887687,
-      "grad_norm": 23.85171890258789,
-      "learning_rate": 1.5413331334360182e-07,
-      "loss": 17.1861,
-      "step": 49
-    },
-    {
-      "epoch": 0.15464913976416006,
-      "grad_norm": 22.377422332763672,
-      "learning_rate": 0.0,
-      "loss": 19.1859,
-      "step": 50
-    },
-    {
-      "epoch": 0.15464913976416006,
-      "eval_loss": 1.06325101852417,
-      "eval_runtime": 150.4088,
-      "eval_samples_per_second": 3.623,
-      "eval_steps_per_second": 1.815,
-      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -404,12 +221,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.5435789463506125e+17,
+  "total_flos": 7.709054073411994e+16,
   "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 sha256:7c7893fcc1d921507987621a11ba58392fa5578668e213df95a55c81995950c5
+oid sha256:c6f6e4fa385cc360d0456add741e899e95c6f03dade6986e9b6175844c1c2dab
 size 6776