Training in progress, step 50, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "k_proj",
-    "q_proj",
-    "v_proj",
-    "down_proj",
     "o_proj",
-    "up_proj"
+    "down_proj",
+    "up_proj",
+    "v_proj",
+    "q_proj",
+    "k_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:ae7790f6750cce5fb155b7082d134522fe9312e8e536a851652e2d551940ea8a
+oid sha256:5a4fd1a1204f820541a8f3b2731e5a5ef37999a03a9c7d0a27dd5dd588cafb95
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8944c9130cc0aa59b1d38ba554ac3c84d606f76602259d50dd3f66f13e86b3d6
+oid sha256:3f4f48320bbf5c5a6823402dff77050fb6330d7bb7d8c7d072e7d14d57a37ae5
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79d969f1a2c98fb08c30a096b34a2e61bf87c7f69b575937f7a0b7c8efd13484
+oid sha256:9cd84017d7a45649ab4b602dd4b32c386d449c9e5dbcaa9d31e2c1dab8834ea0
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d66904108cd7c23c4f04d424a35487440ab0d8755fe6630bbc54ff1ffe96f52b
+oid sha256:945b478f0683f5f1de6a8e7b70e971d13eae00048bbf09dfd05f6821263770bf
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d208c72c4c3f20d4c3f17256f6a6fcd4a2520e9350f5cdb0030dffd1404f076
+oid sha256:87a50460e0aaf5b8ef80783169e5d7bfd133adc474093fd8c944b58733b99b02
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d974818fb8608f37fa9fc42ad2d4832b2d1f47fd529c8ccdb6b0cc17fc7f8a72
+oid sha256:c0809f1ef07bc038f80e0c26d2634aa5671635abc0c4a8b8b7eee6465e6bde43
 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": 10.369842529296875,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.05670541536716756,
+  "best_metric": 10.363082885742188,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.11341083073433512,
   "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": 0.0022682166146867026,
-      "grad_norm": 0.14479899406433105,
+      "grad_norm": 0.13453303277492523,
       "learning_rate": 5e-05,
       "loss": 10.3842,
       "step": 1
@@ -18,186 +18,369 @@
     {
       "epoch": 0.0022682166146867026,
       "eval_loss": 10.386616706848145,
-      "eval_runtime": 3.2554,
-      "eval_samples_per_second": 912.334,
-      "eval_steps_per_second": 114.272,
+      "eval_runtime": 3.0147,
+      "eval_samples_per_second": 985.168,
+      "eval_steps_per_second": 123.395,
       "step": 1
     },
     {
       "epoch": 0.004536433229373405,
-      "grad_norm": 0.14807619154453278,
+      "grad_norm": 0.1353277713060379,
       "learning_rate": 0.0001,
       "loss": 10.3876,
       "step": 2
     },
     {
       "epoch": 0.006804649844060108,
-      "grad_norm": 0.15308985114097595,
+      "grad_norm": 0.14166195690631866,
       "learning_rate": 9.989294616193017e-05,
       "loss": 10.3875,
       "step": 3
     },
     {
       "epoch": 0.00907286645874681,
-      "grad_norm": 0.1542433798313141,
+      "grad_norm": 0.14265072345733643,
       "learning_rate": 9.957224306869053e-05,
-      "loss": 10.3853,
+      "loss": 10.3854,
       "step": 4
     },
     {
       "epoch": 0.011341083073433513,
-      "grad_norm": 0.161626935005188,
+      "grad_norm": 0.1489330232143402,
       "learning_rate": 9.903926402016153e-05,
-      "loss": 10.3862,
+      "loss": 10.3863,
       "step": 5
     },
     {
       "epoch": 0.013609299688120215,
-      "grad_norm": 0.16123023629188538,
+      "grad_norm": 0.14977039396762848,
       "learning_rate": 9.829629131445342e-05,
-      "loss": 10.3841,
+      "loss": 10.3842,
       "step": 6
     },
     {
       "epoch": 0.01587751630280692,
-      "grad_norm": 0.1623682677745819,
+      "grad_norm": 0.15355272591114044,
       "learning_rate": 9.73465064747553e-05,
-      "loss": 10.3832,
+      "loss": 10.3833,
       "step": 7
     },
     {
       "epoch": 0.01814573291749362,
-      "grad_norm": 0.15166254341602325,
+      "grad_norm": 0.1444183886051178,
       "learning_rate": 9.619397662556435e-05,
-      "loss": 10.3861,
+      "loss": 10.3862,
       "step": 8
     },
     {
       "epoch": 0.020413949532180325,
-      "grad_norm": 0.16110487282276154,
+      "grad_norm": 0.15106390416622162,
       "learning_rate": 9.484363707663442e-05,
-      "loss": 10.3847,
+      "loss": 10.3849,
       "step": 9
     },
     {
       "epoch": 0.022682166146867026,
-      "grad_norm": 0.15980345010757446,
+      "grad_norm": 0.154390349984169,
       "learning_rate": 9.330127018922194e-05,
       "loss": 10.3838,
       "step": 10
     },
     {
       "epoch": 0.02495038276155373,
-      "grad_norm": 0.146297425031662,
+      "grad_norm": 0.14189912378787994,
       "learning_rate": 9.157348061512727e-05,
-      "loss": 10.3831,
+      "loss": 10.3832,
       "step": 11
     },
     {
       "epoch": 0.02721859937624043,
-      "grad_norm": 0.16222330927848816,
+      "grad_norm": 0.16048261523246765,
       "learning_rate": 8.966766701456177e-05,
-      "loss": 10.3847,
+      "loss": 10.3848,
       "step": 12
     },
     {
       "epoch": 0.029486815990927135,
-      "grad_norm": 0.1891157180070877,
+      "grad_norm": 0.18116344511508942,
       "learning_rate": 8.759199037394887e-05,
-      "loss": 10.377,
+      "loss": 10.3773,
       "step": 13
     },
     {
       "epoch": 0.03175503260561384,
-      "grad_norm": 0.19309911131858826,
+      "grad_norm": 0.1787891834974289,
       "learning_rate": 8.535533905932738e-05,
-      "loss": 10.3792,
+      "loss": 10.3796,
       "step": 14
     },
     {
       "epoch": 0.03402324922030054,
-      "grad_norm": 0.202869713306427,
+      "grad_norm": 0.19100786745548248,
       "learning_rate": 8.296729075500344e-05,
-      "loss": 10.3785,
+      "loss": 10.3789,
       "step": 15
     },
     {
       "epoch": 0.03629146583498724,
-      "grad_norm": 0.2117149531841278,
+      "grad_norm": 0.19920316338539124,
       "learning_rate": 8.043807145043604e-05,
-      "loss": 10.3761,
+      "loss": 10.3765,
       "step": 16
     },
     {
       "epoch": 0.03855968244967394,
-      "grad_norm": 0.20285949110984802,
+      "grad_norm": 0.19364210963249207,
       "learning_rate": 7.777851165098012e-05,
-      "loss": 10.3787,
+      "loss": 10.3789,
       "step": 17
     },
     {
       "epoch": 0.04082789906436065,
-      "grad_norm": 0.202358677983284,
+      "grad_norm": 0.1934957504272461,
       "learning_rate": 7.500000000000001e-05,
-      "loss": 10.3756,
+      "loss": 10.3758,
       "step": 18
     },
     {
       "epoch": 0.04309611567904735,
-      "grad_norm": 0.20665286481380463,
+      "grad_norm": 0.19975155591964722,
       "learning_rate": 7.211443451095007e-05,
-      "loss": 10.3771,
+      "loss": 10.3772,
       "step": 19
     },
     {
       "epoch": 0.04536433229373405,
-      "grad_norm": 0.21152782440185547,
+      "grad_norm": 0.20424290001392365,
       "learning_rate": 6.91341716182545e-05,
-      "loss": 10.3745,
+      "loss": 10.3748,
       "step": 20
     },
     {
       "epoch": 0.04763254890842075,
-      "grad_norm": 0.22421160340309143,
+      "grad_norm": 0.21936988830566406,
       "learning_rate": 6.607197326515808e-05,
-      "loss": 10.3751,
+      "loss": 10.3752,
       "step": 21
     },
     {
       "epoch": 0.04990076552310746,
-      "grad_norm": 0.19612239301204681,
+      "grad_norm": 0.19495096802711487,
       "learning_rate": 6.294095225512603e-05,
       "loss": 10.3742,
       "step": 22
     },
     {
       "epoch": 0.05216898213779416,
-      "grad_norm": 0.19813410937786102,
+      "grad_norm": 0.1962108314037323,
       "learning_rate": 5.9754516100806423e-05,
       "loss": 10.3749,
       "step": 23
     },
     {
       "epoch": 0.05443719875248086,
-      "grad_norm": 0.20711098611354828,
+      "grad_norm": 0.21276497840881348,
       "learning_rate": 5.6526309611002594e-05,
-      "loss": 10.3744,
+      "loss": 10.3741,
       "step": 24
     },
     {
       "epoch": 0.05670541536716756,
-      "grad_norm": 0.2224423587322235,
+      "grad_norm": 0.22711583971977234,
       "learning_rate": 5.327015646150716e-05,
-      "loss": 10.3696,
+      "loss": 10.3694,
       "step": 25
     },
     {
       "epoch": 0.05670541536716756,
-      "eval_loss": 10.369842529296875,
-      "eval_runtime": 3.2494,
-      "eval_samples_per_second": 914.016,
-      "eval_steps_per_second": 114.483,
+      "eval_loss": 10.370012283325195,
+      "eval_runtime": 3.012,
+      "eval_samples_per_second": 986.057,
+      "eval_steps_per_second": 123.506,
       "step": 25
+    },
+    {
+      "epoch": 0.05897363198185427,
+      "grad_norm": 0.2256181389093399,
+      "learning_rate": 5e-05,
+      "loss": 10.3691,
+      "step": 26
+    },
+    {
+      "epoch": 0.06124184859654097,
+      "grad_norm": 0.2604275941848755,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 10.3696,
+      "step": 27
+    },
+    {
+      "epoch": 0.06351006521122768,
+      "grad_norm": 0.25977396965026855,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 10.3701,
+      "step": 28
+    },
+    {
+      "epoch": 0.06577828182591437,
+      "grad_norm": 0.24867641925811768,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 10.3697,
+      "step": 29
+    },
+    {
+      "epoch": 0.06804649844060108,
+      "grad_norm": 0.25991758704185486,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 10.3685,
+      "step": 30
+    },
+    {
+      "epoch": 0.07031471505528777,
+      "grad_norm": 0.2578147351741791,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 10.3677,
+      "step": 31
+    },
+    {
+      "epoch": 0.07258293166997448,
+      "grad_norm": 0.26339924335479736,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 10.3657,
+      "step": 32
+    },
+    {
+      "epoch": 0.07485114828466119,
+      "grad_norm": 0.26088207960128784,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 10.3669,
+      "step": 33
+    },
+    {
+      "epoch": 0.07711936489934788,
+      "grad_norm": 0.2547827959060669,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.3682,
+      "step": 34
+    },
+    {
+      "epoch": 0.07938758151403459,
+      "grad_norm": 0.24972853064537048,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 10.3678,
+      "step": 35
+    },
+    {
+      "epoch": 0.0816557981287213,
+      "grad_norm": 0.24014292657375336,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 10.3681,
+      "step": 36
+    },
+    {
+      "epoch": 0.08392401474340799,
+      "grad_norm": 0.25370946526527405,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 10.368,
+      "step": 37
+    },
+    {
+      "epoch": 0.0861922313580947,
+      "grad_norm": 0.2755444645881653,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 10.365,
+      "step": 38
+    },
+    {
+      "epoch": 0.0884604479727814,
+      "grad_norm": 0.28044813871383667,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 10.3633,
+      "step": 39
+    },
+    {
+      "epoch": 0.0907286645874681,
+      "grad_norm": 0.2877492308616638,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 10.3634,
+      "step": 40
+    },
+    {
+      "epoch": 0.09299688120215481,
+      "grad_norm": 0.28548380732536316,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 10.3642,
+      "step": 41
+    },
+    {
+      "epoch": 0.0952650978168415,
+      "grad_norm": 0.287057101726532,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.3644,
+      "step": 42
+    },
+    {
+      "epoch": 0.09753331443152821,
+      "grad_norm": 0.27017641067504883,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 10.3632,
+      "step": 43
+    },
+    {
+      "epoch": 0.09980153104621492,
+      "grad_norm": 0.28016337752342224,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 10.3635,
+      "step": 44
+    },
+    {
+      "epoch": 0.10206974766090161,
+      "grad_norm": 0.2789553701877594,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 10.3652,
+      "step": 45
+    },
+    {
+      "epoch": 0.10433796427558832,
+      "grad_norm": 0.26287078857421875,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 10.3658,
+      "step": 46
+    },
+    {
+      "epoch": 0.10660618089027502,
+      "grad_norm": 0.2548418939113617,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 10.3657,
+      "step": 47
+    },
+    {
+      "epoch": 0.10887439750496172,
+      "grad_norm": 0.2463953047990799,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 10.3657,
+      "step": 48
+    },
+    {
+      "epoch": 0.11114261411964843,
+      "grad_norm": 0.24887269735336304,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 10.3673,
+      "step": 49
+    },
+    {
+      "epoch": 0.11341083073433512,
+      "grad_norm": 0.28098398447036743,
+      "learning_rate": 0.0,
+      "loss": 10.3651,
+      "step": 50
+    },
+    {
+      "epoch": 0.11341083073433512,
+      "eval_loss": 10.363082885742188,
+      "eval_runtime": 3.0067,
+      "eval_samples_per_second": 987.799,
+      "eval_steps_per_second": 123.724,
+      "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": 21397394817024.0,
+  "total_flos": 42781424615424.0,
   "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 sha256:7a177b60e693dc813e8f3df7a2d42c94f1117dfde37b89347c189b46762472d4
+oid sha256:7438df3680029d1b3ebd8cda75f93f924b03e7e0482eee806cb9cb7640a2209c
 size 6776