Training in progress, step 25, checkpoint

last-checkpoint/adapter_config.json

@@ -20,11 +20,11 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
     "fc2",
     "v_proj",
-    "dense",
     "q_proj",
+    "k_proj",
+    "dense",
     "fc1"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8641ace53419270953e50f2e98df854dccef9d59f6a514ad2e681f152df9867
+oid sha256:5344e7a7add3e89e41aeb337ebdae046fd6fa892d2b80e735f340c3fd78d3fdc
 size 237402

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4bcef9a91b58d70af76c8eb6df41efc60c1336232637cea7177b97ba498218d
+oid sha256:6ab9bb1a6b28590e8cdf6d5d97f56111d741105fe7bd97b6899e8ea18bef4415
 size 222294

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:099e3b3ec7346c34835b0aff5f54050462d9647eef25fe8194d29bfcdeca6713
+oid sha256:69df9800e8b1c5e00d6d519768544bf65506150c1bb390d68da7ce38e537e541
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33a3144b6acaf405a5c988057c3b0f6d64546f6b2967d86f16487ec9cb7de0f3
+oid sha256:8511a77015534d7db2081b11e409298541ddd24cdcdc646e445d3c1a4528b1fe
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:743c0ffc81ebc4cd6e3620423405ad0497e04f340aafdb48f5af9ab1671896e2
+oid sha256:55aeb9f99504e02c5ea1678e1fb16f17a93f84c005df4f32b00f4c3797da054c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0df6f5a11f5cb4a7d9153c5397414121230ba31550fe0dc8edfc8dbe4c66f782
+oid sha256:a2e36554bfd0557463ab58deaa94a8390a208db7b006d5908d842dc58c2ba8e3
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
+oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
 size 1064

last-checkpoint/trainer_state.json

@@ -1,386 +1,203 @@
 {
-  "best_metric": 6.924656867980957,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.010696188145949487,
+  "best_metric": 6.9282989501953125,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.005348094072974744,
   "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": 0.00021392376291898973,
-      "grad_norm": 0.08630125969648361,
+      "grad_norm": 0.084352046251297,
       "learning_rate": 5e-05,
       "loss": 6.9391,
       "step": 1
     },
     {
       "epoch": 0.00021392376291898973,
-      "eval_loss": 6.9391374588012695,
-      "eval_runtime": 20.6105,
-      "eval_samples_per_second": 1527.958,
-      "eval_steps_per_second": 191.019,
+      "eval_loss": 6.939151287078857,
+      "eval_runtime": 22.5661,
+      "eval_samples_per_second": 1395.547,
+      "eval_steps_per_second": 174.465,
       "step": 1
     },
     {
       "epoch": 0.00042784752583797947,
-      "grad_norm": 0.08528615534305573,
+      "grad_norm": 0.08244480937719345,
       "learning_rate": 0.0001,
       "loss": 6.9384,
       "step": 2
     },
     {
       "epoch": 0.0006417712887569693,
-      "grad_norm": 0.09091469645500183,
+      "grad_norm": 0.08688157051801682,
       "learning_rate": 9.989294616193017e-05,
       "loss": 6.9393,
       "step": 3
     },
     {
       "epoch": 0.0008556950516759589,
-      "grad_norm": 0.09644569456577301,
+      "grad_norm": 0.09273950755596161,
       "learning_rate": 9.957224306869053e-05,
-      "loss": 6.9372,
+      "loss": 6.9373,
       "step": 4
     },
     {
       "epoch": 0.0010696188145949488,
-      "grad_norm": 0.09739217162132263,
+      "grad_norm": 0.09501701593399048,
       "learning_rate": 9.903926402016153e-05,
       "loss": 6.9383,
       "step": 5
     },
     {
       "epoch": 0.0012835425775139385,
-      "grad_norm": 0.10253387689590454,
+      "grad_norm": 0.09917747974395752,
       "learning_rate": 9.829629131445342e-05,
       "loss": 6.9381,
       "step": 6
     },
     {
       "epoch": 0.0014974663404329282,
-      "grad_norm": 0.10638941824436188,
+      "grad_norm": 0.10376238822937012,
       "learning_rate": 9.73465064747553e-05,
-      "loss": 6.9363,
+      "loss": 6.9364,
       "step": 7
     },
     {
       "epoch": 0.0017113901033519179,
-      "grad_norm": 0.11278034001588821,
+      "grad_norm": 0.11044597625732422,
       "learning_rate": 9.619397662556435e-05,
       "loss": 6.9352,
       "step": 8
     },
     {
       "epoch": 0.0019253138662709078,
-      "grad_norm": 0.11507147550582886,
+      "grad_norm": 0.11213497817516327,
       "learning_rate": 9.484363707663442e-05,
-      "loss": 6.9354,
+      "loss": 6.9355,
       "step": 9
     },
     {
       "epoch": 0.0021392376291898977,
-      "grad_norm": 0.11515306681394577,
+      "grad_norm": 0.11234603077173233,
       "learning_rate": 9.330127018922194e-05,
-      "loss": 6.9372,
+      "loss": 6.9373,
       "step": 10
     },
     {
       "epoch": 0.0023531613921088873,
-      "grad_norm": 0.12654078006744385,
+      "grad_norm": 0.12427860498428345,
       "learning_rate": 9.157348061512727e-05,
-      "loss": 6.9337,
+      "loss": 6.9339,
       "step": 11
     },
     {
       "epoch": 0.002567085155027877,
-      "grad_norm": 0.14077888429164886,
+      "grad_norm": 0.13528341054916382,
       "learning_rate": 8.966766701456177e-05,
-      "loss": 6.9351,
+      "loss": 6.9354,
       "step": 12
     },
     {
       "epoch": 0.0027810089179468667,
-      "grad_norm": 0.10465764254331589,
+      "grad_norm": 0.10144588351249695,
       "learning_rate": 8.759199037394887e-05,
-      "loss": 6.9323,
+      "loss": 6.9326,
       "step": 13
     },
     {
       "epoch": 0.0029949326808658564,
-      "grad_norm": 0.09043970704078674,
+      "grad_norm": 0.08907917141914368,
       "learning_rate": 8.535533905932738e-05,
-      "loss": 6.9356,
+      "loss": 6.9358,
       "step": 14
     },
     {
       "epoch": 0.003208856443784846,
-      "grad_norm": 0.09768740832805634,
+      "grad_norm": 0.09633015841245651,
       "learning_rate": 8.296729075500344e-05,
-      "loss": 6.9315,
+      "loss": 6.9317,
       "step": 15
     },
     {
       "epoch": 0.0034227802067038357,
-      "grad_norm": 0.09449315816164017,
+      "grad_norm": 0.09162943065166473,
       "learning_rate": 8.043807145043604e-05,
-      "loss": 6.9324,
+      "loss": 6.9326,
       "step": 16
     },
     {
       "epoch": 0.003636703969622826,
-      "grad_norm": 0.10302135348320007,
+      "grad_norm": 0.10051411390304565,
       "learning_rate": 7.777851165098012e-05,
-      "loss": 6.9313,
+      "loss": 6.9315,
       "step": 17
     },
     {
       "epoch": 0.0038506277325418155,
-      "grad_norm": 0.10031016170978546,
+      "grad_norm": 0.09999406337738037,
       "learning_rate": 7.500000000000001e-05,
-      "loss": 6.9308,
+      "loss": 6.9309,
       "step": 18
     },
     {
       "epoch": 0.004064551495460805,
-      "grad_norm": 0.10906001180410385,
+      "grad_norm": 0.10973299294710159,
       "learning_rate": 7.211443451095007e-05,
-      "loss": 6.9313,
+      "loss": 6.9314,
       "step": 19
     },
     {
       "epoch": 0.004278475258379795,
-      "grad_norm": 0.11029664427042007,
+      "grad_norm": 0.10994168370962143,
       "learning_rate": 6.91341716182545e-05,
       "loss": 6.9305,
       "step": 20
     },
     {
       "epoch": 0.004492399021298785,
-      "grad_norm": 0.1134241446852684,
+      "grad_norm": 0.11387638747692108,
       "learning_rate": 6.607197326515808e-05,
       "loss": 6.9333,
       "step": 21
     },
     {
       "epoch": 0.004706322784217775,
-      "grad_norm": 0.12209273874759674,
+      "grad_norm": 0.11845920979976654,
       "learning_rate": 6.294095225512603e-05,
-      "loss": 6.9279,
+      "loss": 6.9282,
       "step": 22
     },
     {
       "epoch": 0.004920246547136764,
-      "grad_norm": 0.12280123680830002,
+      "grad_norm": 0.12084134668111801,
       "learning_rate": 5.9754516100806423e-05,
-      "loss": 6.9276,
+      "loss": 6.9278,
       "step": 23
     },
     {
       "epoch": 0.005134170310055754,
-      "grad_norm": 0.13325512409210205,
+      "grad_norm": 0.13196800649166107,
       "learning_rate": 5.6526309611002594e-05,
-      "loss": 6.9264,
+      "loss": 6.9267,
       "step": 24
     },
     {
       "epoch": 0.005348094072974744,
-      "grad_norm": 0.15282446146011353,
+      "grad_norm": 0.15287362039089203,
       "learning_rate": 5.327015646150716e-05,
       "loss": 6.9285,
       "step": 25
     },
     {
       "epoch": 0.005348094072974744,
-      "eval_loss": 6.928130626678467,
-      "eval_runtime": 20.6429,
-      "eval_samples_per_second": 1525.562,
-      "eval_steps_per_second": 190.719,
+      "eval_loss": 6.9282989501953125,
+      "eval_runtime": 23.0115,
+      "eval_samples_per_second": 1368.531,
+      "eval_steps_per_second": 171.088,
       "step": 25
-    },
-    {
-      "epoch": 0.005562017835893733,
-      "grad_norm": 0.09425940364599228,
-      "learning_rate": 5e-05,
-      "loss": 6.9305,
-      "step": 26
-    },
-    {
-      "epoch": 0.005775941598812723,
-      "grad_norm": 0.09901078045368195,
-      "learning_rate": 4.6729843538492847e-05,
-      "loss": 6.9293,
-      "step": 27
-    },
-    {
-      "epoch": 0.005989865361731713,
-      "grad_norm": 0.10344414412975311,
-      "learning_rate": 4.347369038899744e-05,
-      "loss": 6.9266,
-      "step": 28
-    },
-    {
-      "epoch": 0.0062037891246507024,
-      "grad_norm": 0.10215310752391815,
-      "learning_rate": 4.0245483899193595e-05,
-      "loss": 6.9274,
-      "step": 29
-    },
-    {
-      "epoch": 0.006417712887569692,
-      "grad_norm": 0.10918069630861282,
-      "learning_rate": 3.705904774487396e-05,
-      "loss": 6.9269,
-      "step": 30
-    },
-    {
-      "epoch": 0.006631636650488682,
-      "grad_norm": 0.1103460043668747,
-      "learning_rate": 3.392802673484193e-05,
-      "loss": 6.9258,
-      "step": 31
-    },
-    {
-      "epoch": 0.0068455604134076715,
-      "grad_norm": 0.11610613018274307,
-      "learning_rate": 3.086582838174551e-05,
-      "loss": 6.9251,
-      "step": 32
-    },
-    {
-      "epoch": 0.007059484176326661,
-      "grad_norm": 0.12197224795818329,
-      "learning_rate": 2.7885565489049946e-05,
-      "loss": 6.9268,
-      "step": 33
-    },
-    {
-      "epoch": 0.007273407939245652,
-      "grad_norm": 0.1161201074719429,
-      "learning_rate": 2.500000000000001e-05,
-      "loss": 6.9275,
-      "step": 34
-    },
-    {
-      "epoch": 0.007487331702164641,
-      "grad_norm": 0.13400213420391083,
-      "learning_rate": 2.2221488349019903e-05,
-      "loss": 6.9247,
-      "step": 35
-    },
-    {
-      "epoch": 0.007701255465083631,
-      "grad_norm": 0.13895855844020844,
-      "learning_rate": 1.9561928549563968e-05,
-      "loss": 6.9246,
-      "step": 36
-    },
-    {
-      "epoch": 0.00791517922800262,
-      "grad_norm": 0.1469612568616867,
-      "learning_rate": 1.703270924499656e-05,
-      "loss": 6.922,
-      "step": 37
-    },
-    {
-      "epoch": 0.00812910299092161,
-      "grad_norm": 0.11093045771121979,
-      "learning_rate": 1.4644660940672627e-05,
-      "loss": 6.927,
-      "step": 38
-    },
-    {
-      "epoch": 0.0083430267538406,
-      "grad_norm": 0.10132980346679688,
-      "learning_rate": 1.2408009626051137e-05,
-      "loss": 6.926,
-      "step": 39
-    },
-    {
-      "epoch": 0.00855695051675959,
-      "grad_norm": 0.10548317432403564,
-      "learning_rate": 1.0332332985438248e-05,
-      "loss": 6.9288,
-      "step": 40
-    },
-    {
-      "epoch": 0.00877087427967858,
-      "grad_norm": 0.10971340537071228,
-      "learning_rate": 8.426519384872733e-06,
-      "loss": 6.9246,
-      "step": 41
-    },
-    {
-      "epoch": 0.00898479804259757,
-      "grad_norm": 0.11398052424192429,
-      "learning_rate": 6.698729810778065e-06,
-      "loss": 6.9256,
-      "step": 42
-    },
-    {
-      "epoch": 0.00919872180551656,
-      "grad_norm": 0.11947134137153625,
-      "learning_rate": 5.156362923365588e-06,
-      "loss": 6.9251,
-      "step": 43
-    },
-    {
-      "epoch": 0.00941264556843555,
-      "grad_norm": 0.11277071386575699,
-      "learning_rate": 3.8060233744356633e-06,
-      "loss": 6.9225,
-      "step": 44
-    },
-    {
-      "epoch": 0.009626569331354539,
-      "grad_norm": 0.11898217350244522,
-      "learning_rate": 2.653493525244721e-06,
-      "loss": 6.9247,
-      "step": 45
-    },
-    {
-      "epoch": 0.009840493094273529,
-      "grad_norm": 0.12966850399971008,
-      "learning_rate": 1.70370868554659e-06,
-      "loss": 6.9218,
-      "step": 46
-    },
-    {
-      "epoch": 0.010054416857192518,
-      "grad_norm": 0.11691312491893768,
-      "learning_rate": 9.607359798384785e-07,
-      "loss": 6.9276,
-      "step": 47
-    },
-    {
-      "epoch": 0.010268340620111508,
-      "grad_norm": 0.13687504827976227,
-      "learning_rate": 4.277569313094809e-07,
-      "loss": 6.9221,
-      "step": 48
-    },
-    {
-      "epoch": 0.010482264383030498,
-      "grad_norm": 0.1413353681564331,
-      "learning_rate": 1.0705383806982606e-07,
-      "loss": 6.9211,
-      "step": 49
-    },
-    {
-      "epoch": 0.010696188145949487,
-      "grad_norm": 0.16661731898784637,
-      "learning_rate": 0.0,
-      "loss": 6.9214,
-      "step": 50
-    },
-    {
-      "epoch": 0.010696188145949487,
-      "eval_loss": 6.924656867980957,
-      "eval_runtime": 20.5821,
-      "eval_samples_per_second": 1530.067,
-      "eval_steps_per_second": 191.283,
-      "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": 5705957376000.0,
+  "total_flos": 2852978688000.0,
   "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:c64096d40126f031656961b5b5c97e590ef451fb8f9b5712c3cf492cbc825bc9
+oid sha256:88b5c315744df6dc63beea7a20ef2621b6518425fc9c600da4b1ff2f63186638
 size 6776