Training in progress, step 50, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "down_proj",
     "gate_proj",
     "up_proj",
-    "q_proj",
     "k_proj",
-    "o_proj"
+    "o_proj",
+    "q_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 sha256:87b613f8f3cbac32004a0f82bf7a98b97c14988e1571669946774462adc90965
+oid sha256:72df4dff72d80c7b31774bcf56de7c7ac6b4c77052afff19c0fae0e9b0976cb9
 size 432223744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9edc5d4e40059ab7fba7d57b74efcf2b5b729af4ec4fe050fc59b770729325c
+oid sha256:528f4c82885d0307b9bc926429960737d4c1a4e569b0feef10021cd2dede2ddf
 size 864785974

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3474f616c022c5123bb639254ff627c2e324cf238eb12ebf6befd7f1dd8545f6
+oid sha256:92c7b1bef3a6dc7acfc05f182236f46296de11af2d5fab6a27da42a8370ae3f8
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d217acfa2ab6c1a1bf289a1bc1afc85123bb46a4956c8dab80ae96f0ae89dc9b
+oid sha256:f1695ec540798f9ddbf4216a16614528616d1af8d09b5d87be0c5958c49503a1
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df10e3480207a5c0f871aa47ed269c00e95ce1769a77ce26b3381f5746b5b05d
+oid sha256:5e7ff66f1cfef25da577469cdbd6892db234d947b4da7b72381ebfde38757869
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0525e9389f19e558929faa912f5f4def598130dd807aa12ef4ad30fd4ccecf6b
+oid sha256:154d504b56cfb9ecdc771d7182a4522044e081041e160ce442103f56739dca8e
 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": 0.0005636036512441933,
+  "best_metric": 0.0005211062380112708,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.003663070752211579,
+  "epoch": 0.007326141504423158,
   "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": 0.00014652283008846317,
-      "grad_norm": 67.46258544921875,
+      "grad_norm": 66.07504272460938,
       "learning_rate": 5e-05,
       "loss": 7.3346,
       "step": 1
@@ -18,186 +18,369 @@
     {
       "epoch": 0.00014652283008846317,
       "eval_loss": 7.334836959838867,
-      "eval_runtime": 2450.429,
-      "eval_samples_per_second": 18.763,
-      "eval_steps_per_second": 2.346,
+      "eval_runtime": 2440.3684,
+      "eval_samples_per_second": 18.841,
+      "eval_steps_per_second": 2.355,
       "step": 1
     },
     {
       "epoch": 0.00029304566017692633,
-      "grad_norm": 67.42963409423828,
+      "grad_norm": 66.05978393554688,
       "learning_rate": 0.0001,
       "loss": 7.3346,
       "step": 2
     },
     {
       "epoch": 0.0004395684902653895,
-      "grad_norm": 17.986305236816406,
+      "grad_norm": 18.386962890625,
       "learning_rate": 9.989294616193017e-05,
-      "loss": 2.2234,
+      "loss": 2.2612,
       "step": 3
     },
     {
       "epoch": 0.0005860913203538527,
-      "grad_norm": 10.093182563781738,
+      "grad_norm": 9.960482597351074,
       "learning_rate": 9.957224306869053e-05,
-      "loss": 0.9459,
+      "loss": 0.9454,
       "step": 4
     },
     {
       "epoch": 0.0007326141504423158,
-      "grad_norm": 4.0528645515441895,
+      "grad_norm": 4.011445999145508,
       "learning_rate": 9.903926402016153e-05,
-      "loss": 0.2877,
+      "loss": 0.2833,
       "step": 5
     },
     {
       "epoch": 0.000879136980530779,
-      "grad_norm": 1.00792396068573,
+      "grad_norm": 1.1179792881011963,
       "learning_rate": 9.829629131445342e-05,
-      "loss": 0.0218,
+      "loss": 0.0223,
       "step": 6
     },
     {
       "epoch": 0.001025659810619242,
-      "grad_norm": 0.8242140412330627,
+      "grad_norm": 2.508209228515625,
       "learning_rate": 9.73465064747553e-05,
-      "loss": 0.0026,
+      "loss": 0.0052,
       "step": 7
     },
     {
       "epoch": 0.0011721826407077053,
-      "grad_norm": 0.01713043637573719,
+      "grad_norm": 0.06485740095376968,
       "learning_rate": 9.619397662556435e-05,
       "loss": 0.0002,
       "step": 8
     },
     {
       "epoch": 0.0013187054707961684,
-      "grad_norm": 0.0027765310369431973,
+      "grad_norm": 0.013003971427679062,
       "learning_rate": 9.484363707663442e-05,
-      "loss": 0.0,
+      "loss": 0.0001,
       "step": 9
     },
     {
       "epoch": 0.0014652283008846315,
-      "grad_norm": 0.005665022414177656,
+      "grad_norm": 0.014595498330891132,
       "learning_rate": 9.330127018922194e-05,
       "loss": 0.0,
       "step": 10
     },
     {
       "epoch": 0.0016117511309730948,
-      "grad_norm": 0.017976634204387665,
+      "grad_norm": 0.003476336831226945,
       "learning_rate": 9.157348061512727e-05,
       "loss": 0.0,
       "step": 11
     },
     {
       "epoch": 0.001758273961061558,
-      "grad_norm": 0.006979241501539946,
+      "grad_norm": 0.006427183747291565,
       "learning_rate": 8.966766701456177e-05,
       "loss": 0.0,
       "step": 12
     },
     {
       "epoch": 0.001904796791150021,
-      "grad_norm": 0.0015923851169645786,
+      "grad_norm": 0.007890215143561363,
       "learning_rate": 8.759199037394887e-05,
       "loss": 0.0,
       "step": 13
     },
     {
       "epoch": 0.002051319621238484,
-      "grad_norm": 0.0010537989437580109,
+      "grad_norm": 0.005319513380527496,
       "learning_rate": 8.535533905932738e-05,
       "loss": 0.0,
       "step": 14
     },
     {
       "epoch": 0.0021978424513269474,
-      "grad_norm": 0.0012975798454135656,
+      "grad_norm": 0.0027053034864366055,
       "learning_rate": 8.296729075500344e-05,
       "loss": 0.0,
       "step": 15
     },
     {
       "epoch": 0.0023443652814154107,
-      "grad_norm": 0.0013601743848994374,
+      "grad_norm": 0.001441505504772067,
       "learning_rate": 8.043807145043604e-05,
       "loss": 0.0,
       "step": 16
     },
     {
       "epoch": 0.0024908881115038735,
-      "grad_norm": 0.0014510821783915162,
+      "grad_norm": 0.0010616765357553959,
       "learning_rate": 7.777851165098012e-05,
       "loss": 0.0,
       "step": 17
     },
     {
       "epoch": 0.002637410941592337,
-      "grad_norm": 0.0015000648563727736,
+      "grad_norm": 0.001055700471624732,
       "learning_rate": 7.500000000000001e-05,
       "loss": 0.0,
       "step": 18
     },
     {
       "epoch": 0.0027839337716808,
-      "grad_norm": 0.0012648840202018619,
+      "grad_norm": 0.0010651879711076617,
       "learning_rate": 7.211443451095007e-05,
       "loss": 0.0,
       "step": 19
     },
     {
       "epoch": 0.002930456601769263,
-      "grad_norm": 0.0009284365805797279,
+      "grad_norm": 0.0008909179596230388,
       "learning_rate": 6.91341716182545e-05,
       "loss": 0.0,
       "step": 20
     },
     {
       "epoch": 0.0030769794318577263,
-      "grad_norm": 0.0007029483676888049,
+      "grad_norm": 0.0007905272650532424,
       "learning_rate": 6.607197326515808e-05,
       "loss": 0.0,
       "step": 21
     },
     {
       "epoch": 0.0032235022619461896,
-      "grad_norm": 0.0004989892477169633,
+      "grad_norm": 0.000660909223370254,
       "learning_rate": 6.294095225512603e-05,
       "loss": 0.0,
       "step": 22
     },
     {
       "epoch": 0.0033700250920346525,
-      "grad_norm": 0.0003535033611115068,
+      "grad_norm": 0.0004630742478184402,
       "learning_rate": 5.9754516100806423e-05,
       "loss": 0.0,
       "step": 23
     },
     {
       "epoch": 0.003516547922123116,
-      "grad_norm": 0.0002854061604011804,
+      "grad_norm": 0.0003868404310196638,
       "learning_rate": 5.6526309611002594e-05,
       "loss": 0.0,
       "step": 24
     },
     {
       "epoch": 0.003663070752211579,
-      "grad_norm": 0.0002517289249226451,
+      "grad_norm": 0.0003109298413619399,
       "learning_rate": 5.327015646150716e-05,
       "loss": 0.0,
       "step": 25
     },
     {
       "epoch": 0.003663070752211579,
-      "eval_loss": 0.0005636036512441933,
-      "eval_runtime": 2444.0569,
-      "eval_samples_per_second": 18.812,
-      "eval_steps_per_second": 2.352,
+      "eval_loss": 0.0005211062380112708,
+      "eval_runtime": 2443.3333,
+      "eval_samples_per_second": 18.818,
+      "eval_steps_per_second": 2.353,
       "step": 25
+    },
+    {
+      "epoch": 0.003809593582300042,
+      "grad_norm": 0.000262366869719699,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.003956116412388505,
+      "grad_norm": 0.00021212754654698074,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.004102639242476968,
+      "grad_norm": 0.0002156026748707518,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.004249162072565432,
+      "grad_norm": 0.0001568874140502885,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.004395684902653895,
+      "grad_norm": 0.0001437966711819172,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.004542207732742358,
+      "grad_norm": 0.00011910089961020276,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.004688730562830821,
+      "grad_norm": 0.00010500229109311476,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.004835253392919284,
+      "grad_norm": 0.00010075217869598418,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.004981776223007747,
+      "grad_norm": 9.148717799689621e-05,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.005128299053096211,
+      "grad_norm": 8.78409409779124e-05,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.005274821883184674,
+      "grad_norm": 8.30805511213839e-05,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.0054213447132731366,
+      "grad_norm": 7.874202128732577e-05,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.0055678675433616,
+      "grad_norm": 6.860808935016394e-05,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.005714390373450063,
+      "grad_norm": 7.494084275094792e-05,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.005860913203538526,
+      "grad_norm": 6.717813812429085e-05,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.00600743603362699,
+      "grad_norm": 6.408966874005273e-05,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.006153958863715453,
+      "grad_norm": 6.148488319013268e-05,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.0063004816938039155,
+      "grad_norm": 6.417003169190139e-05,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.006447004523892379,
+      "grad_norm": 6.637047772528604e-05,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.006593527353980842,
+      "grad_norm": 6.184045923873782e-05,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.006740050184069305,
+      "grad_norm": 7.047447434160858e-05,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.006886573014157769,
+      "grad_norm": 5.9824829804711044e-05,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.007033095844246232,
+      "grad_norm": 5.8508769143372774e-05,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.0071796186743346944,
+      "grad_norm": 6.050009324098937e-05,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.007326141504423158,
+      "grad_norm": 6.264998955884948e-05,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.007326141504423158,
+      "eval_loss": 0.0005369415157474577,
+      "eval_runtime": 2441.5705,
+      "eval_samples_per_second": 18.831,
+      "eval_steps_per_second": 2.354,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,7 +395,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.315690861756416e+17,
+  "total_flos": 6.631381723512832e+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 sha256:4890609b6bb07cc885584bd813aee0e59702d7c9bfaeb0240be3c96e1382ae65
+oid sha256:fdbadb3d73dc147a8615f83812e3216c6fad02d8d1e99a9c0d82882af039b8da
 size 6776