Training in progress, step 50, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "q_proj",
-    "o_proj",
-    "up_proj",
     "down_proj",
+    "v_proj",
     "gate_proj",
-    "v_proj"
+    "up_proj",
+    "q_proj",
+    "k_proj",
+    "o_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 sha256:8da7b557bd1a08436e7decaea7bf2b9ec05357f97962ceedc46c9267a6c5a90b
+oid sha256:e17665ce5a09cfa29e3d3dcb84f65d1d7dacfd5b1884c75a226827ecf58dc0b8
 size 239536272

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94466bbc175489e53e833f1250484651047fc9e4ff1b197de629de091cb46290
+oid sha256:5111106d6eced45466e27e3af0a74820e49a678ebe149dda5234146fabd83f72
 size 479362682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37e823d6e886dfe52c5d0b3bf8492df1504bd655fd41bf5ca88daf918114831d
+oid sha256:bd52ce6e92a34e2c2d6f3cb095d5f7f55b0154704c1f5206749a92ec710927c1
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb717f22cf4c5edb5be69af113b541cc3d239bb37386e0a5bfe3ae3820cef506
+oid sha256:a4a8b67b9f35a71efd654e0e07bb2b6b50f76d05357cf120ced65d6e3b1af31d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be508f7c6fddf829f7fa13480b7a5393394cf16f516393ab3fee4969c8012077
+oid sha256:b37dcc86e5703b281a078b84ad9fedb889d0fd996a5d54dee419547ec986b587
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ad66be3026d320385439dd873fffa16c91f09bb4ffe190dbafbd3f82bd37af7
+oid sha256:4da2a687fade7da0a4e847e38120e89c8257ce234cd78264c4980d8935ca0df6
 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": 0.7032530307769775,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.411522633744856,
+  "best_metric": 0.6561319231987,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.823045267489712,
   "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": 0.01646090534979424,
-      "grad_norm": 2.1076626777648926,
+      "grad_norm": 2.0745296478271484,
       "learning_rate": 5e-05,
       "loss": 2.8513,
       "step": 1
@@ -18,186 +18,369 @@
     {
       "epoch": 0.01646090534979424,
       "eval_loss": 3.8586878776550293,
-      "eval_runtime": 9.2637,
-      "eval_samples_per_second": 44.259,
-      "eval_steps_per_second": 5.613,
+      "eval_runtime": 9.15,
+      "eval_samples_per_second": 44.809,
+      "eval_steps_per_second": 5.683,
       "step": 1
     },
     {
       "epoch": 0.03292181069958848,
-      "grad_norm": 4.27289342880249,
+      "grad_norm": 4.245978832244873,
       "learning_rate": 0.0001,
       "loss": 3.7586,
       "step": 2
     },
     {
       "epoch": 0.04938271604938271,
-      "grad_norm": 3.2222888469696045,
+      "grad_norm": 3.185753345489502,
       "learning_rate": 9.989294616193017e-05,
-      "loss": 2.3785,
+      "loss": 2.3779,
       "step": 3
     },
     {
       "epoch": 0.06584362139917696,
-      "grad_norm": 1.957718014717102,
+      "grad_norm": 1.9672001600265503,
       "learning_rate": 9.957224306869053e-05,
-      "loss": 2.0282,
+      "loss": 2.0297,
       "step": 4
     },
     {
       "epoch": 0.0823045267489712,
-      "grad_norm": 1.7186223268508911,
+      "grad_norm": 1.712628960609436,
       "learning_rate": 9.903926402016153e-05,
-      "loss": 1.8344,
+      "loss": 1.8397,
       "step": 5
     },
     {
       "epoch": 0.09876543209876543,
-      "grad_norm": 1.804044485092163,
+      "grad_norm": 1.813711166381836,
       "learning_rate": 9.829629131445342e-05,
-      "loss": 1.8234,
+      "loss": 1.8286,
       "step": 6
     },
     {
       "epoch": 0.11522633744855967,
-      "grad_norm": 1.2378959655761719,
+      "grad_norm": 1.2593228816986084,
       "learning_rate": 9.73465064747553e-05,
-      "loss": 1.4513,
+      "loss": 1.4568,
       "step": 7
     },
     {
       "epoch": 0.13168724279835392,
-      "grad_norm": 1.2065438032150269,
+      "grad_norm": 1.2200363874435425,
       "learning_rate": 9.619397662556435e-05,
-      "loss": 1.3096,
+      "loss": 1.3131,
       "step": 8
     },
     {
       "epoch": 0.14814814814814814,
-      "grad_norm": 1.109233021736145,
+      "grad_norm": 1.1022920608520508,
       "learning_rate": 9.484363707663442e-05,
-      "loss": 1.2455,
+      "loss": 1.2503,
       "step": 9
     },
     {
       "epoch": 0.1646090534979424,
-      "grad_norm": 1.291716456413269,
+      "grad_norm": 1.273776650428772,
       "learning_rate": 9.330127018922194e-05,
-      "loss": 1.0978,
+      "loss": 1.1055,
       "step": 10
     },
     {
       "epoch": 0.18106995884773663,
-      "grad_norm": 1.3139619827270508,
+      "grad_norm": 1.3083699941635132,
       "learning_rate": 9.157348061512727e-05,
-      "loss": 0.9933,
+      "loss": 1.0066,
       "step": 11
     },
     {
       "epoch": 0.19753086419753085,
-      "grad_norm": 1.085813283920288,
+      "grad_norm": 1.1210218667984009,
       "learning_rate": 8.966766701456177e-05,
-      "loss": 0.8552,
+      "loss": 0.8673,
       "step": 12
     },
     {
       "epoch": 0.2139917695473251,
-      "grad_norm": 0.7361060380935669,
+      "grad_norm": 0.7338252663612366,
       "learning_rate": 8.759199037394887e-05,
-      "loss": 0.9337,
+      "loss": 0.9367,
       "step": 13
     },
     {
       "epoch": 0.23045267489711935,
-      "grad_norm": 2.214524984359741,
+      "grad_norm": 2.1798887252807617,
       "learning_rate": 8.535533905932738e-05,
-      "loss": 1.6196,
+      "loss": 1.6209,
       "step": 14
     },
     {
       "epoch": 0.24691358024691357,
-      "grad_norm": 1.789655327796936,
+      "grad_norm": 1.767669677734375,
       "learning_rate": 8.296729075500344e-05,
-      "loss": 0.7971,
+      "loss": 0.7957,
       "step": 15
     },
     {
       "epoch": 0.26337448559670784,
-      "grad_norm": 1.104480504989624,
+      "grad_norm": 1.1363743543624878,
       "learning_rate": 8.043807145043604e-05,
-      "loss": 0.7159,
+      "loss": 0.7195,
       "step": 16
     },
     {
       "epoch": 0.27983539094650206,
-      "grad_norm": 0.9207172989845276,
+      "grad_norm": 0.9281293749809265,
       "learning_rate": 7.777851165098012e-05,
-      "loss": 0.7,
+      "loss": 0.7021,
       "step": 17
     },
     {
       "epoch": 0.2962962962962963,
-      "grad_norm": 0.8482317328453064,
+      "grad_norm": 0.8513988852500916,
       "learning_rate": 7.500000000000001e-05,
-      "loss": 0.6445,
+      "loss": 0.6473,
       "step": 18
     },
     {
       "epoch": 0.31275720164609055,
-      "grad_norm": 0.8116461634635925,
+      "grad_norm": 0.8034453988075256,
       "learning_rate": 7.211443451095007e-05,
-      "loss": 0.6966,
+      "loss": 0.6974,
       "step": 19
     },
     {
       "epoch": 0.3292181069958848,
-      "grad_norm": 0.7192047238349915,
+      "grad_norm": 0.7160072922706604,
       "learning_rate": 6.91341716182545e-05,
-      "loss": 0.5805,
+      "loss": 0.5821,
       "step": 20
     },
     {
       "epoch": 0.345679012345679,
-      "grad_norm": 0.5720171332359314,
+      "grad_norm": 0.5699191093444824,
       "learning_rate": 6.607197326515808e-05,
-      "loss": 0.706,
+      "loss": 0.7074,
       "step": 21
     },
     {
       "epoch": 0.36213991769547327,
-      "grad_norm": 0.5808382630348206,
+      "grad_norm": 0.5850489735603333,
       "learning_rate": 6.294095225512603e-05,
-      "loss": 0.7216,
+      "loss": 0.7256,
       "step": 22
     },
     {
       "epoch": 0.3786008230452675,
-      "grad_norm": 0.5952896475791931,
+      "grad_norm": 0.5858528017997742,
       "learning_rate": 5.9754516100806423e-05,
-      "loss": 0.6375,
+      "loss": 0.6395,
       "step": 23
     },
     {
       "epoch": 0.3950617283950617,
-      "grad_norm": 0.5605278015136719,
+      "grad_norm": 0.5442656874656677,
       "learning_rate": 5.6526309611002594e-05,
-      "loss": 0.7344,
+      "loss": 0.7342,
       "step": 24
     },
     {
       "epoch": 0.411522633744856,
-      "grad_norm": 0.49808284640312195,
+      "grad_norm": 0.49498945474624634,
       "learning_rate": 5.327015646150716e-05,
-      "loss": 0.5986,
+      "loss": 0.5981,
       "step": 25
     },
     {
       "epoch": 0.411522633744856,
-      "eval_loss": 0.7032530307769775,
-      "eval_runtime": 9.2958,
-      "eval_samples_per_second": 44.106,
-      "eval_steps_per_second": 5.594,
+      "eval_loss": 0.7050751447677612,
+      "eval_runtime": 9.1683,
+      "eval_samples_per_second": 44.719,
+      "eval_steps_per_second": 5.672,
       "step": 25
+    },
+    {
+      "epoch": 0.4279835390946502,
+      "grad_norm": 1.625022053718567,
+      "learning_rate": 5e-05,
+      "loss": 1.3808,
+      "step": 26
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.6726037263870239,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.6507,
+      "step": 27
+    },
+    {
+      "epoch": 0.4609053497942387,
+      "grad_norm": 0.6659382581710815,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.5273,
+      "step": 28
+    },
+    {
+      "epoch": 0.4773662551440329,
+      "grad_norm": 0.698225736618042,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.5542,
+      "step": 29
+    },
+    {
+      "epoch": 0.49382716049382713,
+      "grad_norm": 0.6371154189109802,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.6459,
+      "step": 30
+    },
+    {
+      "epoch": 0.5102880658436214,
+      "grad_norm": 0.5590847730636597,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.685,
+      "step": 31
+    },
+    {
+      "epoch": 0.5267489711934157,
+      "grad_norm": 0.4336808919906616,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.5531,
+      "step": 32
+    },
+    {
+      "epoch": 0.5432098765432098,
+      "grad_norm": 0.5399011969566345,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.6532,
+      "step": 33
+    },
+    {
+      "epoch": 0.5596707818930041,
+      "grad_norm": 0.4386877417564392,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.6143,
+      "step": 34
+    },
+    {
+      "epoch": 0.5761316872427984,
+      "grad_norm": 0.5017386078834534,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.6102,
+      "step": 35
+    },
+    {
+      "epoch": 0.5925925925925926,
+      "grad_norm": 0.6162391304969788,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.6991,
+      "step": 36
+    },
+    {
+      "epoch": 0.6090534979423868,
+      "grad_norm": 0.6711835265159607,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.693,
+      "step": 37
+    },
+    {
+      "epoch": 0.6255144032921811,
+      "grad_norm": 0.5756227970123291,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.8572,
+      "step": 38
+    },
+    {
+      "epoch": 0.6419753086419753,
+      "grad_norm": 2.781473398208618,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.7294,
+      "step": 39
+    },
+    {
+      "epoch": 0.6584362139917695,
+      "grad_norm": 0.6352210640907288,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.5651,
+      "step": 40
+    },
+    {
+      "epoch": 0.6748971193415638,
+      "grad_norm": 0.47287803888320923,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.5217,
+      "step": 41
+    },
+    {
+      "epoch": 0.691358024691358,
+      "grad_norm": 0.5060291886329651,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.5924,
+      "step": 42
+    },
+    {
+      "epoch": 0.7078189300411523,
+      "grad_norm": 0.434349000453949,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.529,
+      "step": 43
+    },
+    {
+      "epoch": 0.7242798353909465,
+      "grad_norm": 0.5044702291488647,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.5424,
+      "step": 44
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 0.42993804812431335,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.6676,
+      "step": 45
+    },
+    {
+      "epoch": 0.757201646090535,
+      "grad_norm": 0.4085606634616852,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.5848,
+      "step": 46
+    },
+    {
+      "epoch": 0.7736625514403292,
+      "grad_norm": 0.4246390163898468,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.6776,
+      "step": 47
+    },
+    {
+      "epoch": 0.7901234567901234,
+      "grad_norm": 0.35061928629875183,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.5528,
+      "step": 48
+    },
+    {
+      "epoch": 0.8065843621399177,
+      "grad_norm": 0.4323487877845764,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.6973,
+      "step": 49
+    },
+    {
+      "epoch": 0.823045267489712,
+      "grad_norm": 0.4282306730747223,
+      "learning_rate": 0.0,
+      "loss": 0.5867,
+      "step": 50
+    },
+    {
+      "epoch": 0.823045267489712,
+      "eval_loss": 0.6561319231987,
+      "eval_runtime": 9.1655,
+      "eval_samples_per_second": 44.733,
+      "eval_steps_per_second": 5.673,
+      "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": 1.2253921316909875e+17,
+  "total_flos": 2.450087619686564e+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 sha256:94f8966a7f5610ce3154bf3af6bc87a6aa3dca284fbee83e288364d669bb4725
+oid sha256:85e8dfa1540ca3fe1a9279429500b8935e685568e77962b57855c979b3e8ce15
 size 6776