Training in progress, step 50, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "q_proj",
-    "gate_proj",
     "o_proj",
     "down_proj",
+    "gate_proj",
+    "k_proj",
+    "up_proj",
     "v_proj",
-    "k_proj"
+    "q_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 sha256:0aecb923fb0e532c6129fae6d8d65b0e42c75564a2ef3e2534b3007cc79cd758
+oid sha256:641eb0d184ee62ddb72b2621ad6e78f932ea4c29eca641c702063c63c6f10f77
 size 859909312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8963bcee51704fc930d5ee8cba7fccbebb9e7ee3bbbf1fbcc54ebbaad4746fe4
+oid sha256:52bf5ee5bd5dbb1359f2d2bd6532253f49d51d51c343323744f90193aa9e28d9
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7496acb7f3d21e9e3dc9774f243da1bfb7a1b6ff901727f4a97fe270f5a8988
+oid sha256:5309eed67eeea06b78ee857e9b0fe08cba68bd47353ec8e6b6b0040c1705e32f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e468e1c7a88d99ea3270dc458af265ac667b4e5cf19bc76630dfa9bc4cf89bd4
+oid sha256:44dc1134e34e0d331bd05c06d0f720a15d94ad275739f118ea86ec35eed3413b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69a1f3489a60efef5ab7b305f27c36322b8802f43a83c332f5fc6bae23777a2b
+oid sha256:db08d075ad785271ff43601a7e958dcd0bbc2cfd9b146573ed5c073b531d48df
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bcea3a12a79a0059c86ee82f36ed5b0fa541b9c2615f70470709cf3ac836663
+oid sha256:8f49675c0c65fbf2387e069b6561b68821e598baf2eaa39817fe72cc35aaba80
 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

@@ -1,203 +1,386 @@
 {
-  "best_metric": 1.753453016281128,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.02689437235258522,
+  "best_metric": 1.7394925355911255,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.05378874470517044,
   "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": 0.0010757748941034088,
-      "grad_norm": 2.889035224914551,
+      "grad_norm": 1.6709057092666626,
       "learning_rate": 5e-05,
-      "loss": 1.7307,
+      "loss": 1.707,
       "step": 1
     },
     {
       "epoch": 0.0010757748941034088,
-      "eval_loss": 2.065730094909668,
-      "eval_runtime": 186.3032,
-      "eval_samples_per_second": 33.617,
-      "eval_steps_per_second": 4.203,
+      "eval_loss": 2.019153356552124,
+      "eval_runtime": 186.2275,
+      "eval_samples_per_second": 33.631,
+      "eval_steps_per_second": 4.205,
       "step": 1
     },
     {
       "epoch": 0.0021515497882068175,
-      "grad_norm": 2.8928565979003906,
+      "grad_norm": 1.8899304866790771,
       "learning_rate": 0.0001,
-      "loss": 1.8653,
+      "loss": 1.8408,
       "step": 2
     },
     {
       "epoch": 0.0032273246823102267,
-      "grad_norm": 1.6839524507522583,
+      "grad_norm": 1.4666272401809692,
       "learning_rate": 9.989294616193017e-05,
-      "loss": 1.756,
+      "loss": 1.7696,
       "step": 3
     },
     {
       "epoch": 0.004303099576413635,
-      "grad_norm": 0.8242851495742798,
+      "grad_norm": 0.9372745752334595,
       "learning_rate": 9.957224306869053e-05,
-      "loss": 1.7457,
+      "loss": 1.7414,
       "step": 4
     },
     {
       "epoch": 0.005378874470517044,
-      "grad_norm": 1.0334848165512085,
+      "grad_norm": 0.8082295656204224,
       "learning_rate": 9.903926402016153e-05,
-      "loss": 1.7532,
+      "loss": 1.7415,
       "step": 5
     },
     {
       "epoch": 0.006454649364620453,
-      "grad_norm": 0.7117134928703308,
+      "grad_norm": 0.9279489517211914,
       "learning_rate": 9.829629131445342e-05,
-      "loss": 1.7827,
+      "loss": 1.7757,
       "step": 6
     },
     {
       "epoch": 0.007530424258723862,
-      "grad_norm": 0.7202480435371399,
+      "grad_norm": 0.701418936252594,
       "learning_rate": 9.73465064747553e-05,
-      "loss": 1.8289,
+      "loss": 1.8196,
       "step": 7
     },
     {
       "epoch": 0.00860619915282727,
-      "grad_norm": 0.6732454299926758,
+      "grad_norm": 0.688548743724823,
       "learning_rate": 9.619397662556435e-05,
-      "loss": 1.7357,
+      "loss": 1.7341,
       "step": 8
     },
     {
       "epoch": 0.00968197404693068,
-      "grad_norm": 0.6462610960006714,
+      "grad_norm": 0.6612863540649414,
       "learning_rate": 9.484363707663442e-05,
-      "loss": 1.7847,
+      "loss": 1.7848,
       "step": 9
     },
     {
       "epoch": 0.010757748941034088,
-      "grad_norm": 0.7184572815895081,
+      "grad_norm": 0.6995035409927368,
       "learning_rate": 9.330127018922194e-05,
-      "loss": 1.8445,
+      "loss": 1.8447,
       "step": 10
     },
     {
       "epoch": 0.011833523835137498,
-      "grad_norm": 0.7928162813186646,
+      "grad_norm": 0.7706447243690491,
       "learning_rate": 9.157348061512727e-05,
-      "loss": 1.8327,
+      "loss": 1.8312,
       "step": 11
     },
     {
       "epoch": 0.012909298729240907,
-      "grad_norm": 0.9331445693969727,
+      "grad_norm": 0.9608161449432373,
       "learning_rate": 8.966766701456177e-05,
-      "loss": 2.0023,
+      "loss": 2.0029,
       "step": 12
     },
     {
       "epoch": 0.013985073623344316,
-      "grad_norm": 1.8583245277404785,
+      "grad_norm": 1.8199213743209839,
       "learning_rate": 8.759199037394887e-05,
-      "loss": 1.6557,
+      "loss": 1.6517,
       "step": 13
     },
     {
       "epoch": 0.015060848517447724,
-      "grad_norm": 1.4030020236968994,
+      "grad_norm": 1.3464016914367676,
       "learning_rate": 8.535533905932738e-05,
-      "loss": 1.6399,
+      "loss": 1.6332,
       "step": 14
     },
     {
       "epoch": 0.016136623411551133,
-      "grad_norm": 1.2228798866271973,
+      "grad_norm": 0.96041339635849,
       "learning_rate": 8.296729075500344e-05,
-      "loss": 1.637,
+      "loss": 1.6261,
       "step": 15
     },
     {
       "epoch": 0.01721239830565454,
-      "grad_norm": 0.8515083193778992,
+      "grad_norm": 0.7431668043136597,
       "learning_rate": 8.043807145043604e-05,
-      "loss": 1.6325,
+      "loss": 1.6273,
       "step": 16
     },
     {
       "epoch": 0.01828817319975795,
-      "grad_norm": 0.6020737290382385,
+      "grad_norm": 0.560585618019104,
       "learning_rate": 7.777851165098012e-05,
-      "loss": 1.6861,
+      "loss": 1.6822,
       "step": 17
     },
     {
       "epoch": 0.01936394809386136,
-      "grad_norm": 0.658804714679718,
+      "grad_norm": 0.5964136123657227,
       "learning_rate": 7.500000000000001e-05,
-      "loss": 1.7261,
+      "loss": 1.7219,
       "step": 18
     },
     {
       "epoch": 0.02043972298796477,
-      "grad_norm": 0.6308284997940063,
+      "grad_norm": 0.6002236604690552,
       "learning_rate": 7.211443451095007e-05,
-      "loss": 1.7423,
+      "loss": 1.7398,
       "step": 19
     },
     {
       "epoch": 0.021515497882068177,
-      "grad_norm": 0.6279967427253723,
+      "grad_norm": 0.6054794788360596,
       "learning_rate": 6.91341716182545e-05,
-      "loss": 1.7781,
+      "loss": 1.778,
       "step": 20
     },
     {
       "epoch": 0.022591272776171584,
-      "grad_norm": 0.6446429491043091,
+      "grad_norm": 0.6320491433143616,
       "learning_rate": 6.607197326515808e-05,
-      "loss": 1.747,
+      "loss": 1.7474,
       "step": 21
     },
     {
       "epoch": 0.023667047670274995,
-      "grad_norm": 0.6265982985496521,
+      "grad_norm": 0.6241698265075684,
       "learning_rate": 6.294095225512603e-05,
-      "loss": 1.8178,
+      "loss": 1.8189,
       "step": 22
     },
     {
       "epoch": 0.024742822564378403,
-      "grad_norm": 0.695231556892395,
+      "grad_norm": 0.7055386304855347,
       "learning_rate": 5.9754516100806423e-05,
-      "loss": 1.7954,
+      "loss": 1.7957,
       "step": 23
     },
     {
       "epoch": 0.025818597458481814,
-      "grad_norm": 0.7961277365684509,
+      "grad_norm": 0.8027210235595703,
       "learning_rate": 5.6526309611002594e-05,
-      "loss": 1.9499,
+      "loss": 1.9507,
       "step": 24
     },
     {
       "epoch": 0.02689437235258522,
-      "grad_norm": 1.026402235031128,
+      "grad_norm": 1.0420467853546143,
       "learning_rate": 5.327015646150716e-05,
-      "loss": 2.1511,
+      "loss": 2.1519,
       "step": 25
     },
     {
       "epoch": 0.02689437235258522,
-      "eval_loss": 1.753453016281128,
-      "eval_runtime": 186.4029,
-      "eval_samples_per_second": 33.599,
-      "eval_steps_per_second": 4.201,
+      "eval_loss": 1.7508697509765625,
+      "eval_runtime": 186.2853,
+      "eval_samples_per_second": 33.62,
+      "eval_steps_per_second": 4.203,
       "step": 25
+    },
+    {
+      "epoch": 0.027970147246688632,
+      "grad_norm": 0.6345541477203369,
+      "learning_rate": 5e-05,
+      "loss": 1.5864,
+      "step": 26
+    },
+    {
+      "epoch": 0.02904592214079204,
+      "grad_norm": 0.5340394377708435,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.555,
+      "step": 27
+    },
+    {
+      "epoch": 0.030121697034895447,
+      "grad_norm": 0.49378207325935364,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.6126,
+      "step": 28
+    },
+    {
+      "epoch": 0.031197471928998858,
+      "grad_norm": 0.4962691068649292,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.6681,
+      "step": 29
+    },
+    {
+      "epoch": 0.032273246823102265,
+      "grad_norm": 0.490527480840683,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.7026,
+      "step": 30
+    },
+    {
+      "epoch": 0.033349021717205676,
+      "grad_norm": 0.49440085887908936,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.6943,
+      "step": 31
+    },
+    {
+      "epoch": 0.03442479661130908,
+      "grad_norm": 0.5249375700950623,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.7494,
+      "step": 32
+    },
+    {
+      "epoch": 0.03550057150541249,
+      "grad_norm": 0.5410753488540649,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.7389,
+      "step": 33
+    },
+    {
+      "epoch": 0.0365763463995159,
+      "grad_norm": 0.5691052675247192,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.7568,
+      "step": 34
+    },
+    {
+      "epoch": 0.03765212129361931,
+      "grad_norm": 0.628642201423645,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.8005,
+      "step": 35
+    },
+    {
+      "epoch": 0.03872789618772272,
+      "grad_norm": 0.6629976034164429,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.8407,
+      "step": 36
+    },
+    {
+      "epoch": 0.03980367108182613,
+      "grad_norm": 0.8179542422294617,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.9433,
+      "step": 37
+    },
+    {
+      "epoch": 0.04087944597592954,
+      "grad_norm": 0.6521536707878113,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.6141,
+      "step": 38
+    },
+    {
+      "epoch": 0.04195522087003294,
+      "grad_norm": 0.5380288362503052,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.6136,
+      "step": 39
+    },
+    {
+      "epoch": 0.043030995764136354,
+      "grad_norm": 0.505171000957489,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.5648,
+      "step": 40
+    },
+    {
+      "epoch": 0.044106770658239765,
+      "grad_norm": 0.509820818901062,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.6574,
+      "step": 41
+    },
+    {
+      "epoch": 0.04518254555234317,
+      "grad_norm": 0.5152492523193359,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.7135,
+      "step": 42
+    },
+    {
+      "epoch": 0.04625832044644658,
+      "grad_norm": 0.4926588535308838,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.6862,
+      "step": 43
+    },
+    {
+      "epoch": 0.04733409534054999,
+      "grad_norm": 0.5057544708251953,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.7803,
+      "step": 44
+    },
+    {
+      "epoch": 0.0484098702346534,
+      "grad_norm": 0.5117193460464478,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.6953,
+      "step": 45
+    },
+    {
+      "epoch": 0.049485645128756806,
+      "grad_norm": 0.5249567627906799,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.7361,
+      "step": 46
+    },
+    {
+      "epoch": 0.050561420022860216,
+      "grad_norm": 0.5613279342651367,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.7436,
+      "step": 47
+    },
+    {
+      "epoch": 0.05163719491696363,
+      "grad_norm": 0.6121152639389038,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.8016,
+      "step": 48
+    },
+    {
+      "epoch": 0.05271296981106703,
+      "grad_norm": 0.6896836757659912,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.9185,
+      "step": 49
+    },
+    {
+      "epoch": 0.05378874470517044,
+      "grad_norm": 0.9745162725448608,
+      "learning_rate": 0.0,
+      "loss": 2.1614,
+      "step": 50
+    },
+    {
+      "epoch": 0.05378874470517044,
+      "eval_loss": 1.7394925355911255,
+      "eval_runtime": 186.2842,
+      "eval_samples_per_second": 33.621,
+      "eval_steps_per_second": 4.203,
+      "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": 2.829012279754752e+17,
+  "total_flos": 5.658024559509504e+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:cde298347aefb5569ecda1d0ffbfc1f74fe5a8aad71a508769958efdcaf21bdf
+oid sha256:987fd07a10c7dc3d0202f3fd844ca5c32e5eda76cf15397ae30934c49a3acd1e
 size 6776