Training in progress, step 50, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
+    "up_proj",
     "o_proj",
     "q_proj",
     "gate_proj",
     "down_proj",
-    "up_proj",
-    "k_proj",
-    "v_proj"
+    "k_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 sha256:4af57c90c2aef9dade2c6b9a9733349393127646da0e2aadf732213af6e8cff5
+oid sha256:b03ca3a4cb4c02ea4882f8d4ae22b749b6cf2995da09c894f3b6a71495c35d92
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12942a26eeac8dada2376611f0c60db1f675db0668829338cf77838341ed1f74
+oid sha256:31721c3c99d6e4dd85b5bdd8fc0468d1463151298b72d973fd7de9db038f961a
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcf3237885fe379174253442cfddde58af957477ddc024acd1f23db7cac1fb76
-size 15024
+oid sha256:6325e3dd0fe33d2d9f79df075ba461f04593a1fee636ba78bb997edc93429fb0
+size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31244a54444acfa2cb79b2989fa1eadd9300faf09fd29e2cce4db5ef2bbd5ba9
+oid sha256:8b375ee3bf798dadc585d676cb519f0380a4fc94483dd5cecb34d79746675b20
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6678efb1d91d4b5f962c86ca8fd2ba7bd648984bcd68a68653eaf1e47e6e7fd0
+oid sha256:27caa134403786386ec27f9441953387d2d46573059bd24bd4239a4cd5e9b2fd
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df056a32208e475ca72659f2d557a28eca2d4a7c9de32a5bdeefeb39ab01ecd6
+oid sha256:ca3d01a6bf3606d93f8e97980f2797167672ff81e1803b1ce18ceb9bc1e8124e
 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": 2.18762469291687,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.34904013961605584,
+  "best_metric": 2.1079092025756836,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6980802792321117,
   "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": 0.013961605584642234,
-      "grad_norm": 2.3046627044677734,
+      "grad_norm": 2.440608263015747,
       "learning_rate": 5e-05,
       "loss": 3.0767,
       "step": 1
@@ -18,186 +18,369 @@
     {
       "epoch": 0.013961605584642234,
       "eval_loss": 3.6313090324401855,
-      "eval_runtime": 14.7492,
-      "eval_samples_per_second": 32.747,
-      "eval_steps_per_second": 4.136,
+      "eval_runtime": 14.6219,
+      "eval_samples_per_second": 33.033,
+      "eval_steps_per_second": 4.172,
       "step": 1
     },
     {
       "epoch": 0.027923211169284468,
-      "grad_norm": 2.6478118896484375,
+      "grad_norm": 2.794785976409912,
       "learning_rate": 0.0001,
       "loss": 3.2593,
       "step": 2
     },
     {
       "epoch": 0.041884816753926704,
-      "grad_norm": 2.6827518939971924,
+      "grad_norm": 2.8147521018981934,
       "learning_rate": 9.989294616193017e-05,
-      "loss": 3.3034,
+      "loss": 3.3011,
       "step": 3
     },
     {
       "epoch": 0.055846422338568937,
-      "grad_norm": 1.908111572265625,
+      "grad_norm": 1.9635080099105835,
       "learning_rate": 9.957224306869053e-05,
-      "loss": 2.9132,
+      "loss": 2.9119,
       "step": 4
     },
     {
       "epoch": 0.06980802792321117,
-      "grad_norm": 1.7897250652313232,
+      "grad_norm": 1.8362520933151245,
       "learning_rate": 9.903926402016153e-05,
-      "loss": 2.877,
+      "loss": 2.8748,
       "step": 5
     },
     {
       "epoch": 0.08376963350785341,
-      "grad_norm": 2.1173017024993896,
+      "grad_norm": 2.1290366649627686,
       "learning_rate": 9.829629131445342e-05,
-      "loss": 2.7219,
+      "loss": 2.7166,
       "step": 6
     },
     {
       "epoch": 0.09773123909249563,
-      "grad_norm": 1.83841073513031,
+      "grad_norm": 1.8561207056045532,
       "learning_rate": 9.73465064747553e-05,
-      "loss": 2.6185,
+      "loss": 2.6145,
       "step": 7
     },
     {
       "epoch": 0.11169284467713787,
-      "grad_norm": 1.6945081949234009,
+      "grad_norm": 1.7427964210510254,
       "learning_rate": 9.619397662556435e-05,
-      "loss": 2.3684,
+      "loss": 2.3675,
       "step": 8
     },
     {
       "epoch": 0.1256544502617801,
-      "grad_norm": 1.6825312376022339,
+      "grad_norm": 1.6925208568572998,
       "learning_rate": 9.484363707663442e-05,
-      "loss": 2.5296,
+      "loss": 2.5244,
       "step": 9
     },
     {
       "epoch": 0.13961605584642234,
-      "grad_norm": 1.83368718624115,
+      "grad_norm": 1.8548673391342163,
       "learning_rate": 9.330127018922194e-05,
-      "loss": 2.5269,
+      "loss": 2.5257,
       "step": 10
     },
     {
       "epoch": 0.15357766143106458,
-      "grad_norm": 2.0443615913391113,
+      "grad_norm": 2.0587422847747803,
       "learning_rate": 9.157348061512727e-05,
-      "loss": 2.3321,
+      "loss": 2.3299,
       "step": 11
     },
     {
       "epoch": 0.16753926701570682,
-      "grad_norm": 2.1939291954040527,
+      "grad_norm": 2.2293004989624023,
       "learning_rate": 8.966766701456177e-05,
-      "loss": 2.2375,
+      "loss": 2.2368,
       "step": 12
     },
     {
       "epoch": 0.18150087260034903,
-      "grad_norm": 2.5192129611968994,
+      "grad_norm": 2.629159688949585,
       "learning_rate": 8.759199037394887e-05,
-      "loss": 2.3876,
+      "loss": 2.3904,
       "step": 13
     },
     {
       "epoch": 0.19546247818499127,
-      "grad_norm": 2.0990617275238037,
+      "grad_norm": 2.1623623371124268,
       "learning_rate": 8.535533905932738e-05,
-      "loss": 2.4447,
+      "loss": 2.4445,
       "step": 14
     },
     {
       "epoch": 0.2094240837696335,
-      "grad_norm": 1.3212895393371582,
+      "grad_norm": 1.3389151096343994,
       "learning_rate": 8.296729075500344e-05,
-      "loss": 2.414,
+      "loss": 2.4144,
       "step": 15
     },
     {
       "epoch": 0.22338568935427575,
-      "grad_norm": 1.3915622234344482,
+      "grad_norm": 1.4149812459945679,
       "learning_rate": 8.043807145043604e-05,
-      "loss": 2.3652,
+      "loss": 2.3635,
       "step": 16
     },
     {
       "epoch": 0.23734729493891799,
-      "grad_norm": 1.446217656135559,
+      "grad_norm": 1.4710769653320312,
       "learning_rate": 7.777851165098012e-05,
-      "loss": 2.3562,
+      "loss": 2.356,
       "step": 17
     },
     {
       "epoch": 0.2513089005235602,
-      "grad_norm": 1.3253506422042847,
+      "grad_norm": 1.358171820640564,
       "learning_rate": 7.500000000000001e-05,
-      "loss": 2.3233,
+      "loss": 2.3229,
       "step": 18
     },
     {
       "epoch": 0.26527050610820246,
-      "grad_norm": 1.2720378637313843,
+      "grad_norm": 1.3044663667678833,
       "learning_rate": 7.211443451095007e-05,
-      "loss": 2.231,
+      "loss": 2.233,
       "step": 19
     },
     {
       "epoch": 0.2792321116928447,
-      "grad_norm": 1.3503715991973877,
+      "grad_norm": 1.367074966430664,
       "learning_rate": 6.91341716182545e-05,
-      "loss": 2.2531,
+      "loss": 2.2508,
       "step": 20
     },
     {
       "epoch": 0.2931937172774869,
-      "grad_norm": 1.3358739614486694,
+      "grad_norm": 1.3645036220550537,
       "learning_rate": 6.607197326515808e-05,
-      "loss": 2.0876,
+      "loss": 2.0879,
       "step": 21
     },
     {
       "epoch": 0.30715532286212915,
-      "grad_norm": 1.518196940422058,
+      "grad_norm": 1.5373777151107788,
       "learning_rate": 6.294095225512603e-05,
-      "loss": 2.2104,
+      "loss": 2.2098,
       "step": 22
     },
     {
       "epoch": 0.32111692844677137,
-      "grad_norm": 1.5301507711410522,
+      "grad_norm": 1.54306960105896,
       "learning_rate": 5.9754516100806423e-05,
-      "loss": 2.0746,
+      "loss": 2.0754,
       "step": 23
     },
     {
       "epoch": 0.33507853403141363,
-      "grad_norm": 1.6280711889266968,
+      "grad_norm": 1.6383461952209473,
       "learning_rate": 5.6526309611002594e-05,
-      "loss": 2.1143,
+      "loss": 2.1132,
       "step": 24
     },
     {
       "epoch": 0.34904013961605584,
-      "grad_norm": 2.544659376144409,
+      "grad_norm": 2.515599250793457,
       "learning_rate": 5.327015646150716e-05,
-      "loss": 2.1337,
+      "loss": 2.1327,
       "step": 25
     },
     {
       "epoch": 0.34904013961605584,
-      "eval_loss": 2.18762469291687,
-      "eval_runtime": 14.7385,
-      "eval_samples_per_second": 32.771,
-      "eval_steps_per_second": 4.139,
+      "eval_loss": 2.187441825866699,
+      "eval_runtime": 14.6195,
+      "eval_samples_per_second": 33.038,
+      "eval_steps_per_second": 4.172,
       "step": 25
+    },
+    {
+      "epoch": 0.36300174520069806,
+      "grad_norm": 1.2345504760742188,
+      "learning_rate": 5e-05,
+      "loss": 2.3329,
+      "step": 26
+    },
+    {
+      "epoch": 0.3769633507853403,
+      "grad_norm": 1.255537509918213,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 2.34,
+      "step": 27
+    },
+    {
+      "epoch": 0.39092495636998253,
+      "grad_norm": 1.2513974905014038,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.1838,
+      "step": 28
+    },
+    {
+      "epoch": 0.4048865619546248,
+      "grad_norm": 1.2584850788116455,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 2.4511,
+      "step": 29
+    },
+    {
+      "epoch": 0.418848167539267,
+      "grad_norm": 1.214241623878479,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 2.2581,
+      "step": 30
+    },
+    {
+      "epoch": 0.4328097731239092,
+      "grad_norm": 1.2207328081130981,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 2.1056,
+      "step": 31
+    },
+    {
+      "epoch": 0.4467713787085515,
+      "grad_norm": 1.3635737895965576,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.3291,
+      "step": 32
+    },
+    {
+      "epoch": 0.4607329842931937,
+      "grad_norm": 1.3297851085662842,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.9666,
+      "step": 33
+    },
+    {
+      "epoch": 0.47469458987783597,
+      "grad_norm": 1.489034652709961,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.1087,
+      "step": 34
+    },
+    {
+      "epoch": 0.4886561954624782,
+      "grad_norm": 1.600051999092102,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.9851,
+      "step": 35
+    },
+    {
+      "epoch": 0.5026178010471204,
+      "grad_norm": 1.614622712135315,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 2.0479,
+      "step": 36
+    },
+    {
+      "epoch": 0.5165794066317626,
+      "grad_norm": 1.826269268989563,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.9601,
+      "step": 37
+    },
+    {
+      "epoch": 0.5305410122164049,
+      "grad_norm": 1.017246961593628,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.3264,
+      "step": 38
+    },
+    {
+      "epoch": 0.5445026178010471,
+      "grad_norm": 0.9326218366622925,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.2343,
+      "step": 39
+    },
+    {
+      "epoch": 0.5584642233856894,
+      "grad_norm": 1.1198312044143677,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.192,
+      "step": 40
+    },
+    {
+      "epoch": 0.5724258289703316,
+      "grad_norm": 1.0579617023468018,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 2.1154,
+      "step": 41
+    },
+    {
+      "epoch": 0.5863874345549738,
+      "grad_norm": 1.1373172998428345,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.1256,
+      "step": 42
+    },
+    {
+      "epoch": 0.6003490401396161,
+      "grad_norm": 1.1976994276046753,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.1098,
+      "step": 43
+    },
+    {
+      "epoch": 0.6143106457242583,
+      "grad_norm": 1.2756996154785156,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.0461,
+      "step": 44
+    },
+    {
+      "epoch": 0.6282722513089005,
+      "grad_norm": 1.2834415435791016,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.8656,
+      "step": 45
+    },
+    {
+      "epoch": 0.6422338568935427,
+      "grad_norm": 1.436659812927246,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 2.0414,
+      "step": 46
+    },
+    {
+      "epoch": 0.6561954624781849,
+      "grad_norm": 1.4373010396957397,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.9463,
+      "step": 47
+    },
+    {
+      "epoch": 0.6701570680628273,
+      "grad_norm": 1.585813045501709,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.9823,
+      "step": 48
+    },
+    {
+      "epoch": 0.6841186736474695,
+      "grad_norm": 1.6328294277191162,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.9625,
+      "step": 49
+    },
+    {
+      "epoch": 0.6980802792321117,
+      "grad_norm": 2.0439422130584717,
+      "learning_rate": 0.0,
+      "loss": 1.9024,
+      "step": 50
+    },
+    {
+      "epoch": 0.6980802792321117,
+      "eval_loss": 2.1079092025756836,
+      "eval_runtime": 14.6122,
+      "eval_samples_per_second": 33.055,
+      "eval_steps_per_second": 4.175,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+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:ae1476d186d368aae1c70941a1ec0fc19237587fb46cf02ce6f45ea7aa7119a7
+oid sha256:290fc8e8a0e0d01919684cc61f32289edab8d8ad1ec65cc2f86cba0a00f2ad6c
 size 6776