Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9275ba9f436954c221b7df3b9ca6e4c9adff3056bfdf0306fcef864e0b28d44c
+oid sha256:f87ca14db72cd50cb5df0f4db5f3303be01f5a532f0507db72d81475c9f826f9
 size 140815952

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:056230e2fd290647c47c0c0f94e6165f66bcbb2fae455a6da5e586aad12d4bb2
+oid sha256:45342b6c03b20d284dcbdc4fe845b8885405b67a5318180d6f34afffe75f292b
 size 71878612

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02528fb6e04bc8e3deb51115508eafe8833791641061f4c533c3d7e23e659592
+oid sha256:697b8f4e422aec7380f46cd9c2057935bc161fc291f3eb4c2dbde3a4d4c261f9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb15fdd4c0ab874f4afa0ea95fae119cbc74554df5fbe92ab825fe27063eaa04
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.2562970817089081,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.00852006475249212,
+  "best_metric": 0.24534127116203308,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.01704012950498424,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 115.131,
       "eval_steps_per_second": 14.397,
       "step": 25
+    },
+    {
+      "epoch": 0.008860867342591804,
+      "grad_norm": 1.486140489578247,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.2159,
+      "step": 26
+    },
+    {
+      "epoch": 0.00920166993269149,
+      "grad_norm": 1.8835890293121338,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.2349,
+      "step": 27
+    },
+    {
+      "epoch": 0.009542472522791173,
+      "grad_norm": 1.8669521808624268,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 0.2159,
+      "step": 28
+    },
+    {
+      "epoch": 0.009883275112890859,
+      "grad_norm": 1.622249722480774,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.2197,
+      "step": 29
+    },
+    {
+      "epoch": 0.010224077702990542,
+      "grad_norm": 2.078935384750366,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.2029,
+      "step": 30
+    },
+    {
+      "epoch": 0.010564880293090228,
+      "grad_norm": 1.943671703338623,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.2141,
+      "step": 31
+    },
+    {
+      "epoch": 0.010905682883189912,
+      "grad_norm": 1.981119990348816,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.2017,
+      "step": 32
+    },
+    {
+      "epoch": 0.011246485473289597,
+      "grad_norm": 2.3581714630126953,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.2743,
+      "step": 33
+    },
+    {
+      "epoch": 0.011587288063389281,
+      "grad_norm": 2.593571662902832,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.3099,
+      "step": 34
+    },
+    {
+      "epoch": 0.011928090653488967,
+      "grad_norm": 1.9463130235671997,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.2304,
+      "step": 35
+    },
+    {
+      "epoch": 0.01226889324358865,
+      "grad_norm": 2.119544744491577,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.2791,
+      "step": 36
+    },
+    {
+      "epoch": 0.012609695833688336,
+      "grad_norm": 2.3796632289886475,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.3268,
+      "step": 37
+    },
+    {
+      "epoch": 0.012950498423788022,
+      "grad_norm": 3.150411605834961,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.4008,
+      "step": 38
+    },
+    {
+      "epoch": 0.013291301013887705,
+      "grad_norm": 2.5175278186798096,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.3034,
+      "step": 39
+    },
+    {
+      "epoch": 0.013632103603987391,
+      "grad_norm": 2.4369542598724365,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.3142,
+      "step": 40
+    },
+    {
+      "epoch": 0.013972906194087075,
+      "grad_norm": 3.3217461109161377,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.3605,
+      "step": 41
+    },
+    {
+      "epoch": 0.01431370878418676,
+      "grad_norm": 2.68766188621521,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.3525,
+      "step": 42
+    },
+    {
+      "epoch": 0.014654511374286444,
+      "grad_norm": 3.276628017425537,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.4045,
+      "step": 43
+    },
+    {
+      "epoch": 0.01499531396438613,
+      "grad_norm": 3.3158345222473145,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.4197,
+      "step": 44
+    },
+    {
+      "epoch": 0.015336116554485813,
+      "grad_norm": 3.3790440559387207,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.4011,
+      "step": 45
+    },
+    {
+      "epoch": 0.015676919144585497,
+      "grad_norm": 3.6487362384796143,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.4834,
+      "step": 46
+    },
+    {
+      "epoch": 0.016017721734685183,
+      "grad_norm": 3.7635161876678467,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.45,
+      "step": 47
+    },
+    {
+      "epoch": 0.01635852432478487,
+      "grad_norm": 3.297227621078491,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.4442,
+      "step": 48
+    },
+    {
+      "epoch": 0.016699326914884554,
+      "grad_norm": 4.7598795890808105,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.6405,
+      "step": 49
+    },
+    {
+      "epoch": 0.01704012950498424,
+      "grad_norm": 4.400386810302734,
+      "learning_rate": 0.0,
+      "loss": 0.6194,
+      "step": 50
+    },
+    {
+      "epoch": 0.01704012950498424,
+      "eval_loss": 0.24534127116203308,
+      "eval_runtime": 42.9768,
+      "eval_samples_per_second": 114.992,
+      "eval_steps_per_second": 14.38,
+      "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": 966060303974400.0,
+  "total_flos": 1932120607948800.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null