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:bd55c91683cd28d6105cbaceb8ee9ebeb557d261066ff5412b23889d8b885e8b
+oid sha256:b4d06429a47fac9e9e9e8ce15884196dc7b73a51714f8b0e9c4ff9af8da6f3e5
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbb8a1c97f4bbecd5bed3a9fa28c16258de6a3db4ce992ddd64f8570096c5e5f
+oid sha256:2b8527785f96e452dfb2b39e7fbdeea6bddb5d2a7eb4eab7b44229917b387b84
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6886601050c390f39a92426ca2f7959a365b5e2de4b6529b41a3d7880f91070e
+oid sha256:94e8481a44704e21f870c94103d7b53d8a69c32e607580ab81c67a86d78c867a
 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": 0.5596538186073303,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.31645569620253167,
+  "best_metric": 0.5091546773910522,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6329113924050633,
   "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": 15.07,
       "eval_steps_per_second": 1.912,
       "step": 25
+    },
+    {
+      "epoch": 0.3291139240506329,
+      "grad_norm": 7.093173503875732,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 2.3286,
+      "step": 26
+    },
+    {
+      "epoch": 0.34177215189873417,
+      "grad_norm": 5.931855201721191,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 1.9256,
+      "step": 27
+    },
+    {
+      "epoch": 0.35443037974683544,
+      "grad_norm": 7.020291328430176,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 2.2209,
+      "step": 28
+    },
+    {
+      "epoch": 0.3670886075949367,
+      "grad_norm": 6.310258388519287,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 2.231,
+      "step": 29
+    },
+    {
+      "epoch": 0.379746835443038,
+      "grad_norm": 6.792581081390381,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 2.2158,
+      "step": 30
+    },
+    {
+      "epoch": 0.3924050632911392,
+      "grad_norm": 6.202337265014648,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 2.0049,
+      "step": 31
+    },
+    {
+      "epoch": 0.4050632911392405,
+      "grad_norm": 5.8156914710998535,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 2.069,
+      "step": 32
+    },
+    {
+      "epoch": 0.4177215189873418,
+      "grad_norm": 5.831786155700684,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 2.1343,
+      "step": 33
+    },
+    {
+      "epoch": 0.43037974683544306,
+      "grad_norm": 6.260862827301025,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 2.3229,
+      "step": 34
+    },
+    {
+      "epoch": 0.4430379746835443,
+      "grad_norm": 5.3327202796936035,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.0672,
+      "step": 35
+    },
+    {
+      "epoch": 0.45569620253164556,
+      "grad_norm": 4.9809417724609375,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 1.9,
+      "step": 36
+    },
+    {
+      "epoch": 0.46835443037974683,
+      "grad_norm": 6.4525909423828125,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 2.0248,
+      "step": 37
+    },
+    {
+      "epoch": 0.4810126582278481,
+      "grad_norm": 6.171474933624268,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.9821,
+      "step": 38
+    },
+    {
+      "epoch": 0.4936708860759494,
+      "grad_norm": 4.337746620178223,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.9903,
+      "step": 39
+    },
+    {
+      "epoch": 0.5063291139240507,
+      "grad_norm": 4.888207912445068,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 2.0018,
+      "step": 40
+    },
+    {
+      "epoch": 0.5189873417721519,
+      "grad_norm": 5.527780532836914,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.0755,
+      "step": 41
+    },
+    {
+      "epoch": 0.5316455696202531,
+      "grad_norm": 5.051205158233643,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.979,
+      "step": 42
+    },
+    {
+      "epoch": 0.5443037974683544,
+      "grad_norm": 5.09185266494751,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 2.0654,
+      "step": 43
+    },
+    {
+      "epoch": 0.5569620253164557,
+      "grad_norm": 4.7769694328308105,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.7859,
+      "step": 44
+    },
+    {
+      "epoch": 0.569620253164557,
+      "grad_norm": 6.080770969390869,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.8062,
+      "step": 45
+    },
+    {
+      "epoch": 0.5822784810126582,
+      "grad_norm": 6.04468297958374,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 2.0148,
+      "step": 46
+    },
+    {
+      "epoch": 0.5949367088607594,
+      "grad_norm": 6.175866603851318,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.8943,
+      "step": 47
+    },
+    {
+      "epoch": 0.6075949367088608,
+      "grad_norm": 6.0562615394592285,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.9837,
+      "step": 48
+    },
+    {
+      "epoch": 0.620253164556962,
+      "grad_norm": 7.458826541900635,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.5447,
+      "step": 49
+    },
+    {
+      "epoch": 0.6329113924050633,
+      "grad_norm": 6.869083881378174,
+      "learning_rate": 0.0,
+      "loss": 2.0644,
+      "step": 50
+    },
+    {
+      "epoch": 0.6329113924050633,
+      "eval_loss": 0.5091546773910522,
+      "eval_runtime": 9.1468,
+      "eval_samples_per_second": 14.65,
+      "eval_steps_per_second": 1.859,
+      "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": 3.255520470446899e+16,
+  "total_flos": 6.475265990669107e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null