Training in progress, step 161, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a90827f22f5c383c23f542f38e58363a035f45f979ba43cdc69e527689e33e6a
+oid sha256:0db233712b868d6ea9281d882cb4d7f45c2b9b6dc7b1554f23f3ff652d61f24c
 size 1048651800

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06af3d9ab28f962337a17b9e50f5ae969ce3e88bdfc69bcd1a8933e40a885f3b
+oid sha256:6483f84e6a1a6b692dec4f951b1d65d8fc7aab192f6ef97bc4ecdff1d3266e4f
 size 533138580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7981662228708a9683e3aa8009af597e888743c4110db805a3021704903122d
+oid sha256:8fcbda300fce890a4863a40a8772f8f77022b72b12a440762888cf3436cdef9c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8403162ebec32e9fc064abda7c96193ae83edce13882417a3e99416d0ba414ef
+oid sha256:8062d7971351733b717f38459c8d482c1746e7e410c9c85b07ea9956567048a7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.28952550888061523,
   "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 2.7906976744186047,
+  "epoch": 2.9953488372093022,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 161,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1089,6 +1089,83 @@
       "eval_samples_per_second": 8.372,
       "eval_steps_per_second": 2.116,
       "step": 150
+    },
+    {
+      "epoch": 2.8093023255813954,
+      "grad_norm": 1.4344302415847778,
+      "learning_rate": 7.547737146098809e-07,
+      "loss": 0.768,
+      "step": 151
+    },
+    {
+      "epoch": 2.827906976744186,
+      "grad_norm": 1.6189731359481812,
+      "learning_rate": 6.117861322210028e-07,
+      "loss": 0.5337,
+      "step": 152
+    },
+    {
+      "epoch": 2.8465116279069766,
+      "grad_norm": 1.4234650135040283,
+      "learning_rate": 4.836832401747892e-07,
+      "loss": 0.5149,
+      "step": 153
+    },
+    {
+      "epoch": 2.8651162790697673,
+      "grad_norm": 1.1778002977371216,
+      "learning_rate": 3.705204868840894e-07,
+      "loss": 0.4272,
+      "step": 154
+    },
+    {
+      "epoch": 2.883720930232558,
+      "grad_norm": 1.35899019241333,
+      "learning_rate": 2.7234685403047243e-07,
+      "loss": 0.3179,
+      "step": 155
+    },
+    {
+      "epoch": 2.902325581395349,
+      "grad_norm": 1.4125027656555176,
+      "learning_rate": 1.892048353628217e-07,
+      "loss": 0.365,
+      "step": 156
+    },
+    {
+      "epoch": 2.9209302325581397,
+      "grad_norm": 1.287215232849121,
+      "learning_rate": 1.211304183042494e-07,
+      "loss": 0.3343,
+      "step": 157
+    },
+    {
+      "epoch": 2.9395348837209303,
+      "grad_norm": 1.398272156715393,
+      "learning_rate": 6.81530683751752e-08,
+      "loss": 0.3152,
+      "step": 158
+    },
+    {
+      "epoch": 2.958139534883721,
+      "grad_norm": 1.168246865272522,
+      "learning_rate": 3.029571643941353e-08,
+      "loss": 0.1939,
+      "step": 159
+    },
+    {
+      "epoch": 2.9767441860465116,
+      "grad_norm": 1.5252883434295654,
+      "learning_rate": 7.574748778697015e-09,
+      "loss": 0.4645,
+      "step": 160
+    },
+    {
+      "epoch": 2.9953488372093022,
+      "grad_norm": 1.418809413909912,
+      "learning_rate": 0.0,
+      "loss": 0.3772,
+      "step": 161
     }
   ],
   "logging_steps": 1,
@@ -1112,12 +1189,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.228854847635456e+17,
+  "total_flos": 4.532890163478528e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null