Training in progress, step 162, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8475dcb443d9b9e5f1b2cf128cceb774a6d02011b393502b6e9deeb52ea358dd
+oid sha256:5706102b2281ac5b3a916317ad0ff0ecec32386eb7dfebfc838f9cb28b5d121f
 size 140815952

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:204c776af22c34800802e08156c67a929c170a5db09d27de1cbcfc44bc7758db
+oid sha256:14ed20dc2759785b5ab2431b3969ab166ce85230f28b4b6128c643b919946863
 size 71878612

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27f42c8af3c4ae2ad37c84566911d62c97008110667d058e02109f73c5377f2c
+oid sha256:92142d2d76785608f87cb4cad94758b8983e019865d68ad54984b2ea9d7578ba
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ed7454232ee2a5e2b25a5b6f82cc3a4462ff259aa0925317244942a2aecbea8
+oid sha256:37d3373f4006be09e15478c20075f16407c8e03504d4995b420a93433e54c5dc
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.0366058349609375,
   "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.9259259259259259,
+  "epoch": 1.0,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 162,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1089,6 +1089,90 @@
       "eval_samples_per_second": 41.253,
       "eval_steps_per_second": 10.427,
       "step": 150
+    },
+    {
+      "epoch": 0.9320987654320988,
+      "grad_norm": 5.5308146476745605,
+      "learning_rate": 1.286667868385627e-06,
+      "loss": 1.351,
+      "step": 151
+    },
+    {
+      "epoch": 0.9382716049382716,
+      "grad_norm": 6.575994968414307,
+      "learning_rate": 1.064157733632276e-06,
+      "loss": 1.3306,
+      "step": 152
+    },
+    {
+      "epoch": 0.9444444444444444,
+      "grad_norm": 8.211260795593262,
+      "learning_rate": 8.62551347632029e-07,
+      "loss": 1.2282,
+      "step": 153
+    },
+    {
+      "epoch": 0.9506172839506173,
+      "grad_norm": 4.557495594024658,
+      "learning_rate": 6.819348298638839e-07,
+      "loss": 1.0393,
+      "step": 154
+    },
+    {
+      "epoch": 0.9567901234567902,
+      "grad_norm": 5.561540126800537,
+      "learning_rate": 5.223853336398632e-07,
+      "loss": 0.81,
+      "step": 155
+    },
+    {
+      "epoch": 0.9629629629629629,
+      "grad_norm": 5.5861077308654785,
+      "learning_rate": 3.839710131477492e-07,
+      "loss": 1.1083,
+      "step": 156
+    },
+    {
+      "epoch": 0.9691358024691358,
+      "grad_norm": 7.85378885269165,
+      "learning_rate": 2.667509943378721e-07,
+      "loss": 1.53,
+      "step": 157
+    },
+    {
+      "epoch": 0.9753086419753086,
+      "grad_norm": 5.781926155090332,
+      "learning_rate": 1.7077534966650766e-07,
+      "loss": 1.125,
+      "step": 158
+    },
+    {
+      "epoch": 0.9814814814814815,
+      "grad_norm": 6.874696731567383,
+      "learning_rate": 9.60850767065924e-08,
+      "loss": 1.2242,
+      "step": 159
+    },
+    {
+      "epoch": 0.9876543209876543,
+      "grad_norm": 6.842217922210693,
+      "learning_rate": 4.2712080634949024e-08,
+      "loss": 0.9251,
+      "step": 160
+    },
+    {
+      "epoch": 0.9938271604938271,
+      "grad_norm": 3.6685681343078613,
+      "learning_rate": 1.0679160603449534e-08,
+      "loss": 0.9695,
+      "step": 161
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 5.732940673828125,
+      "learning_rate": 0.0,
+      "loss": 1.3258,
+      "step": 162
     }
   ],
   "logging_steps": 1,
@@ -1112,12 +1196,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.15927236476928e+16,
+  "total_flos": 1.2505650634948608e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null