Training in progress, step 63, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6f539cae862091000d8e382e8d26c2d724a267c0980007ce73051a6ed7b5d65
+oid sha256:bf8c0d77fc68826caff6ed48bef2ede6097c0b0b2e0a3d69679e1f7840583794
 size 381467712

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1aab1df3b996e7b34b7555718a6d5704d09b2be310d6a03a43c7c367a1d406f7
+oid sha256:1f32e5d3a614001dce47d674a3a525553cfc1aaedfb453114f04d7f61fd1b28e
 size 763142410

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac45fa83129ea64319199c193b188a71b7cdafe684f33ea329b41ad0c4a12f66
+oid sha256:2669227e8cf84bfa0341ef1f0aaeb18ec95cc3e598892a80acdc1939b1c78722
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa84912dc5169418dab0c9481959b08f78823c331191bb4af9e0e50da769e644
+oid sha256:badf8dd7fd843c03f3dfa379f5a62cbdac918ff18b84343f94ed7c04cd128a3f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7339180707931519,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 2.380952380952381,
+  "epoch": 3.0,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 63,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -373,6 +373,97 @@
       "eval_samples_per_second": 23.53,
       "eval_steps_per_second": 11.765,
       "step": 50
+    },
+    {
+      "epoch": 2.4285714285714284,
+      "grad_norm": 5.302610874176025,
+      "learning_rate": 1.801634892205545e-05,
+      "loss": 2.907,
+      "step": 51
+    },
+    {
+      "epoch": 2.4761904761904763,
+      "grad_norm": 3.535484790802002,
+      "learning_rate": 1.5296290238968303e-05,
+      "loss": 2.816,
+      "step": 52
+    },
+    {
+      "epoch": 2.5238095238095237,
+      "grad_norm": 2.9045586585998535,
+      "learning_rate": 1.2761390862810907e-05,
+      "loss": 2.8551,
+      "step": 53
+    },
+    {
+      "epoch": 2.571428571428571,
+      "grad_norm": 5.55578088760376,
+      "learning_rate": 1.0425175578537299e-05,
+      "loss": 2.7582,
+      "step": 54
+    },
+    {
+      "epoch": 2.619047619047619,
+      "grad_norm": 7.579736232757568,
+      "learning_rate": 8.30010910550611e-06,
+      "loss": 2.8881,
+      "step": 55
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 4.39998722076416,
+      "learning_rate": 6.397529592809614e-06,
+      "loss": 2.7402,
+      "step": 56
+    },
+    {
+      "epoch": 2.7142857142857144,
+      "grad_norm": 8.276344299316406,
+      "learning_rate": 4.727588125342669e-06,
+      "loss": 2.7021,
+      "step": 57
+    },
+    {
+      "epoch": 2.761904761904762,
+      "grad_norm": 4.667769908905029,
+      "learning_rate": 3.299194563372604e-06,
+      "loss": 2.9088,
+      "step": 58
+    },
+    {
+      "epoch": 2.8095238095238093,
+      "grad_norm": 4.007717132568359,
+      "learning_rate": 2.1199700045797077e-06,
+      "loss": 2.8541,
+      "step": 59
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 6.375820636749268,
+      "learning_rate": 1.196206122203647e-06,
+      "loss": 2.864,
+      "step": 60
+    },
+    {
+      "epoch": 2.9047619047619047,
+      "grad_norm": 4.68563175201416,
+      "learning_rate": 5.328315962444874e-07,
+      "loss": 2.8855,
+      "step": 61
+    },
+    {
+      "epoch": 2.9523809523809526,
+      "grad_norm": 4.791390895843506,
+      "learning_rate": 1.333858168224178e-07,
+      "loss": 2.7794,
+      "step": 62
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 7.031291484832764,
+      "learning_rate": 0.0,
+      "loss": 2.8601,
+      "step": 63
     }
   ],
   "logging_steps": 1,
@@ -396,12 +487,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.9169691222081536e+16,
+  "total_flos": 3.673626526089216e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null