Training in progress, step 63, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c6c2d451242f2c29a8fe507859cfd39f0e3b035a1752e3e93140903b3c1dc1c
+oid sha256:ff508e6d42caf80a3e7a4e6ae624f79720ad42d7b3d4a19628a8823f39e97d0d
 size 381467712

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05236b04cc12e41bca65a4684b23a2cd3f2abaccda4d3c05a32bcd0ed1845385
+oid sha256:fb8031397ad617e11a787edf300a4454b069274ca0ad64ab1592704f1e6ab34b
 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": 0.7201187610626221,
   "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": 23.725,
       "eval_steps_per_second": 11.863,
       "step": 50
+    },
+    {
+      "epoch": 2.4285714285714284,
+      "grad_norm": 14.500555038452148,
+      "learning_rate": 1.801634892205545e-05,
+      "loss": 2.9736,
+      "step": 51
+    },
+    {
+      "epoch": 2.4761904761904763,
+      "grad_norm": 7.0939812660217285,
+      "learning_rate": 1.5296290238968303e-05,
+      "loss": 2.816,
+      "step": 52
+    },
+    {
+      "epoch": 2.5238095238095237,
+      "grad_norm": 3.804086208343506,
+      "learning_rate": 1.2761390862810907e-05,
+      "loss": 2.7451,
+      "step": 53
+    },
+    {
+      "epoch": 2.571428571428571,
+      "grad_norm": 6.390565395355225,
+      "learning_rate": 1.0425175578537299e-05,
+      "loss": 2.7337,
+      "step": 54
+    },
+    {
+      "epoch": 2.619047619047619,
+      "grad_norm": 11.50753116607666,
+      "learning_rate": 8.30010910550611e-06,
+      "loss": 2.8611,
+      "step": 55
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 6.187903881072998,
+      "learning_rate": 6.397529592809614e-06,
+      "loss": 2.7281,
+      "step": 56
+    },
+    {
+      "epoch": 2.7142857142857144,
+      "grad_norm": 8.113085746765137,
+      "learning_rate": 4.727588125342669e-06,
+      "loss": 2.7478,
+      "step": 57
+    },
+    {
+      "epoch": 2.761904761904762,
+      "grad_norm": 6.269874095916748,
+      "learning_rate": 3.299194563372604e-06,
+      "loss": 2.9062,
+      "step": 58
+    },
+    {
+      "epoch": 2.8095238095238093,
+      "grad_norm": 10.525289535522461,
+      "learning_rate": 2.1199700045797077e-06,
+      "loss": 2.8869,
+      "step": 59
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 7.636288166046143,
+      "learning_rate": 1.196206122203647e-06,
+      "loss": 2.8721,
+      "step": 60
+    },
+    {
+      "epoch": 2.9047619047619047,
+      "grad_norm": 9.5599365234375,
+      "learning_rate": 5.328315962444874e-07,
+      "loss": 2.9166,
+      "step": 61
+    },
+    {
+      "epoch": 2.9523809523809526,
+      "grad_norm": 6.276193618774414,
+      "learning_rate": 1.333858168224178e-07,
+      "loss": 2.8343,
+      "step": 62
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 9.120771408081055,
+      "learning_rate": 0.0,
+      "loss": 2.7545,
+      "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