Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40a908afa249cd252016cad0d2f7be545ec51cc72ba7d2cdaf9f071840bc0408
+oid sha256:fdd157eb27b27c4f70d8e8a7d777bdee43049ccaf0a856327b80e3b51e7a32d7
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ed850848fc48063b3d29bd3cbedb65899cb14458c27112a29456bc8e1ce5e15
+oid sha256:f576b3dc6aed275c73922211a420ba493d9c26fda60025f0a27973462f15ea02
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:097784a8459b5523bce7987c706d00d9b0797f9210986fe9634a24ded975f97c
+oid sha256:62ed3fd3312f96c17ea93ab3f7344a9def6141fa3d024e167875cba869f24ea5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.1929351091384888,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.008487163165711862,
+  "best_metric": 1.1750564575195312,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.012730744748567792,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 17.201,
       "eval_steps_per_second": 8.609,
       "step": 20
+    },
+    {
+      "epoch": 0.008911521323997454,
+      "grad_norm": 0.5157674551010132,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 1.1561,
+      "step": 21
+    },
+    {
+      "epoch": 0.010184595798854232,
+      "grad_norm": 0.5437240600585938,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.1501,
+      "step": 24
+    },
+    {
+      "epoch": 0.010608953957139827,
+      "eval_loss": 1.1779104471206665,
+      "eval_runtime": 57.7927,
+      "eval_samples_per_second": 17.182,
+      "eval_steps_per_second": 8.6,
+      "step": 25
+    },
+    {
+      "epoch": 0.011457670273711012,
+      "grad_norm": 0.5273560285568237,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 1.1227,
+      "step": 27
+    },
+    {
+      "epoch": 0.012730744748567792,
+      "grad_norm": 0.5340238213539124,
+      "learning_rate": 0.0,
+      "loss": 1.1004,
+      "step": 30
+    },
+    {
+      "epoch": 0.012730744748567792,
+      "eval_loss": 1.1750564575195312,
+      "eval_runtime": 57.6221,
+      "eval_samples_per_second": 17.233,
+      "eval_steps_per_second": 8.625,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7511608746049536.0,
+  "total_flos": 1.1221045163851776e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null