Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75641a4ac140594058c3832f1e4fbb220557617fba7947ff8052d8c71e1da0cd
+oid sha256:db93db9a24c68d18fe54ecf2b5d2a454d20ca4073081276aa372b54e9e22ed7a
 size 26008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11886a4a6c2e2cfcf94dbe212ec9f83fef7e722d40a3305962972671c30f259b
+oid sha256:92dc2d59506dec059b21359d3cdead817086bf7eae7542a04dad435c8067a143
 size 68874

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e97ead28242dd097af80112cb3bd8d751944021cbf255fca1535e0f2a22344d9
+oid sha256:c5288ed9323916daf49e9e619b5ce81ab40c19e01021e3ee0c12210ac8bab7de
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.949509620666504,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.004519263360072308,
+  "best_metric": 11.947105407714844,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.009038526720144616,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 32.249,
       "eval_steps_per_second": 16.124,
       "step": 10
+    },
+    {
+      "epoch": 0.00542311603208677,
+      "grad_norm": 0.05678074061870575,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 11.9508,
+      "step": 12
+    },
+    {
+      "epoch": 0.006778895040108463,
+      "grad_norm": 0.06515557318925858,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 11.9496,
+      "step": 15
+    },
+    {
+      "epoch": 0.006778895040108463,
+      "eval_loss": 11.948259353637695,
+      "eval_runtime": 28.8883,
+      "eval_samples_per_second": 32.262,
+      "eval_steps_per_second": 16.131,
+      "step": 15
+    },
+    {
+      "epoch": 0.008134674048130154,
+      "grad_norm": 0.07017915695905685,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 11.9489,
+      "step": 18
+    },
+    {
+      "epoch": 0.009038526720144616,
+      "eval_loss": 11.947105407714844,
+      "eval_runtime": 28.7664,
+      "eval_samples_per_second": 32.399,
+      "eval_steps_per_second": 16.199,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5902073856.0,
+  "total_flos": 12366249984.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null