Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c9ecd6a60fcdf45bf1b4da5727e899457605e6f9ff6cc057d5e028f95100d2e
+oid sha256:690e88d90de5e9d135318a5129516c66f486cd04a979b4dcab5decd65864eb95
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:984ec7a1742934770bc4ddfb2bac424c5d4f2b995ee3aff67d7c5069d1316be1
+oid sha256:59694740345e380517465313ea617bfd4648dce5759edbb9056348e1ede16b37
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d20aa8d6f51d4cb51b41476affac69a53d8719b0ebf11c0cbd33939351613156
+oid sha256:eded4db5dec434ed3d2d95752ada2711a27d28d29da1d89572acb7fb8362dfd1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 3.430868148803711,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.003608317171079338,
+  "best_metric": 3.3954291343688965,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.005412475756619007,
   "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": 8.171,
       "eval_steps_per_second": 2.043,
       "step": 20
+    },
+    {
+      "epoch": 0.0037887330296333048,
+      "grad_norm": 3.054889678955078,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 3.4866,
+      "step": 21
+    },
+    {
+      "epoch": 0.004329980605295205,
+      "grad_norm": 3.2791240215301514,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 3.4309,
+      "step": 24
+    },
+    {
+      "epoch": 0.0045103964638491725,
+      "eval_loss": 3.4044599533081055,
+      "eval_runtime": 571.68,
+      "eval_samples_per_second": 8.165,
+      "eval_steps_per_second": 2.041,
+      "step": 25
+    },
+    {
+      "epoch": 0.004871228180957106,
+      "grad_norm": 3.1638684272766113,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 3.3678,
+      "step": 27
+    },
+    {
+      "epoch": 0.005412475756619007,
+      "grad_norm": 3.3767316341400146,
+      "learning_rate": 0.0,
+      "loss": 3.3503,
+      "step": 30
+    },
+    {
+      "epoch": 0.005412475756619007,
+      "eval_loss": 3.3954291343688965,
+      "eval_runtime": 571.6345,
+      "eval_samples_per_second": 8.166,
+      "eval_steps_per_second": 2.042,
+      "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": 1.483774567120896e+16,
+  "total_flos": 2.225661850681344e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null