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:f680661f91cd13bffd05a44cd2827ec468605dd1e597569c841c1d172e019a30
+oid sha256:6a4e56c5007630d2df01c33c1a9b2820007cbf44cb2445890532f414ac3b4b47
 size 109009752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:850bec7ddf177c1b55bd204c2b50d4e5aaf2064625acad7cd289ed0a45092bed
+oid sha256:fc8d12fe175eeb71c05e2e78d34eef597d6be7340f5493244552bc35acbe4230
 size 56088148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c89f06444f5cc648c6780217f23fc6f5b8d3cdd68b0f37a0269f97a4299652c
+oid sha256:3f97758a5d16f310f615cddfbb1fad1883be440852915cab3d4ed0447c741e8a
 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": 1.2643587589263916,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.01701041888156496,
+  "best_metric": 1.2515279054641724,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.02551562832234744,
   "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": 4.374,
       "eval_steps_per_second": 1.096,
       "step": 20
+    },
+    {
+      "epoch": 0.017860939825643206,
+      "grad_norm": 0.34396985173225403,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 1.2435,
+      "step": 21
+    },
+    {
+      "epoch": 0.02041250265787795,
+      "grad_norm": 0.46297478675842285,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 1.2216,
+      "step": 24
+    },
+    {
+      "epoch": 0.0212630236019562,
+      "eval_loss": 1.2535417079925537,
+      "eval_runtime": 225.9946,
+      "eval_samples_per_second": 4.381,
+      "eval_steps_per_second": 1.097,
+      "step": 25
+    },
+    {
+      "epoch": 0.022964065490112696,
+      "grad_norm": 0.34886497259140015,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 1.2274,
+      "step": 27
+    },
+    {
+      "epoch": 0.02551562832234744,
+      "grad_norm": 0.47201740741729736,
+      "learning_rate": 0.0,
+      "loss": 1.2441,
+      "step": 30
+    },
+    {
+      "epoch": 0.02551562832234744,
+      "eval_loss": 1.2515279054641724,
+      "eval_runtime": 226.9002,
+      "eval_samples_per_second": 4.363,
+      "eval_steps_per_second": 1.093,
+      "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": 1.943208091189248e+16,
+  "total_flos": 2.788081174315008e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null