Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:657772b9f346a5108e8dd264d2760ab54462cc33c92496fef3a23debc9c640b7
+oid sha256:cf724e710b5fe85170a46bfc94c4648c409127de448318d0171ebc2220c899e2
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3d7c71e28c4bee400fee172018472dbd2582caa48e5e7ea99c405a1c929f7e4
+oid sha256:2cab32bbb9f600be033b93461304e980b5af3252d5771ac3aebb7b3f4945b3c8
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1698424ff146bcbfe1356a243484a7bf217ef6a25305200a2a40567c1858ba0
+oid sha256:2e3540149a4da276050c8040279e53fbd6bae2961729657791763596edd20e7b
 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": 1.3187538385391235,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0015241869415283786,
+  "best_metric": 1.306259036064148,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0022862804122925676,
   "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": 17.422,
       "eval_steps_per_second": 8.712,
       "step": 20
+    },
+    {
+      "epoch": 0.0016003962886047974,
+      "grad_norm": 1.3565210103988647,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 5.1341,
+      "step": 21
+    },
+    {
+      "epoch": 0.0018290243298340542,
+      "grad_norm": 1.1311779022216797,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 5.3614,
+      "step": 24
+    },
+    {
+      "epoch": 0.001905233676910473,
+      "eval_loss": 1.3094598054885864,
+      "eval_runtime": 318.1539,
+      "eval_samples_per_second": 17.366,
+      "eval_steps_per_second": 8.684,
+      "step": 25
+    },
+    {
+      "epoch": 0.002057652371063311,
+      "grad_norm": 1.2344831228256226,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 5.4583,
+      "step": 27
+    },
+    {
+      "epoch": 0.0022862804122925676,
+      "grad_norm": 1.1939010620117188,
+      "learning_rate": 0.0,
+      "loss": 5.4103,
+      "step": 30
+    },
+    {
+      "epoch": 0.0022862804122925676,
+      "eval_loss": 1.306259036064148,
+      "eval_runtime": 316.9298,
+      "eval_samples_per_second": 17.433,
+      "eval_steps_per_second": 8.718,
+      "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": 3684183016734720.0,
+  "total_flos": 5526274525102080.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null