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:ef5950b3e173f515ffb1ebfe5344182b14cef393439715212c1455c04d3f7ebd
+oid sha256:abebd30ddb93d4d1bd7bd33de99a34f9a791073cc0a30f1b3cccf1284a6d1b03
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63b1ccc2423e6bd26680c5d9f3effda6f2cb4f4a2f5d937ac8d5dc4b585e1d1e
+oid sha256:bfee28ecfba2dd180864bd61227ecf13cedfa12c5d5aadc90e3f1c441f1376a0
 size 323290986

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec222382215b1fd911e1f9d923ef83dc7c6f7ea48c4d37361f397d827c182756
+oid sha256:6b31e7f5d7e166d0f2d2d3c9cd8b86d2d8f6ded3e47549a0d5cd339093d4cc4a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 3.7718515396118164,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.01805869074492099,
+  "best_metric": 3.655759572982788,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.02708803611738149,
   "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": 2.179,
       "eval_steps_per_second": 1.092,
       "step": 20
+    },
+    {
+      "epoch": 0.018961625282167043,
+      "grad_norm": 1.2040863037109375,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 3.7649,
+      "step": 21
+    },
+    {
+      "epoch": 0.02167042889390519,
+      "grad_norm": 1.3548814058303833,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 3.762,
+      "step": 24
+    },
+    {
+      "epoch": 0.022573363431151242,
+      "eval_loss": 3.676147222518921,
+      "eval_runtime": 214.9473,
+      "eval_samples_per_second": 2.173,
+      "eval_steps_per_second": 1.089,
+      "step": 25
+    },
+    {
+      "epoch": 0.02437923250564334,
+      "grad_norm": 1.168529748916626,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 3.4375,
+      "step": 27
+    },
+    {
+      "epoch": 0.02708803611738149,
+      "grad_norm": 1.4925258159637451,
+      "learning_rate": 0.0,
+      "loss": 3.9388,
+      "step": 30
+    },
+    {
+      "epoch": 0.02708803611738149,
+      "eval_loss": 3.655759572982788,
+      "eval_runtime": 213.1505,
+      "eval_samples_per_second": 2.191,
+      "eval_steps_per_second": 1.098,
+      "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": 1.4155533539868672e+16,
+  "total_flos": 2.114592047313715e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null