Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20f0e1542c13f7e08f1c3c20478f2a253bfd5a8f74164a10796a0f1cd4cfcdc3
+oid sha256:1c7ec78ee16fbf8215c7d122c8ee57db19168f0b8b84558097d075e3d3c69b41
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab3f4c728a10d21be89f98758bfdf3400c2ed7c154ee168915e23d12ac17002f
+oid sha256:3a866e17ad64c68ac0d7d00d563c3ceb82903d34425a9839b75235e537dc1a72
 size 148047722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1602f4b9e7c9bf339373e2c887608333f686af18bd19f710db43367937f27367
+oid sha256:f21817f11d5487005de742e9d4bcd3ada581b65221b66cdd367ec2cd636b3b5d
 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": 2.077925443649292,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0006442209355698537,
+  "best_metric": 2.0622153282165527,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0009663314033547805,
   "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": 21.922,
       "eval_steps_per_second": 10.961,
       "step": 20
+    },
+    {
+      "epoch": 0.0006764319823483463,
+      "grad_norm": 0.41135507822036743,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 1.9462,
+      "step": 21
+    },
+    {
+      "epoch": 0.0007730651226838244,
+      "grad_norm": 0.38372039794921875,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.9378,
+      "step": 24
+    },
+    {
+      "epoch": 0.0008052761694623171,
+      "eval_loss": 2.0651965141296387,
+      "eval_runtime": 590.8792,
+      "eval_samples_per_second": 22.123,
+      "eval_steps_per_second": 11.061,
+      "step": 25
+    },
+    {
+      "epoch": 0.0008696982630193024,
+      "grad_norm": 0.42051398754119873,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 2.0133,
+      "step": 27
+    },
+    {
+      "epoch": 0.0009663314033547805,
+      "grad_norm": 0.40871503949165344,
+      "learning_rate": 0.0,
+      "loss": 2.0912,
+      "step": 30
+    },
+    {
+      "epoch": 0.0009663314033547805,
+      "eval_loss": 2.0622153282165527,
+      "eval_runtime": 592.6925,
+      "eval_samples_per_second": 22.055,
+      "eval_steps_per_second": 11.028,
+      "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": 1306268836823040.0,
+  "total_flos": 1959403255234560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null