Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06a71f0c6f1593e27b6a57b5c8074ab724a84182e88f2ccb097c3d043fbcc696
+oid sha256:f792b1e515069d6be95c2af426f051a2ee96adbac573ffca33e8a35e6041228d
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1fbee43aad6759954f6961f1a13f6fcbd4482c173e671c90bfac32ed47da69a
+oid sha256:2e7a83a8930d1bb48b63817eeccb9528cffbae134da7b86f87a07bc6ded5ad50
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f120eab57cb34758db5a40733b0284a6893b7e3c880198a795a94e4423192bb
+oid sha256:9eaa33d20e07dc1f46cd2a040ebc866469aea3a5fa481cb8089c458c623632f8
 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": 0.9269101023674011,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.008506113769271665,
+  "best_metric": 0.9118663668632507,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.012759170653907496,
   "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": 7.546,
       "eval_steps_per_second": 3.773,
       "step": 20
+    },
+    {
+      "epoch": 0.008931419457735247,
+      "grad_norm": 1.3416038751602173,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 3.798,
+      "step": 21
+    },
+    {
+      "epoch": 0.010207336523125997,
+      "grad_norm": 1.850062608718872,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 3.9275,
+      "step": 24
+    },
+    {
+      "epoch": 0.01063264221158958,
+      "eval_loss": 0.9143272042274475,
+      "eval_runtime": 131.3764,
+      "eval_samples_per_second": 7.536,
+      "eval_steps_per_second": 3.768,
+      "step": 25
+    },
+    {
+      "epoch": 0.011483253588516746,
+      "grad_norm": 1.4373589754104614,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 3.4133,
+      "step": 27
+    },
+    {
+      "epoch": 0.012759170653907496,
+      "grad_norm": 1.2759556770324707,
+      "learning_rate": 0.0,
+      "loss": 3.5974,
+      "step": 30
+    },
+    {
+      "epoch": 0.012759170653907496,
+      "eval_loss": 0.9118663668632507,
+      "eval_runtime": 131.5224,
+      "eval_samples_per_second": 7.527,
+      "eval_steps_per_second": 3.764,
+      "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