Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51896c32ad4cd846f76d92f9021b8246277f2f73e690742d67c1339e96952c36
+oid sha256:0a7c1850bb82fd162410f68024a0ee0391eabadb7c77cfe32d1fdd78b71e6d21
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50624f1c2df90bb7cd7a7d02ae229f1434e9c8b495c65f265ed2a9cf77d94c83
+oid sha256:3b3b73a7752a1459513724118a56b9d9c2c9d3579c304110242f79171a9cc7cd
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00b243aea78e1eb9c2783b2ede924fa98ed34ea4662672ae5272ac00736eb8da
+oid sha256:9fedad20328739b48a278e5d6bf7b598b93e7e9e6122794784a428c2cbfe64d0
 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": 0.9966016411781311,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.011778563015312132,
+  "best_metric": 0.9854258298873901,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0176678445229682,
   "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": 0.966,
       "eval_steps_per_second": 0.242,
       "step": 20
+    },
+    {
+      "epoch": 0.012367491166077738,
+      "grad_norm": 0.7645674347877502,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 3.8865,
+      "step": 21
+    },
+    {
+      "epoch": 0.014134275618374558,
+      "grad_norm": 0.6579309105873108,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 4.0399,
+      "step": 24
+    },
+    {
+      "epoch": 0.014723203769140165,
+      "eval_loss": 0.9871670007705688,
+      "eval_runtime": 1466.2758,
+      "eval_samples_per_second": 0.975,
+      "eval_steps_per_second": 0.244,
+      "step": 25
+    },
+    {
+      "epoch": 0.015901060070671377,
+      "grad_norm": 0.6547338366508484,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 3.7659,
+      "step": 27
+    },
+    {
+      "epoch": 0.0176678445229682,
+      "grad_norm": 0.6517524719238281,
+      "learning_rate": 0.0,
+      "loss": 4.2543,
+      "step": 30
+    },
+    {
+      "epoch": 0.0176678445229682,
+      "eval_loss": 0.9854258298873901,
+      "eval_runtime": 1474.3562,
+      "eval_samples_per_second": 0.97,
+      "eval_steps_per_second": 0.243,
+      "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": 5.0782317576192e+16,
+  "total_flos": 7.6173476364288e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null