Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cc6b349c88584d928ec74d7781121867cc6d3470865240ac4c43353e69478db
+oid sha256:308d9601ba077573b5c997659683c53992f444acd6b0ebfa273c6eeaa7f9708a
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b516410cfd0d9b327416c6b57ebad8a9c539bc9d5cb63c86951bab13fac1bbbc
+oid sha256:859863884225a703d3c0b0b03fd2e7bcfbe538f47e086c50efa86148bbc883b9
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13afc7b396ae81bcf059d4e0773a0bc122616b0208baad9f4c6e29d04eea6f2e
+oid sha256:cb1ba436a7b4c7a6297b6623ae3d115cdc640c3f7987c0afc62b31e7b2911f8a
 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": 0.505159854888916,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.07017543859649122,
+  "best_metric": 0.49777576327323914,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.10526315789473684,
   "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": 15.073,
       "eval_steps_per_second": 3.768,
       "step": 20
+    },
+    {
+      "epoch": 0.07368421052631578,
+      "grad_norm": 2.047795534133911,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 1.9805,
+      "step": 21
+    },
+    {
+      "epoch": 0.08421052631578947,
+      "grad_norm": 2.3392300605773926,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 2.1016,
+      "step": 24
+    },
+    {
+      "epoch": 0.08771929824561403,
+      "eval_loss": 0.49939754605293274,
+      "eval_runtime": 15.921,
+      "eval_samples_per_second": 15.074,
+      "eval_steps_per_second": 3.769,
+      "step": 25
+    },
+    {
+      "epoch": 0.09473684210526316,
+      "grad_norm": 2.271373748779297,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 2.029,
+      "step": 27
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 2.240652322769165,
+      "learning_rate": 0.0,
+      "loss": 1.9719,
+      "step": 30
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "eval_loss": 0.49777576327323914,
+      "eval_runtime": 15.9337,
+      "eval_samples_per_second": 15.062,
+      "eval_steps_per_second": 3.766,
+      "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": 1.4238372348297216e+16,
+  "total_flos": 2.1269667335110656e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null