Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b32214d468ab6732fb01c5e5b492ecf3af95915bf12b368b8b456d19cbb17ce
+oid sha256:6372a132fd1b52016a9caccd8606ef4438372ef87c601844cb18f9735025e046
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4541276bcbd02d62f18ec90f370144a040bd157b6aa82cd978f17a7ee58b51e8
+oid sha256:032a7e252c371619f6fe96f7d57eed739880f288cd779d6127c8b95528fd9b00
 size 320082106

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e73b09dfedcc20fe98c028842939a948923b18ad251d24eb8236e87e8f64ea6
+oid sha256:ebf772bc926118d68bbad5abedaf339646da8a2796802f9d60a89d9af85a2665
 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": 1.7412056922912598,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0010095146758195997,
+  "best_metric": 1.733486294746399,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0015142720137293997,
   "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": 5.942,
       "eval_steps_per_second": 2.971,
       "step": 20
+    },
+    {
+      "epoch": 0.0010599904096105796,
+      "grad_norm": 0.23081372678279877,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 1.8133,
+      "step": 21
+    },
+    {
+      "epoch": 0.0012114176109835196,
+      "grad_norm": 0.24668963253498077,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.7785,
+      "step": 24
+    },
+    {
+      "epoch": 0.0012618933447744996,
+      "eval_loss": 1.735094666481018,
+      "eval_runtime": 1403.5657,
+      "eval_samples_per_second": 5.943,
+      "eval_steps_per_second": 2.972,
+      "step": 25
+    },
+    {
+      "epoch": 0.0013628448123564597,
+      "grad_norm": 0.2573795020580292,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 1.6955,
+      "step": 27
+    },
+    {
+      "epoch": 0.0015142720137293997,
+      "grad_norm": 0.25954729318618774,
+      "learning_rate": 0.0,
+      "loss": 1.7924,
+      "step": 30
+    },
+    {
+      "epoch": 0.0015142720137293997,
+      "eval_loss": 1.733486294746399,
+      "eval_runtime": 1403.6226,
+      "eval_samples_per_second": 5.943,
+      "eval_steps_per_second": 2.972,
+      "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": 9475143927595008.0,
+  "total_flos": 1.388598679044096e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null