Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ab162ca70ec28d3082584d23d98be9ac43bc5f2a17f6c241ff40c76d68e0716
+oid sha256:8500343cd233745bde80232240d82975e67e763b3b674b1f1b9d47e3629c9590
 size 56662952

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71fdf13d341f5206ae7bbe8eabbcd9673f7080d281718ee1175c2432746e7173
+oid sha256:2e59583aa4479ed12dda80dd9640090b064c057d773484b99a55cf3b533b9695
 size 113488058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3aff579637cfa6683f2ae549836cfa528ed063daedc8e024acac820ccaf0039
+oid sha256:a4c51f9108a8a9eff488033a9bf6af40c8cfc6b5bd82d256e7494c9ade7936f7
 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": 0.785580575466156,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0003789385930010042,
+  "best_metric": 0.7517985105514526,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0005684078895015062,
   "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": 36.363,
       "eval_steps_per_second": 18.182,
       "step": 20
+    },
+    {
+      "epoch": 0.0003978855226510544,
+      "grad_norm": 2.369555950164795,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 3.2738,
+      "step": 21
+    },
+    {
+      "epoch": 0.00045472631160120504,
+      "grad_norm": 2.318856716156006,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 3.1185,
+      "step": 24
+    },
+    {
+      "epoch": 0.0004736732412512552,
+      "eval_loss": 0.7574231624603271,
+      "eval_runtime": 610.8614,
+      "eval_samples_per_second": 36.38,
+      "eval_steps_per_second": 18.191,
+      "step": 25
+    },
+    {
+      "epoch": 0.0005115671005513556,
+      "grad_norm": 1.9150217771530151,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 3.0714,
+      "step": 27
+    },
+    {
+      "epoch": 0.0005684078895015062,
+      "grad_norm": 2.5222971439361572,
+      "learning_rate": 0.0,
+      "loss": 3.2386,
+      "step": 30
+    },
+    {
+      "epoch": 0.0005684078895015062,
+      "eval_loss": 0.7517985105514526,
+      "eval_runtime": 610.903,
+      "eval_samples_per_second": 36.377,
+      "eval_steps_per_second": 18.189,
+      "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": 1427399245824000.0,
+  "total_flos": 2118560985907200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null