Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e0f372637e0c7150930c7bc438678212e19018dcb70b6aa2ba2db3101dbaade
+oid sha256:fc7b8f58f44db658f7be52e7653f19a7a12663f30ab8dd27f9931f7d1375e9c9
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e73012e58fffb212d8b7527be320dbc5c8fdf4b94c951e454f740d5a9c0709b3
+oid sha256:9b23eb7d4a7be164e2245818345b80ef5bb9e074c51e70a071ac7a8af8973cac
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c85a5d20398029878a337e126c42e0d688a3349e9c9799e99f9ca3261cda24e
+oid sha256:29bce83e54e27a417e6f41105c647d262513f5288c47ffd3bc8c48a4eee15073
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
+oid sha256:4521b8db9cc205e54aa606d85e707c024abd2d8ad4a20bec4b2cff365dc59cdf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.4975270628929138,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.008487163165711862,
+  "best_metric": 0.4909574091434479,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.010608953957139827,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,49 @@
       "eval_samples_per_second": 2.921,
       "eval_steps_per_second": 1.462,
       "step": 20
+    },
+    {
+      "epoch": 0.008911521323997454,
+      "grad_norm": 0.7785081267356873,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.4113,
+      "step": 21
+    },
+    {
+      "epoch": 0.009335879482283047,
+      "grad_norm": 0.7753713130950928,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.4395,
+      "step": 22
+    },
+    {
+      "epoch": 0.00976023764056864,
+      "grad_norm": 1.0116839408874512,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.4698,
+      "step": 23
+    },
+    {
+      "epoch": 0.010184595798854232,
+      "grad_norm": 0.8368872404098511,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.4849,
+      "step": 24
+    },
+    {
+      "epoch": 0.010608953957139827,
+      "grad_norm": 1.0019539594650269,
+      "learning_rate": 0.0,
+      "loss": 0.4729,
+      "step": 25
+    },
+    {
+      "epoch": 0.010608953957139827,
+      "eval_loss": 0.4909574091434479,
+      "eval_runtime": 346.4561,
+      "eval_samples_per_second": 2.866,
+      "eval_steps_per_second": 1.435,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -210,12 +253,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6704670399528960.0,
+  "total_flos": 8461756435267584.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null