Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1da9f0e1748b79b0e2ea094ecc52c3475afb89979699261200296acbbf4c5b0
+oid sha256:52f74548e5a78bf6cf5abd1142a3d3f59959cf100a96d04c044c6ed5f08d299f
 size 1157746040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adfa8bf05dc665b19a9d27cdfc7aeb1f8e04a1e815cd33dacbdaff1b978c4950
+oid sha256:87b8ca7e671ccc87c1d407749d7a201f71c0c0c4b4c30b2b28565a76a6f97114
 size 588700500

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7211b19267643e4a4695239646f9fc645d8110b1d66e4a8494a1b44822fb5bcd
+oid sha256:e4f8738976c873c6ba5baff112bc02356e3685386bd797f76d4b2c4969703c33
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edaf981d1dfb35fd3b5ff50f9b58cbbedb093fe8427ac222964e342dc83dc071
+oid sha256:89df26d2648b7bbd96c19b1cc0947215f3b7f788b7b6e7a6d1179c8d03cbffea
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.625133752822876,
   "best_model_checkpoint": "miner_id_24/checkpoint-350",
-  "epoch": 0.0994742077589882,
+  "epoch": 0.1136848088674151,
   "eval_steps": 50,
-  "global_step": 350,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -316,6 +316,49 @@
       "eval_samples_per_second": 9.015,
       "eval_steps_per_second": 2.263,
       "step": 350
+    },
+    {
+      "epoch": 0.10231632798067358,
+      "grad_norm": 3.755326986312866,
+      "learning_rate": 4.540313094251309e-05,
+      "loss": 1.605,
+      "step": 360
+    },
+    {
+      "epoch": 0.10515844820235896,
+      "grad_norm": 3.1094276905059814,
+      "learning_rate": 3.958686804145719e-05,
+      "loss": 1.6938,
+      "step": 370
+    },
+    {
+      "epoch": 0.10800056842404433,
+      "grad_norm": 3.3867297172546387,
+      "learning_rate": 3.4079547545037634e-05,
+      "loss": 1.6012,
+      "step": 380
+    },
+    {
+      "epoch": 0.11084268864572971,
+      "grad_norm": 4.2931599617004395,
+      "learning_rate": 2.8908000565118947e-05,
+      "loss": 1.1067,
+      "step": 390
+    },
+    {
+      "epoch": 0.1136848088674151,
+      "grad_norm": 37.14210510253906,
+      "learning_rate": 2.4097422358745275e-05,
+      "loss": 1.8836,
+      "step": 400
+    },
+    {
+      "epoch": 0.1136848088674151,
+      "eval_loss": 1.6405808925628662,
+      "eval_runtime": 82.1006,
+      "eval_samples_per_second": 9.026,
+      "eval_steps_per_second": 2.266,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -330,7 +373,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -344,7 +387,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.106822301712384e+16,
+  "total_flos": 6.932068558700544e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null