Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9bbdb53454ddb4bfbc50c2610739c46a0363647c906555a909ff08714815fda
+oid sha256:e88ebe2be20788bc539651b679a971a801ee85910b8abd6df89ad42bd3c3a98d
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d00896b81ff7ea25b18a342d9773da1dfcce8b64289adb8bbfd84f519fceadfa
+oid sha256:d51f71196ad4e4a8a836f94df07d58951f608b6543cbc049b2ade08dbd0b685c
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0051399e6a3dd54a71b6d6dd16c16b02bb8aff2beada0d9f4a8af47bdba0ba47
+oid sha256:f81882bc0516d4b960f29597047d8635d2fc194ec9f38f0e37d605856653d7bf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd4836ddf60b44e58a6b1c94aa6a6c90a55c6b9d3781b50bd68866141db98eb6
+oid sha256:44be7752e8f250f5c645b94c737a086e3ba6f8529fa94bf2d0ed1a0911f14f5a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.5598700642585754,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.019753086419753086,
+  "epoch": 0.02962962962962963,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 13.558,
       "eval_steps_per_second": 3.389,
       "step": 100
+    },
+    {
+      "epoch": 0.021728395061728394,
+      "grad_norm": 3.2152905464172363,
+      "learning_rate": 0.00019518163667954527,
+      "loss": 1.2275,
+      "step": 110
+    },
+    {
+      "epoch": 0.023703703703703703,
+      "grad_norm": 5.397396087646484,
+      "learning_rate": 0.00019206065447161056,
+      "loss": 1.1189,
+      "step": 120
+    },
+    {
+      "epoch": 0.02567901234567901,
+      "grad_norm": 5.359374523162842,
+      "learning_rate": 0.00018850090580795544,
+      "loss": 0.6904,
+      "step": 130
+    },
+    {
+      "epoch": 0.027654320987654323,
+      "grad_norm": 8.899271011352539,
+      "learning_rate": 0.00018451973342624464,
+      "loss": 1.3084,
+      "step": 140
+    },
+    {
+      "epoch": 0.02962962962962963,
+      "grad_norm": 43.73984909057617,
+      "learning_rate": 0.00018013653319813575,
+      "loss": 2.3037,
+      "step": 150
+    },
+    {
+      "epoch": 0.02962962962962963,
+      "eval_loss": 0.7312282919883728,
+      "eval_runtime": 157.912,
+      "eval_samples_per_second": 13.501,
+      "eval_steps_per_second": 3.375,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -115,7 +158,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 2
       }
     },
     "TrainerControl": {
@@ -129,7 +172,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.370090452385792e+16,
+  "total_flos": 3.523832597132083e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null