Training in progress, step 170, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:480d04c6a926444def1429dc33a1fe22e39da7d221159d43c99b539437465d19
+oid sha256:777f88c0fb9cc4c42e43334f6d9fec0428b5b47952cada109214eb8aa3d44699
 size 194563400

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea4c7c222eac50c7b503e2aeddf3486cc8817aaf6f6a2db27055883f9fe0b1b1
+oid sha256:f5c5d9407152d844f63784c447d20896bc2e57aa3bf5775eed398b50d837bf04
 size 99235764

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41a3f09479c8db549f49ad67575d3a33d8f3d71007e65938dea57bdd9f47be60
+oid sha256:beb0c18b6062425824cddd605e9c9b215ab24c7c036f0e4d279ccb5c974403e3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9037087ffb4f9832ca5c41a5341235731b38f400553502e7da55d0ac1d1965dd
+oid sha256:9f0eb49a8f40f69ba68a14a6468b61014042911a930d1cd0d9dc3c51ec8f4713
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.9662845730781555,
   "best_model_checkpoint": "miner_id_24/checkpoint-140",
-  "epoch": 0.7776427703523694,
+  "epoch": 0.8262454434993924,
   "eval_steps": 10,
-  "global_step": 160,
+  "global_step": 170,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1263,6 +1263,84 @@
       "eval_samples_per_second": 3.448,
       "eval_steps_per_second": 0.699,
       "step": 160
+    },
+    {
+      "epoch": 0.7825030376670717,
+      "grad_norm": 0.11883629858493805,
+      "learning_rate": 0.0001887376873718548,
+      "loss": 0.8172,
+      "step": 161
+    },
+    {
+      "epoch": 0.787363304981774,
+      "grad_norm": 0.14962925016880035,
+      "learning_rate": 0.00018859093629069058,
+      "loss": 0.8627,
+      "step": 162
+    },
+    {
+      "epoch": 0.7922235722964763,
+      "grad_norm": 0.17162087559700012,
+      "learning_rate": 0.00018844329309978145,
+      "loss": 0.825,
+      "step": 163
+    },
+    {
+      "epoch": 0.7970838396111786,
+      "grad_norm": 0.14641453325748444,
+      "learning_rate": 0.00018829475928589271,
+      "loss": 0.8163,
+      "step": 164
+    },
+    {
+      "epoch": 0.8019441069258809,
+      "grad_norm": 0.1582384705543518,
+      "learning_rate": 0.00018814533634475822,
+      "loss": 1.0263,
+      "step": 165
+    },
+    {
+      "epoch": 0.8068043742405833,
+      "grad_norm": 0.15247194468975067,
+      "learning_rate": 0.00018799502578106534,
+      "loss": 0.8945,
+      "step": 166
+    },
+    {
+      "epoch": 0.8116646415552855,
+      "grad_norm": 0.1615608185529709,
+      "learning_rate": 0.00018784382910843976,
+      "loss": 0.9895,
+      "step": 167
+    },
+    {
+      "epoch": 0.8165249088699879,
+      "grad_norm": 0.1320793181657791,
+      "learning_rate": 0.0001876917478494303,
+      "loss": 0.8975,
+      "step": 168
+    },
+    {
+      "epoch": 0.8213851761846902,
+      "grad_norm": 0.15704546868801117,
+      "learning_rate": 0.00018753878353549357,
+      "loss": 0.8848,
+      "step": 169
+    },
+    {
+      "epoch": 0.8262454434993924,
+      "grad_norm": 0.15228189527988434,
+      "learning_rate": 0.00018738493770697852,
+      "loss": 1.062,
+      "step": 170
+    },
+    {
+      "epoch": 0.8262454434993924,
+      "eval_loss": 0.9668231010437012,
+      "eval_runtime": 62.8803,
+      "eval_samples_per_second": 3.451,
+      "eval_steps_per_second": 0.7,
+      "step": 170
     }
   ],
   "logging_steps": 1,
@@ -1277,7 +1355,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 2
+        "early_stopping_patience_counter": 3
       }
     },
     "TrainerControl": {
@@ -1286,12 +1364,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.2585189683167232e+17,
+  "total_flos": 2.3994561894285312e+17,
   "train_batch_size": 5,
   "trial_name": null,
   "trial_params": null