Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b35b9ed461c3e6c546c79105d1fb4d0d9891b9ab3f9f3f3e75939707bf9d392
+oid sha256:e4f9bf03f12ed06be301210d17dd9dc60de4e45055c2f6b70eb0b64a0c92bccf
 size 34456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5138b999f241cc70c33276c38055d7475a58ef427f9f7a27f9d968ab9cd0dea
+oid sha256:31fb9aa928a84806913284f78e9893258be257089130e887e4892f63a0e0db3a
 size 73222

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:626e1547b92e89d816564ade29e030b0c151d52c605ae4cae652cac0cd286dca
+oid sha256:6a338581079056173815c84f21c20ce58416dd85f7b2a0826e764ca82b3348bd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e883b7b3f89fde3f0f981a15cfeb8504571510ffa0b99f735bed98a1fe00478
+oid sha256:d5ad005f18ad2c3c460e78d824d33373300bb1b0c9741a994c687b284a694890
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 11.5,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.08751458576429405,
+  "epoch": 0.11668611435239207,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 180.627,
       "eval_steps_per_second": 45.282,
       "step": 150
+    },
+    {
+      "epoch": 0.09334889148191365,
+      "grad_norm": 0.0020716609433293343,
+      "learning_rate": 0.00017451298973437308,
+      "loss": 23.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.09918319719953325,
+      "grad_norm": 0.0024205869995057583,
+      "learning_rate": 0.0001694167565454241,
+      "loss": 23.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.10501750291715285,
+      "grad_norm": 0.002702507423236966,
+      "learning_rate": 0.0001639896397455543,
+      "loss": 23.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.11085180863477247,
+      "grad_norm": 0.005600139033049345,
+      "learning_rate": 0.0001582580797022808,
+      "loss": 23.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.11668611435239207,
+      "grad_norm": 0.003788295201957226,
+      "learning_rate": 0.00015225,
+      "loss": 23.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.11668611435239207,
+      "eval_loss": 11.5,
+      "eval_runtime": 3.9381,
+      "eval_samples_per_second": 183.338,
+      "eval_steps_per_second": 45.961,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -158,7 +201,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 2
+        "early_stopping_patience_counter": 3
       }
     },
     "TrainerControl": {
@@ -167,12 +210,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3024905404416.0,
+  "total_flos": 4029857366016.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null