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:f31fe1d8c6eb4a852554561fafad5c8146e9307dfbcac2c39b1ccb801042df67
+oid sha256:eb9449f501a33fb4c39e0b40504f046f2e72b1c2aa6e0561d024a615b207b315
 size 9864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b1f60e31c91218d21b60727655515b475b3bcd6f9d5cf8ec510de118da4e84e
+oid sha256:9811d07e42d70936c46aef69a289074a1424bd7d4e78b7c0e342b99de28ae0b7
 size 24006

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5e3ee68625628f94a974f985412f9b3f0f12a64e78854d3ec5a93beccc0d80f
+oid sha256:478c5ca077b63e58ceada58b8a7e42535a678f763a7be5cfb22fca483d4106e5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44be7752e8f250f5c645b94c737a086e3ba6f8529fa94bf2d0ed1a0911f14f5a
+oid sha256:08c6d9b93a9a31eb6ebeb3ab3dc09ba23202435e453d5c3be3fefb3bbf21d637
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 11.5,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.020483408439164276,
+  "epoch": 0.027311211252219036,
   "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": 88.116,
       "eval_steps_per_second": 22.029,
       "step": 150
+    },
+    {
+      "epoch": 0.02184896900177523,
+      "grad_norm": 5.329944542609155e-05,
+      "learning_rate": 0.0001753726596345424,
+      "loss": 23.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.02321452956438618,
+      "grad_norm": 4.0211780287791044e-05,
+      "learning_rate": 0.00017025132184860355,
+      "loss": 23.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.024580090126997134,
+      "grad_norm": 7.137226202758029e-05,
+      "learning_rate": 0.00016479747048321714,
+      "loss": 23.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.025945650689608083,
+      "grad_norm": 0.00010167378059122711,
+      "learning_rate": 0.00015903767615401616,
+      "loss": 23.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.027311211252219036,
+      "grad_norm": 0.0001430771080777049,
+      "learning_rate": 0.000153,
+      "loss": 23.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.027311211252219036,
+      "eval_loss": 11.5,
+      "eval_runtime": 34.9549,
+      "eval_samples_per_second": 88.228,
+      "eval_steps_per_second": 22.057,
+      "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": 5405920002048.0,
+  "total_flos": 7191269965824.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null