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:e84e39b96f66dd2dc058d7f005767301cf4eb378ad758357c8d0db1fbb0e3ca7
+oid sha256:4d830768fffc7ad146ac0d1ae3d5910f30dc7ef1963ddaadbc86a645c39946c5
 size 100690288

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:035cbdcf7b0fd17e88289894b5eab564b2d7d3cd817d3971ef8978a86bb41580
+oid sha256:ed86d5e5311a86f62d63d083a9eb932db531932d973fb8702bc96b906cc6a950
 size 51344890

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a5e35292f48fe5dcedcd4adb76a6c066107df32ab44e79e28ddb2c7166b61f8
+oid sha256:255e5e093c94359a0ffbd2b1118f21b626003264f92ed11b6d39296a92df8755
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5220d0af0ff98b2d6e04334f1c29842da7230747bf3383cf1f883a4d2eb6d4f2
+oid sha256:90c455b2a7603e9003556345290fd0185bd6c6017de2b595e3f9c6216f721e5e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9537206292152405,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.008840690752637473,
+  "best_metric": 0.9498990178108215,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.011787587670183296,
   "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": 22.307,
       "eval_steps_per_second": 5.579,
       "step": 150
+    },
+    {
+      "epoch": 0.009430070136146638,
+      "grad_norm": 1.7608845233917236,
+      "learning_rate": 2.2644444444444443e-06,
+      "loss": 0.8132,
+      "step": 160
+    },
+    {
+      "epoch": 0.010019449519655802,
+      "grad_norm": 1.804176926612854,
+      "learning_rate": 1.6983333333333333e-06,
+      "loss": 0.8789,
+      "step": 170
+    },
+    {
+      "epoch": 0.010608828903164967,
+      "grad_norm": 2.2931344509124756,
+      "learning_rate": 1.1322222222222221e-06,
+      "loss": 0.9468,
+      "step": 180
+    },
+    {
+      "epoch": 0.011198208286674132,
+      "grad_norm": 2.321553945541382,
+      "learning_rate": 5.661111111111111e-07,
+      "loss": 1.0531,
+      "step": 190
+    },
+    {
+      "epoch": 0.011787587670183296,
+      "grad_norm": 3.831026077270508,
+      "learning_rate": 0.0,
+      "loss": 1.0614,
+      "step": 200
+    },
+    {
+      "epoch": 0.011787587670183296,
+      "eval_loss": 0.9498990178108215,
+      "eval_runtime": 240.2481,
+      "eval_samples_per_second": 22.302,
+      "eval_steps_per_second": 5.578,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -167,12 +210,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6822246010060800.0,
+  "total_flos": 9096328013414400.0,
   "train_batch_size": 6,
   "trial_name": null,
   "trial_params": null