Training in progress, step 1350, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:087c6da6c560a25ffb7ab92c0d5605bdadac7ab728ca24d5c46d4038a89b3997
+oid sha256:5dd59cc37c01e371a95eb2d0658162ad360f53603d8c21065f49d74c625c47dd
 size 608282672

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e8002c1ba0f67145f1d3f1b8d01383441830ed3058ddb031a0c2f4b678c2cc3
+oid sha256:02634bdb3e98cef96461ceed468b5470bbe070408556bd4cfec2ab82673ca362
 size 168149074

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:379ffe2a6c1e7c30b5d2c9f431b8b3af760b3661da210b891dd64a757c20122d
+oid sha256:d5b95f764d72ed6aa17d7197e22e16e0cc217530d7d3f18f36eafb2b4ceb1e32
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:beb0b0f4cb227409c25efa2d36f03edfc3a0032e3296f1707945c3a0c5611cc5
+oid sha256:a866955cff9370cd3957339d6bf23f5ca8494fc491b0c5ef9330a9273b5d4460
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.714248538017273,
-  "best_model_checkpoint": "miner_id_24/checkpoint-1050",
-  "epoch": 2.1534320323014806,
+  "best_metric": 0.714054524898529,
+  "best_model_checkpoint": "miner_id_24/checkpoint-1350",
+  "epoch": 2.4226110363391653,
   "eval_steps": 150,
-  "global_step": 1200,
+  "global_step": 1350,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -919,6 +919,119 @@
       "eval_samples_per_second": 9.865,
       "eval_steps_per_second": 1.24,
       "step": 1200
+    },
+    {
+      "epoch": 2.171377299237326,
+      "grad_norm": 5.972046375274658,
+      "learning_rate": 2.86474508437579e-06,
+      "loss": 2.8707,
+      "step": 1210
+    },
+    {
+      "epoch": 2.1893225661731717,
+      "grad_norm": 3.227733850479126,
+      "learning_rate": 2.67658249108603e-06,
+      "loss": 2.4486,
+      "step": 1220
+    },
+    {
+      "epoch": 2.2072678331090176,
+      "grad_norm": 3.5549120903015137,
+      "learning_rate": 2.4942045588130504e-06,
+      "loss": 2.3472,
+      "step": 1230
+    },
+    {
+      "epoch": 2.225213100044863,
+      "grad_norm": 4.020270347595215,
+      "learning_rate": 2.317696896481024e-06,
+      "loss": 2.6453,
+      "step": 1240
+    },
+    {
+      "epoch": 2.2431583669807087,
+      "grad_norm": 4.551384925842285,
+      "learning_rate": 2.1471423574861643e-06,
+      "loss": 2.777,
+      "step": 1250
+    },
+    {
+      "epoch": 2.2611036339165547,
+      "grad_norm": 5.8825812339782715,
+      "learning_rate": 1.982621000804979e-06,
+      "loss": 2.8939,
+      "step": 1260
+    },
+    {
+      "epoch": 2.2790489008524,
+      "grad_norm": 3.2557361125946045,
+      "learning_rate": 1.8242100534143065e-06,
+      "loss": 2.5914,
+      "step": 1270
+    },
+    {
+      "epoch": 2.2969941677882457,
+      "grad_norm": 3.4699723720550537,
+      "learning_rate": 1.6719838740406313e-06,
+      "loss": 2.3236,
+      "step": 1280
+    },
+    {
+      "epoch": 2.3149394347240917,
+      "grad_norm": 4.2601752281188965,
+      "learning_rate": 1.5260139182558363e-06,
+      "loss": 2.6321,
+      "step": 1290
+    },
+    {
+      "epoch": 2.332884701659937,
+      "grad_norm": 4.615097522735596,
+      "learning_rate": 1.3863687049356465e-06,
+      "loss": 2.8052,
+      "step": 1300
+    },
+    {
+      "epoch": 2.3508299685957827,
+      "grad_norm": 5.796968936920166,
+      "learning_rate": 1.25311378409661e-06,
+      "loss": 2.9489,
+      "step": 1310
+    },
+    {
+      "epoch": 2.3687752355316287,
+      "grad_norm": 3.3097987174987793,
+      "learning_rate": 1.1263117061266677e-06,
+      "loss": 2.4068,
+      "step": 1320
+    },
+    {
+      "epoch": 2.3867205024674742,
+      "grad_norm": 3.570329427719116,
+      "learning_rate": 1.006021992423738e-06,
+      "loss": 2.3704,
+      "step": 1330
+    },
+    {
+      "epoch": 2.4046657694033198,
+      "grad_norm": 3.7566256523132324,
+      "learning_rate": 8.923011074561405e-07,
+      "loss": 2.5744,
+      "step": 1340
+    },
+    {
+      "epoch": 2.4226110363391653,
+      "grad_norm": 4.76233434677124,
+      "learning_rate": 7.852024322579649e-07,
+      "loss": 2.684,
+      "step": 1350
+    },
+    {
+      "epoch": 2.4226110363391653,
+      "eval_loss": 0.714054524898529,
+      "eval_runtime": 95.2194,
+      "eval_samples_per_second": 9.861,
+      "eval_steps_per_second": 1.239,
+      "step": 1350
     }
   ],
   "logging_steps": 10,
@@ -933,7 +1046,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -947,7 +1060,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.2309772145626972e+18,
+  "total_flos": 2.50754898332536e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null