Training in progress, step 2638, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc7a32ae1a260d232561f8bfa7cadee6bbcd47aca2968958089976f95afd9512
+oid sha256:0d2d9a8d6795192f637c7fd56cae539e7d3120cfadfde689a0e8f65910f3e46c
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4630961c792966353518425385bb6bdec4ee01ada3092767c85b23a263ff78d
+oid sha256:d52f666587ac029c213c632acf57f59dae1c5a9631fcd09bc194b4473efa6bd1
 size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0df359f92a67934fe621c77a319e3203ed8bf9f11020a6732c84063a23dd6bca
+oid sha256:f996ce44acaa379abe63ccd766fc8a9cc3ce72bbc46d7af068e024d3c0760985
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f216ea40a4443b0f449133ae4ca79e6899c677cb6c40f87fbb71204a9e2a38ba
+oid sha256:8936bfdedeac688941b6f290fca3503d9a0d3f36a293d20a5b181c2f84403d43
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.396539568901062,
   "best_model_checkpoint": "miner_id_24/checkpoint-2550",
-  "epoch": 0.966824644549763,
+  "epoch": 1.0001895734597157,
   "eval_steps": 150,
-  "global_step": 2550,
+  "global_step": 2638,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1936,6 +1936,62 @@
       "eval_samples_per_second": 21.01,
       "eval_steps_per_second": 5.255,
       "step": 2550
+    },
+    {
+      "epoch": 0.9706161137440759,
+      "grad_norm": 0.7466861605644226,
+      "learning_rate": 2.239628211639977e-07,
+      "loss": 0.6012,
+      "step": 2560
+    },
+    {
+      "epoch": 0.9744075829383886,
+      "grad_norm": 0.7521525621414185,
+      "learning_rate": 1.7024815810632865e-07,
+      "loss": 0.4468,
+      "step": 2570
+    },
+    {
+      "epoch": 0.9781990521327014,
+      "grad_norm": 0.7282313704490662,
+      "learning_rate": 1.2387617489619253e-07,
+      "loss": 0.3767,
+      "step": 2580
+    },
+    {
+      "epoch": 0.9819905213270143,
+      "grad_norm": 0.6949441432952881,
+      "learning_rate": 8.485370469277776e-08,
+      "loss": 0.3192,
+      "step": 2590
+    },
+    {
+      "epoch": 0.985781990521327,
+      "grad_norm": 0.6286324262619019,
+      "learning_rate": 5.3186497665308474e-08,
+      "loss": 0.2562,
+      "step": 2600
+    },
+    {
+      "epoch": 0.9895734597156398,
+      "grad_norm": 0.6858911514282227,
+      "learning_rate": 2.8879220145727748e-08,
+      "loss": 0.5689,
+      "step": 2610
+    },
+    {
+      "epoch": 0.9933649289099526,
+      "grad_norm": 0.7098546624183655,
+      "learning_rate": 1.193545394109763e-08,
+      "loss": 0.3939,
+      "step": 2620
+    },
+    {
+      "epoch": 0.9971563981042654,
+      "grad_norm": 0.6426143050193787,
+      "learning_rate": 2.3576958057880406e-09,
+      "loss": 0.3271,
+      "step": 2630
     }
   ],
   "logging_steps": 10,
@@ -1959,12 +2015,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.2657873952762757e+18,
+  "total_flos": 2.3448665055370936e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null