Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e37405de8391ef7687baf9d7901cb51843117399ea1d9d259aa61ebf90223d51
+oid sha256:00cbea13bb72c37a5c6cb295de2488fdba0bd33a728fc6549ca08cfa27eebd04
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2c086033575fb443c2ffedcfbc78e34ddd715147bd8980645463444933d4f32
+oid sha256:2210e45cb50bc6bbaa19796495757ee2d4fc139b8d2e3ead56b88009ccb337ba
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc3e6b3c3225c0d18610ff0681c760c9a53bdc6330a7fa4105d2b548f0d683b5
+oid sha256:32036baf2129b14295a305d74eaad3e3f5de7d0b68ae15034683f37d0722de79
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
+oid sha256:4521b8db9cc205e54aa606d85e707c024abd2d8ad4a20bec4b2cff365dc59cdf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.330055594444275,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.049049662783568364,
+  "best_metric": 1.3201075792312622,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.061312078479460456,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,49 @@
       "eval_samples_per_second": 3.124,
       "eval_steps_per_second": 1.562,
       "step": 20
+    },
+    {
+      "epoch": 0.05150214592274678,
+      "grad_norm": 1.3180733919143677,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.9756,
+      "step": 21
+    },
+    {
+      "epoch": 0.0539546290619252,
+      "grad_norm": 1.5977431535720825,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.1031,
+      "step": 22
+    },
+    {
+      "epoch": 0.056407112201103615,
+      "grad_norm": 1.7216845750808716,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 1.225,
+      "step": 23
+    },
+    {
+      "epoch": 0.05885959534028203,
+      "grad_norm": 1.3368281126022339,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 1.0769,
+      "step": 24
+    },
+    {
+      "epoch": 0.061312078479460456,
+      "grad_norm": 2.0585391521453857,
+      "learning_rate": 0.0,
+      "loss": 1.5834,
+      "step": 25
+    },
+    {
+      "epoch": 0.061312078479460456,
+      "eval_loss": 1.3201075792312622,
+      "eval_runtime": 53.7749,
+      "eval_samples_per_second": 3.199,
+      "eval_steps_per_second": 1.599,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -210,12 +253,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6352059230060544.0,
+  "total_flos": 7858637380780032.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null