Training in progress, step 161, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e7fb7070fe3c78032a4267d41e7551d82338b3c1462af03e404db5e84bdecc8
+oid sha256:5a75019b723da12847a8e67c1815cda6e19dcc55b097d8848e781654fa5d5fc0
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7405d83d907a493274d3e3b9d91bca7f5669f32c921d9204a236cdcf4f5effa2
+oid sha256:2e3bf2ee638a9e38c3c95bca2c91305df8981e6aa56dc253e59ae9f598ab819c
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b21ad250ed629583b981aa1751b7cc0399e9da392cb65450c78ad43fead7b681
+oid sha256:b97cdb702ca2d6b2ce010bfb78441526eef3f54e573dc99a3fb58801cf91a728
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77fecceef02880a4146c504aef986e50a2aa79b7ebef5c03c12015958eb0af66
+oid sha256:60772f64231e90f8ab464fc52a2e99407881e390f96f20fa87b685c94fc274b7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.5378552675247192,
   "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 2.803738317757009,
+  "epoch": 3.0093457943925235,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 161,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1089,6 +1089,83 @@
       "eval_samples_per_second": 13.584,
       "eval_steps_per_second": 3.471,
       "step": 150
+    },
+    {
+      "epoch": 2.822429906542056,
+      "grad_norm": 0.30164217948913574,
+      "learning_rate": 1.0782481637284013e-06,
+      "loss": 0.4942,
+      "step": 151
+    },
+    {
+      "epoch": 2.8411214953271027,
+      "grad_norm": 0.3085636794567108,
+      "learning_rate": 8.739801888871469e-07,
+      "loss": 0.4912,
+      "step": 152
+    },
+    {
+      "epoch": 2.8598130841121496,
+      "grad_norm": 0.31507790088653564,
+      "learning_rate": 6.909760573925561e-07,
+      "loss": 0.4403,
+      "step": 153
+    },
+    {
+      "epoch": 2.878504672897196,
+      "grad_norm": 0.31937018036842346,
+      "learning_rate": 5.29314981262985e-07,
+      "loss": 0.4012,
+      "step": 154
+    },
+    {
+      "epoch": 2.897196261682243,
+      "grad_norm": 0.32064154744148254,
+      "learning_rate": 3.8906693432924634e-07,
+      "loss": 0.3926,
+      "step": 155
+    },
+    {
+      "epoch": 2.9158878504672896,
+      "grad_norm": 0.3167048692703247,
+      "learning_rate": 2.702926219468882e-07,
+      "loss": 0.358,
+      "step": 156
+    },
+    {
+      "epoch": 2.9345794392523366,
+      "grad_norm": 0.3441549837589264,
+      "learning_rate": 1.7304345472035631e-07,
+      "loss": 0.3674,
+      "step": 157
+    },
+    {
+      "epoch": 2.953271028037383,
+      "grad_norm": 0.3453781306743622,
+      "learning_rate": 9.73615262502503e-08,
+      "loss": 0.3522,
+      "step": 158
+    },
+    {
+      "epoch": 2.97196261682243,
+      "grad_norm": 0.40237289667129517,
+      "learning_rate": 4.3279594913447905e-08,
+      "loss": 0.3334,
+      "step": 159
+    },
+    {
+      "epoch": 2.9906542056074765,
+      "grad_norm": 0.2904709279537201,
+      "learning_rate": 1.082106968385288e-08,
+      "loss": 0.4844,
+      "step": 160
+    },
+    {
+      "epoch": 3.0093457943925235,
+      "grad_norm": 0.5161787271499634,
+      "learning_rate": 0.0,
+      "loss": 0.6484,
+      "step": 161
     }
   ],
   "logging_steps": 1,
@@ -1112,12 +1189,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.054999739727872e+17,
+  "total_flos": 2.2051405370386022e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null