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:a5d8a664404aa65418e3eed3b4445583558597a4f358d26b46a2f01be45d166e
+oid sha256:da2e4cca4ad239c2b73e6294a52ab696eb5bb8c91e00ca7e0164591fb14345cd
 size 12609416

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb85aeafc5a669b89863ec30fd549bdb658d0b47eba6dddc2a7367d859273f57
+oid sha256:e19a55330098c808368859381ab08697555af4ac7b83027c133081ac581db335
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82fff60c1567c80d7d34b54da8cfe5d29725416e64a96c9872b25aa85230d6ba
+oid sha256:a752c48a999f0b1fec49c94722b759e138cbe5a0cf927bd733aa9eb798e5016a
 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": 0.6370649933815002,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0012226994146326553,
+  "best_metric": 0.6279169321060181,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.0015283742682908191,
   "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": 14.629,
       "eval_steps_per_second": 7.315,
       "step": 20
+    },
+    {
+      "epoch": 0.001283834385364288,
+      "grad_norm": 4.617562294006348,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 2.4855,
+      "step": 21
+    },
+    {
+      "epoch": 0.0013449693560959209,
+      "grad_norm": 10.809088706970215,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 3.8675,
+      "step": 22
+    },
+    {
+      "epoch": 0.0014061043268275536,
+      "grad_norm": 3.4955766201019287,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 2.0119,
+      "step": 23
+    },
+    {
+      "epoch": 0.0014672392975591862,
+      "grad_norm": 5.152188777923584,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 3.0797,
+      "step": 24
+    },
+    {
+      "epoch": 0.0015283742682908191,
+      "grad_norm": 7.279388427734375,
+      "learning_rate": 0.0,
+      "loss": 2.4554,
+      "step": 25
+    },
+    {
+      "epoch": 0.0015283742682908191,
+      "eval_loss": 0.6279169321060181,
+      "eval_runtime": 471.6453,
+      "eval_samples_per_second": 14.604,
+      "eval_steps_per_second": 7.302,
+      "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": 204564804403200.0,
+  "total_flos": 262743785472000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null