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:dd17faa28b705c00725ed94ca7e640238d5f8156d9688eef6307db3c8644c7c4
+oid sha256:1ee8a36cb5df9294381d0fd23b73a590e6db41af2bc9f3c753f95305120139e3
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bef34617dadb4f71f9fd15ec4102ccda16f2d0c01761e6c5e57fcd2bb402a601
+oid sha256:cfa48b22aa492c3950b6c45c7641a19a8f4e3b35ace25f9f7fb0813967b665c7
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcf7798404e1bc6a3d9600a9f3df20469c8b23af137a19e5bc32db3bc281bffc
+oid sha256:b4d2d28e1797428fac2128d77d92984fd0a27f275b217114cc3c25416633d98b
 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": 0.6605696082115173,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0033819488480236735,
+  "best_metric": 0.6571388244628906,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.004227436060029592,
   "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": 8.423,
       "eval_steps_per_second": 4.212,
       "step": 20
+    },
+    {
+      "epoch": 0.0035510462904248573,
+      "grad_norm": 0.47143518924713135,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.7764,
+      "step": 21
+    },
+    {
+      "epoch": 0.003720143732826041,
+      "grad_norm": 0.47666624188423157,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.595,
+      "step": 22
+    },
+    {
+      "epoch": 0.0038892411752272245,
+      "grad_norm": 0.44477328658103943,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.6747,
+      "step": 23
+    },
+    {
+      "epoch": 0.004058338617628408,
+      "grad_norm": 0.40303224325180054,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.4601,
+      "step": 24
+    },
+    {
+      "epoch": 0.004227436060029592,
+      "grad_norm": 0.5073460936546326,
+      "learning_rate": 0.0,
+      "loss": 0.6363,
+      "step": 25
+    },
+    {
+      "epoch": 0.004227436060029592,
+      "eval_loss": 0.6571388244628906,
+      "eval_runtime": 292.1469,
+      "eval_samples_per_second": 8.523,
+      "eval_steps_per_second": 4.262,
+      "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": 351700747026432.0,
+  "total_flos": 440738910830592.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null