Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d00159c9abc0a77d9455583187771c0b839c6427abbb2e0e32ef0365bf38e41
+oid sha256:88d0e56cbc99a95afb93c53aad1753874846f1b7714eefaaf63efb2bc0e6715d
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:954f91e465dcf1ae6c0d7a4de601f829a5e0f229e252791d86cabd6bc781730f
+oid sha256:6bcaded3b623c35cbe65325eacd4f12cf688444d9c8c0d515905be7f8792afb8
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22d574342ada71a12cc91e24303080433a832ed44983bf4aac463550d48c0c92
+oid sha256:28bb8cd36f407a81ad8a852c0cafc09272cd757fc0bb883a948f9d458d361cbc
 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": 0.5352662205696106,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0033819488480236735,
+  "best_metric": 0.5326106548309326,
+  "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": 6.103,
       "eval_steps_per_second": 3.051,
       "step": 20
+    },
+    {
+      "epoch": 0.0035510462904248573,
+      "grad_norm": 0.26431265473365784,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.5648,
+      "step": 21
+    },
+    {
+      "epoch": 0.003720143732826041,
+      "grad_norm": 0.25868359208106995,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.4454,
+      "step": 22
+    },
+    {
+      "epoch": 0.0038892411752272245,
+      "grad_norm": 0.2780039310455322,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.5067,
+      "step": 23
+    },
+    {
+      "epoch": 0.004058338617628408,
+      "grad_norm": 0.24686838686466217,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.5751,
+      "step": 24
+    },
+    {
+      "epoch": 0.004227436060029592,
+      "grad_norm": 0.229422926902771,
+      "learning_rate": 0.0,
+      "loss": 0.5064,
+      "step": 25
+    },
+    {
+      "epoch": 0.004227436060029592,
+      "eval_loss": 0.5326106548309326,
+      "eval_runtime": 408.4156,
+      "eval_samples_per_second": 6.097,
+      "eval_steps_per_second": 3.048,
+      "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": 5456256005308416.0,
+  "total_flos": 6718524185640960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null