Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5945f06c3216ae06581911ec7cec068649a020e45af1930ec95e0cbd6be00e9f
+oid sha256:7018023d4f874733dc4e83d73e9e6807ae3490a92bf4fb26e7194a17da409eab
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fe03004dbc39f8b110a600cb4ddb64125e8e668b7553d6cf9c11c5d3ceb10ad
+oid sha256:0e9a45078a17c67c5a8cd8072adb58b2af97c889e1ba3c0c09b10a5febf110da
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4b82d94a3f3ba4658ccb6aa5c8b6ba7ae6394ee1ce2647f24e42e072d6200c3
+oid sha256:f58b98283f0cf134b4005d9b921adb02a846a23631404be12129392a65cfe4e3
 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": 0.37839406728744507,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.03885381253035454,
+  "best_metric": 0.37054625153541565,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.04856726566294318,
   "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": 1.28,
       "eval_steps_per_second": 0.643,
       "step": 20
+    },
+    {
+      "epoch": 0.04079650315687227,
+      "grad_norm": 1.6893807649612427,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.9269,
+      "step": 21
+    },
+    {
+      "epoch": 0.042739193783389993,
+      "grad_norm": 3.412912607192993,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.5264,
+      "step": 22
+    },
+    {
+      "epoch": 0.044681884409907724,
+      "grad_norm": 1.6971460580825806,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 1.1537,
+      "step": 23
+    },
+    {
+      "epoch": 0.04662457503642545,
+      "grad_norm": 1.9251805543899536,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 1.5245,
+      "step": 24
+    },
+    {
+      "epoch": 0.04856726566294318,
+      "grad_norm": 1.8850699663162231,
+      "learning_rate": 0.0,
+      "loss": 1.1356,
+      "step": 25
+    },
+    {
+      "epoch": 0.04856726566294318,
+      "eval_loss": 0.37054625153541565,
+      "eval_runtime": 171.6641,
+      "eval_samples_per_second": 1.264,
+      "eval_steps_per_second": 0.635,
+      "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": 6332448610713600.0,
+  "total_flos": 7915560763392000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null