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:acc957fa28c312944c57b944aca060253420a7a0f5733ccb42bb4c9142605d27
+oid sha256:2be2a23fbf35032ed2002495108970b35daa6857152d5324425aa24667ac952c
 size 15182728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de1ced7cfab97a72640abe1758f0830edc796229af8961978a441fc804e32971
+oid sha256:eebebf447a4c83f3d6af0afc51a966b489847e092d81f46cea4f2e89fb5c2508
 size 8075796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b92f2c4d40b75a1c427afcc3b9f446470aabb0e122237b7afe731531934f208
+oid sha256:1f20995103c299fea8f8f69c46bdc51fe8e0da6c299dc26d1f37190f8797826a
 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": 0.45222973823547363,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.001704049247023239,
+  "best_metric": 0.42355671525001526,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.0021300615587790486,
   "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": 10.163,
       "eval_steps_per_second": 5.081,
       "step": 20
+    },
+    {
+      "epoch": 0.001789251709374401,
+      "grad_norm": 3.6809463500976562,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.502,
+      "step": 21
+    },
+    {
+      "epoch": 0.0018744541717255628,
+      "grad_norm": 2.1427297592163086,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.347,
+      "step": 22
+    },
+    {
+      "epoch": 0.001959656634076725,
+      "grad_norm": 2.23321795463562,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.1978,
+      "step": 23
+    },
+    {
+      "epoch": 0.002044859096427887,
+      "grad_norm": 3.3327629566192627,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.4026,
+      "step": 24
+    },
+    {
+      "epoch": 0.0021300615587790486,
+      "grad_norm": 3.6156723499298096,
+      "learning_rate": 0.0,
+      "loss": 0.4378,
+      "step": 25
+    },
+    {
+      "epoch": 0.0021300615587790486,
+      "eval_loss": 0.42355671525001526,
+      "eval_runtime": 483.5763,
+      "eval_samples_per_second": 10.22,
+      "eval_steps_per_second": 5.11,
+      "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": 153447605207040.0,
+  "total_flos": 191809506508800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null