Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:458d26ce88ffcea2dcec3c9743c009547c1ec332eda63bc0ca4107c20bbe3147
+oid sha256:cea4aa77a9536a6cfc0523f203127e1ff400e88fa2f7b266916eed56e56ae8cf
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6e49c320959beba44505a80293183cddc85c46c98f03c75588ff47e2dd245cc
+oid sha256:763efe88e451051d1b2e493e7981e07d2b3c80ec5f61979310eab2eaf6c630ec
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7332cedcc7b3b36b7974e070bd9fa7171e6a96e191919b27b6014d872048e1e
+oid sha256:90c16045da30470604a19dd4a24b5233aab3ae5fc2ba8d2bb12f06c16d1d934c
 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": 0.6494202017784119,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.016635475150758992,
+  "best_metric": 0.6313887238502502,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.020794343938448742,
   "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": 3.299,
       "eval_steps_per_second": 1.653,
       "step": 20
+    },
+    {
+      "epoch": 0.017467248908296942,
+      "grad_norm": 1.283953070640564,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 2.6506,
+      "step": 21
+    },
+    {
+      "epoch": 0.018299022665834892,
+      "grad_norm": 1.1710776090621948,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 2.7642,
+      "step": 22
+    },
+    {
+      "epoch": 0.019130796423372842,
+      "grad_norm": 1.0391024351119995,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 2.4619,
+      "step": 23
+    },
+    {
+      "epoch": 0.019962570180910792,
+      "grad_norm": 1.1879003047943115,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 2.5633,
+      "step": 24
+    },
+    {
+      "epoch": 0.020794343938448742,
+      "grad_norm": 1.1049716472625732,
+      "learning_rate": 0.0,
+      "loss": 2.5356,
+      "step": 25
+    },
+    {
+      "epoch": 0.020794343938448742,
+      "eval_loss": 0.6313887238502502,
+      "eval_runtime": 153.4015,
+      "eval_samples_per_second": 3.305,
+      "eval_steps_per_second": 1.656,
+      "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": 1.26648972214272e+16,
+  "total_flos": 1.5831121526784e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null