Training in progress, step 165, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:850811860fd40c90e373647c1216625830bbf3a94ea1f94bfe8790fd933746af
+oid sha256:11e3eaf1df4449a9c510a7e6b7731182db606cc2f8bef792e3d77931d8f7c6f2
 size 295488936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8803034221e4f58d09a7eb033fc1030d7eb56aac297027c0d799af78f305b0d3
+oid sha256:9df5e9b4404194ec2151bd6614d461226499e0f22c3fe1adf28819206d072430
 size 150486964

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e395ea3c23033b63c4fc0880c16c17d8577a55e9a7b288c415cc3af79ac0c52c
+oid sha256:503bba02ead32ef1bbc944334a02d0335677cc620e54a4b6936c6a2adfbfacb2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac6117964e488fc602d1c2599fbb9c2f355dd5f77ec215fe61d2fb5c75627620
+oid sha256:9a9687a1b8f656eb1ba7c54db2096d9fb4dcefbc465460811f45afd99ce73ed4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.1915530115365982,
   "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.9090909090909091,
+  "epoch": 1.0,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 165,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1089,6 +1089,111 @@
       "eval_samples_per_second": 22.987,
       "eval_steps_per_second": 5.788,
       "step": 150
+    },
+    {
+      "epoch": 0.9151515151515152,
+      "grad_norm": 0.6598231792449951,
+      "learning_rate": 1.999477085883711e-06,
+      "loss": 0.1742,
+      "step": 151
+    },
+    {
+      "epoch": 0.9212121212121213,
+      "grad_norm": 1.0412766933441162,
+      "learning_rate": 1.725635200065323e-06,
+      "loss": 0.2975,
+      "step": 152
+    },
+    {
+      "epoch": 0.9272727272727272,
+      "grad_norm": 0.9595324397087097,
+      "learning_rate": 1.471624014469919e-06,
+      "loss": 0.2484,
+      "step": 153
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 0.7045427560806274,
+      "learning_rate": 1.2375478747413017e-06,
+      "loss": 0.1995,
+      "step": 154
+    },
+    {
+      "epoch": 0.9393939393939394,
+      "grad_norm": 0.6390289664268494,
+      "learning_rate": 1.0235029373752758e-06,
+      "loss": 0.2269,
+      "step": 155
+    },
+    {
+      "epoch": 0.9454545454545454,
+      "grad_norm": 0.6821112036705017,
+      "learning_rate": 8.295771302193722e-07,
+      "loss": 0.2029,
+      "step": 156
+    },
+    {
+      "epoch": 0.9515151515151515,
+      "grad_norm": 0.7083057761192322,
+      "learning_rate": 6.558501163527964e-07,
+      "loss": 0.2191,
+      "step": 157
+    },
+    {
+      "epoch": 0.9575757575757575,
+      "grad_norm": 0.8139418363571167,
+      "learning_rate": 5.023932613615445e-07,
+      "loss": 0.3047,
+      "step": 158
+    },
+    {
+      "epoch": 0.9636363636363636,
+      "grad_norm": 0.9935289025306702,
+      "learning_rate": 3.692696040220267e-07,
+      "loss": 0.211,
+      "step": 159
+    },
+    {
+      "epoch": 0.9696969696969697,
+      "grad_norm": 0.9533095359802246,
+      "learning_rate": 2.5653383040524227e-07,
+      "loss": 0.2982,
+      "step": 160
+    },
+    {
+      "epoch": 0.9757575757575757,
+      "grad_norm": 0.7618079781532288,
+      "learning_rate": 1.6423225141223852e-07,
+      "loss": 0.2872,
+      "step": 161
+    },
+    {
+      "epoch": 0.9818181818181818,
+      "grad_norm": 0.5216308832168579,
+      "learning_rate": 9.240278374995637e-08,
+      "loss": 0.1049,
+      "step": 162
+    },
+    {
+      "epoch": 0.9878787878787879,
+      "grad_norm": 0.6591054201126099,
+      "learning_rate": 4.107493435538401e-08,
+      "loss": 0.2146,
+      "step": 163
+    },
+    {
+      "epoch": 0.9939393939393939,
+      "grad_norm": 1.1252936124801636,
+      "learning_rate": 1.0269788274358538e-08,
+      "loss": 0.4417,
+      "step": 164
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.5213817954063416,
+      "learning_rate": 0.0,
+      "loss": 0.1846,
+      "step": 165
     }
   ],
   "logging_steps": 1,
@@ -1112,12 +1217,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.0821709602816e+16,
+  "total_flos": 4.487836699459584e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null