Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96b1421221ff432c8931b969f510ef8b852ee27cf173ba78527977251278507e
+oid sha256:47e06b60a65da1d36c4c402134993afe05cf9c5aeb1bc02124e9f013bc64f8d2
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb4416d1ffc718613fc6612db5fdde5b82a5dca06f6c44edb7ebc4cd5201aa29
+oid sha256:e90a9145d00905510fe99bc62b452dfa57105bccce84adc5dac5c30efd977b97
 size 164464564

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c8addbca335a36dfc0be2fb883b05344c05c475f00b9a438210b73abda110f4
+oid sha256:180f6a34cec4da22c12f953563bdcc58531cb08c4ee973bc4513347222db9656
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5220d0af0ff98b2d6e04334f1c29842da7230747bf3383cf1f883a4d2eb6d4f2
+oid sha256:90c455b2a7603e9003556345290fd0185bd6c6017de2b595e3f9c6216f721e5e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.582314670085907,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.11904761904761904,
+  "best_metric": 0.5373075008392334,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.15873015873015872,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 13.698,
       "eval_steps_per_second": 3.442,
       "step": 150
+    },
+    {
+      "epoch": 0.12698412698412698,
+      "grad_norm": 9.03739070892334,
+      "learning_rate": 2.2644444444444443e-06,
+      "loss": 0.4166,
+      "step": 160
+    },
+    {
+      "epoch": 0.1349206349206349,
+      "grad_norm": 5.134159088134766,
+      "learning_rate": 1.6983333333333333e-06,
+      "loss": 0.3406,
+      "step": 170
+    },
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": 7.450616836547852,
+      "learning_rate": 1.1322222222222221e-06,
+      "loss": 0.4627,
+      "step": 180
+    },
+    {
+      "epoch": 0.15079365079365079,
+      "grad_norm": 12.882534980773926,
+      "learning_rate": 5.661111111111111e-07,
+      "loss": 0.5223,
+      "step": 190
+    },
+    {
+      "epoch": 0.15873015873015872,
+      "grad_norm": 17.285032272338867,
+      "learning_rate": 0.0,
+      "loss": 0.6207,
+      "step": 200
+    },
+    {
+      "epoch": 0.15873015873015872,
+      "eval_loss": 0.5373075008392334,
+      "eval_runtime": 29.0493,
+      "eval_samples_per_second": 13.701,
+      "eval_steps_per_second": 3.442,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -167,12 +210,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.95441574248448e+16,
+  "total_flos": 5.27255432331264e+16,
   "train_batch_size": 6,
   "trial_name": null,
   "trial_params": null