Training in progress, step 334, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7271b7abd71ff28a6d8862329ed25f52ef9bdaed0cd5f9426db9af7d154d0162
+oid sha256:a40893551892869cef6185900dc5cd060ec50c15a4dedd57c0148d6c49941d00
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c97053614ad9d594d3c931b703e869bd2ed545d776abf4c92958c8accb20b2d
+oid sha256:2f47766cd7c29a3133b6ec6a8c13f2d4751a2d59c70bb6070522812124244ec3
 size 41460084

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdf57361bea28743679736bace185586f54b838c0b6e89f824be140ba835deb8
+oid sha256:23baeff9d8f6e26f2714adedc68547feeee95d2a00fc7ab711e496286b75c485
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c14f228dcfe997eb31918193f198918e61dc44a4118e1ce6d0f02c3f7f0fb85b
+oid sha256:3decfd55b176ddf4d3636844920f3f2a82e97670ba9e40977f0230eaf3d1c0f8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.010375738143921,
   "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 2.696629213483146,
+  "epoch": 3.002247191011236,
   "eval_steps": 100,
-  "global_step": 300,
+  "global_step": 334,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -249,6 +249,27 @@
       "eval_samples_per_second": 13.432,
       "eval_steps_per_second": 3.376,
       "step": 300
+    },
+    {
+      "epoch": 2.7865168539325844,
+      "grad_norm": 0.8065077066421509,
+      "learning_rate": 2.6955129420176196e-06,
+      "loss": 0.7093,
+      "step": 310
+    },
+    {
+      "epoch": 2.8764044943820224,
+      "grad_norm": 0.8511288166046143,
+      "learning_rate": 9.199596635154683e-07,
+      "loss": 0.8656,
+      "step": 320
+    },
+    {
+      "epoch": 2.966292134831461,
+      "grad_norm": 0.7981316447257996,
+      "learning_rate": 7.520474957699586e-08,
+      "loss": 0.6292,
+      "step": 330
     }
   ],
   "logging_steps": 10,
@@ -272,12 +293,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.312152896050299e+17,
+  "total_flos": 4.8005266479670886e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null