Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f38ad1926844bd4e8778799df4a3fd38c29501aca568a0d60c45d865ace7f591
+oid sha256:20657ea7452f5613180176755efa2e5c0eca8444e7ab7e1b351f7b6e220c4d64
 size 95402480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04d54c6e8e1b9a7e49d99b02d001e123f217111e53c5387447a11c027fa0e097
+oid sha256:2293821baa8e0263dbd0822f786ff53b3c336d367214f674b12d7bbe108b33bd
 size 191012170

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e16bdf370742716a02b73cdc1cc08bf8c26688d8e390eced9a1803f36ab354eb
+oid sha256:30706e59c4db224f838a07e4459e29e0b6a4cd0e7a75bdaa4c474c6f7ea6196a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2eb657255baf6b1420bbcfab19529abd45c6011f0c415bddb3c278a51f7f142
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.82761812210083,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0007728423208454895,
+  "best_metric": 1.8159558773040771,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0011592634812682343,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 7.905,
       "eval_steps_per_second": 3.953,
       "step": 20
+    },
+    {
+      "epoch": 0.0008114844368877639,
+      "grad_norm": 8.811689376831055,
+      "learning_rate": 2.8711035421746367e-05,
+      "loss": 13.6651,
+      "step": 21
+    },
+    {
+      "epoch": 0.0009274107850145874,
+      "grad_norm": 26.95303726196289,
+      "learning_rate": 1.3551568628929434e-05,
+      "loss": 13.2066,
+      "step": 24
+    },
+    {
+      "epoch": 0.0009660529010568618,
+      "eval_loss": 1.8177318572998047,
+      "eval_runtime": 1377.2324,
+      "eval_samples_per_second": 7.912,
+      "eval_steps_per_second": 3.956,
+      "step": 25
+    },
+    {
+      "epoch": 0.0010433371331414107,
+      "grad_norm": 6.742008686065674,
+      "learning_rate": 3.511175705587433e-06,
+      "loss": 12.3683,
+      "step": 27
+    },
+    {
+      "epoch": 0.0011592634812682343,
+      "grad_norm": 6.709179878234863,
+      "learning_rate": 0.0,
+      "loss": 12.5037,
+      "step": 30
+    },
+    {
+      "epoch": 0.0011592634812682343,
+      "eval_loss": 1.8159558773040771,
+      "eval_runtime": 1378.8448,
+      "eval_samples_per_second": 7.903,
+      "eval_steps_per_second": 3.952,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5779302566068224.0,
+  "total_flos": 8633279141904384.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null