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:f63287f71741657e67743f272886f1c595bf92a1d03189984552a9c27f95122d
+oid sha256:46d14c2cc0fb69e0f1adaf7af0ebde47058a813bd33bfe343fe74dab06753a50
 size 56660888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccdeb5f216b9b73c741deb16a7ef7fb674446ad7bbef841aa8cd7426d1edd8cf
+oid sha256:6b5912ac9f99dcf9959fb43a75fc3671cb42ab6aafaf2c88c5fd792c1303fec4
 size 113488058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:732f4baeaa4944417ef090e2b340bbb18a6c6e47bd4124ccec37cdce05e59c23
+oid sha256:3fba821f2fde64b69710fa0a3cba3a5db27b6eefb4c670e83c0d046488ff4ef1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.6288348436355591,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.006169031462060457,
+  "best_metric": 0.607528030872345,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.009253547193090685,
   "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": 19.435,
       "eval_steps_per_second": 9.725,
       "step": 20
+    },
+    {
+      "epoch": 0.006477483035163479,
+      "grad_norm": 0.27787524461746216,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 0.4794,
+      "step": 21
+    },
+    {
+      "epoch": 0.007402837754472548,
+      "grad_norm": 0.3034648597240448,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 0.5732,
+      "step": 24
+    },
+    {
+      "epoch": 0.0077112893275755705,
+      "eval_loss": 0.6111285090446472,
+      "eval_runtime": 70.2828,
+      "eval_samples_per_second": 19.422,
+      "eval_steps_per_second": 9.718,
+      "step": 25
+    },
+    {
+      "epoch": 0.008328192473781616,
+      "grad_norm": 0.2949819564819336,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 0.5781,
+      "step": 27
+    },
+    {
+      "epoch": 0.009253547193090685,
+      "grad_norm": 0.3319774270057678,
+      "learning_rate": 0.0,
+      "loss": 0.6198,
+      "step": 30
+    },
+    {
+      "epoch": 0.009253547193090685,
+      "eval_loss": 0.607528030872345,
+      "eval_runtime": 70.2908,
+      "eval_samples_per_second": 19.419,
+      "eval_steps_per_second": 9.717,
+      "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": 1321366494117888.0,
+  "total_flos": 1973893157879808.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null