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:a9e738334be2d5a76569b083f10ad7f050fba5a9c183508c665571b4beaf22b3
+oid sha256:b07840c8e0a1ecad3141e69b3a336225632508ff4e073cf6313660c9a0dfeb97
 size 25192592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d98064f0b09df1f9fe47a3e80667a88a117f984ccb0b52e1e7f47c0ea81e40b
+oid sha256:36c91d6c612512abecda47c7bd90e1df5ba211d128060cf724ae4e58144f5547
 size 50493050

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6030e2eec03ac3bd8af1f9fd206c9a2d7d37bd3a2bcfc1cfa963fa848c4476f5
+oid sha256:5276250df0c5e47e366505e9e84da6df708e00fffaaf00909bfa58d1f37aa351
 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": 2.9805502891540527,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.09512485136741974,
+  "best_metric": 2.9646615982055664,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.1426872770511296,
   "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": 85.715,
       "eval_steps_per_second": 21.67,
       "step": 20
+    },
+    {
+      "epoch": 0.09988109393579073,
+      "grad_norm": 24.07295036315918,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 11.5067,
+      "step": 21
+    },
+    {
+      "epoch": 0.11414982164090369,
+      "grad_norm": 23.57462501525879,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 11.9897,
+      "step": 24
+    },
+    {
+      "epoch": 0.11890606420927467,
+      "eval_loss": 2.96132493019104,
+      "eval_runtime": 1.6292,
+      "eval_samples_per_second": 109.253,
+      "eval_steps_per_second": 27.62,
+      "step": 25
+    },
+    {
+      "epoch": 0.12841854934601665,
+      "grad_norm": 25.987632751464844,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 11.3795,
+      "step": 27
+    },
+    {
+      "epoch": 0.1426872770511296,
+      "grad_norm": 27.918235778808594,
+      "learning_rate": 0.0,
+      "loss": 12.4756,
+      "step": 30
+    },
+    {
+      "epoch": 0.1426872770511296,
+      "eval_loss": 2.9646615982055664,
+      "eval_runtime": 1.6445,
+      "eval_samples_per_second": 108.241,
+      "eval_steps_per_second": 27.364,
+      "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": 752264109096960.0,
+  "total_flos": 1106270748672000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null