Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:109f85a8a6aae19a8283d64bbbd499c660468d93c34c505eaeed2472374c6c79
+oid sha256:fa05af74293cfb744e86cf4607028a82ac444f801992d92e72c6542d20646e9c
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:859739c467e69200ac256415c2558cbaaa82138cbfaeb2bb61fc6744dab58596
+oid sha256:6b7bb319a8f172d5150ec7b4462bf5bb73f915693a9246e377cb0ab08bc72c1b
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d21aa072b3bf17a29e473aa0967bf113e0eabd6990ff76f63b1925aca7670d7
+oid sha256:f6ab27a84af36622f16b61fed83a7edd90d0fa1feaadbc6fce86db6dc14ec89f
 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": 1.959831714630127,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.08629989212513485,
+  "best_metric": 1.8901664018630981,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.12944983818770225,
   "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": 10.267,
       "eval_steps_per_second": 2.58,
       "step": 20
+    },
+    {
+      "epoch": 0.09061488673139159,
+      "grad_norm": 3.3498525619506836,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 7.7349,
+      "step": 21
+    },
+    {
+      "epoch": 0.10355987055016182,
+      "grad_norm": 3.1760308742523193,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 7.4737,
+      "step": 24
+    },
+    {
+      "epoch": 0.10787486515641856,
+      "eval_loss": 1.8999488353729248,
+      "eval_runtime": 18.9426,
+      "eval_samples_per_second": 10.294,
+      "eval_steps_per_second": 2.587,
+      "step": 25
+    },
+    {
+      "epoch": 0.11650485436893204,
+      "grad_norm": 4.965217590332031,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 7.5005,
+      "step": 27
+    },
+    {
+      "epoch": 0.12944983818770225,
+      "grad_norm": 3.8475265502929688,
+      "learning_rate": 0.0,
+      "loss": 7.7703,
+      "step": 30
+    },
+    {
+      "epoch": 0.12944983818770225,
+      "eval_loss": 1.8901664018630981,
+      "eval_runtime": 18.9937,
+      "eval_samples_per_second": 10.267,
+      "eval_steps_per_second": 2.58,
+      "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": 7368366033469440.0,
+  "total_flos": 1.105254905020416e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null