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:a72ecec4a6d176c31fda7909e4eef65093c71720b76d80d1dbb355647c9b503d
+oid sha256:960ded5ddbf9ee05931cb064c83c8f0bdb8340fcf94b7385de088c43fb31ae10
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:724f08819dfcbc2b4d6a46b7ce70507c070707173550b64a222271f7f5acdf75
+oid sha256:28041e07db837581654f8541c351a9e482fbb9c0e0e6e4977070ab4f5e4d49ff
 size 90365754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:892b1fe3dc1e64ec9b3f3b298cf52383c0b2865f25751bdc82a7d035aa64dc87
+oid sha256:87ec051d7ad1062f67995559b3d1cf810ad19a80b91d357353455bea0b04baa7
 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": 3.1064229011535645,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.003290826820238585,
+  "best_metric": 3.0958034992218018,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0049362402303578775,
   "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": 62.691,
       "eval_steps_per_second": 15.679,
       "step": 20
+    },
+    {
+      "epoch": 0.003455368161250514,
+      "grad_norm": 0.8514401316642761,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 2.9635,
+      "step": 21
+    },
+    {
+      "epoch": 0.003948992184286302,
+      "grad_norm": 0.9742792844772339,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 3.0894,
+      "step": 24
+    },
+    {
+      "epoch": 0.004113533525298231,
+      "eval_loss": 3.0976011753082275,
+      "eval_runtime": 81.6108,
+      "eval_samples_per_second": 62.712,
+      "eval_steps_per_second": 15.684,
+      "step": 25
+    },
+    {
+      "epoch": 0.00444261620732209,
+      "grad_norm": 0.9490313529968262,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 3.116,
+      "step": 27
+    },
+    {
+      "epoch": 0.0049362402303578775,
+      "grad_norm": 1.042704701423645,
+      "learning_rate": 0.0,
+      "loss": 3.0409,
+      "step": 30
+    },
+    {
+      "epoch": 0.0049362402303578775,
+      "eval_loss": 3.0958034992218018,
+      "eval_runtime": 81.7908,
+      "eval_samples_per_second": 62.574,
+      "eval_steps_per_second": 15.65,
+      "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": 1983831267606528.0,
+  "total_flos": 2951553837170688.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null