Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:226022adf81de62412ea2af1f2ef197f574f532301eb290134740b25623dca19
+oid sha256:055ed0cddac36e8e465d63850f5d7489b584606d80bd09cd1cf692310f1af89e
 size 26008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9f2b8f4df48545fa8698d0107fe826da2c093f73d79e387b480bcfe95aaa3d4
+oid sha256:9a99f93851fa984ed3c19a534e78600b997527e031122d39de51128432b54ca7
 size 68874

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dace3653fe0e7343aeff78961da71266f92cc83f6bc7a8561cfa91c303e54dba
+oid sha256:5c4b2018b52c1fc9332cfebf7c5c719d3cfb18d97200dec86a051dd64d3a14d3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.931585311889648,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.008506113769271665,
+  "best_metric": 11.931512832641602,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.012759170653907496,
   "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": 68.656,
       "eval_steps_per_second": 34.328,
       "step": 20
+    },
+    {
+      "epoch": 0.008931419457735247,
+      "grad_norm": 0.009931663051247597,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 11.9307,
+      "step": 21
+    },
+    {
+      "epoch": 0.010207336523125997,
+      "grad_norm": 0.01326278317719698,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 11.932,
+      "step": 24
+    },
+    {
+      "epoch": 0.01063264221158958,
+      "eval_loss": 11.931526184082031,
+      "eval_runtime": 13.586,
+      "eval_samples_per_second": 72.869,
+      "eval_steps_per_second": 36.434,
+      "step": 25
+    },
+    {
+      "epoch": 0.011483253588516746,
+      "grad_norm": 0.009728243574500084,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 11.9328,
+      "step": 27
+    },
+    {
+      "epoch": 0.012759170653907496,
+      "grad_norm": 0.01359177939593792,
+      "learning_rate": 0.0,
+      "loss": 11.9329,
+      "step": 30
+    },
+    {
+      "epoch": 0.012759170653907496,
+      "eval_loss": 11.931512832641602,
+      "eval_runtime": 14.4102,
+      "eval_samples_per_second": 68.701,
+      "eval_steps_per_second": 34.351,
+      "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": 7588380672.0,
+  "total_flos": 11335729152.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null