Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:024749c29807a6ddc8205354d76089346433baedfe15b0df3a6165b860e8fe20
+oid sha256:23b716fb6ed2faa4d75a719be94a9fa9eb4ab737d9a4fcb5a5a93c5f21b569ff
 size 101752088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed5680303179ef548a4fec584dbba5c400e42de795204913987c94a28f8a667d
+oid sha256:38a8cb5082ff546cdb94c38713491e6840a8a262859da2bd5d58449625d844d8
 size 203622650

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:452fe74d51cca21123d51f284e0794a19387c119f848f609cb1bce5c061e3ef9
+oid sha256:a9b34add5ab0f68716c96806d540c00b03453de42a09c62ec53261dcc22d0d5c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.117767095565796,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.000830685523228044,
+  "best_metric": 1.903814435005188,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.001661371046456088,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 6.582,
       "eval_steps_per_second": 3.291,
       "step": 10
+    },
+    {
+      "epoch": 0.0009968226278736527,
+      "grad_norm": 0.27616485953330994,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 1.948,
+      "step": 12
+    },
+    {
+      "epoch": 0.0012460282848420659,
+      "grad_norm": 0.33960211277008057,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.8767,
+      "step": 15
+    },
+    {
+      "epoch": 0.0012460282848420659,
+      "eval_loss": 1.9999240636825562,
+      "eval_runtime": 769.1009,
+      "eval_samples_per_second": 6.591,
+      "eval_steps_per_second": 3.296,
+      "step": 15
+    },
+    {
+      "epoch": 0.001495233941810479,
+      "grad_norm": 0.49282512068748474,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.8134,
+      "step": 18
+    },
+    {
+      "epoch": 0.001661371046456088,
+      "eval_loss": 1.903814435005188,
+      "eval_runtime": 768.6889,
+      "eval_samples_per_second": 6.594,
+      "eval_steps_per_second": 3.298,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1810980604477440.0,
+  "total_flos": 3868913109565440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null