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:db884f5e30667d187b470f003b5f0fd8ac2e1a74978b38543ec98c182e75c032
+oid sha256:9f6b6e88fab7e73b1927556deacf3e8e302b6d8fc88359fed3bf3cdc73313672
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fd3906fd9fd496e5d39599828d63efb7e8c52d9540db5255d2aff48497d3f5c
+oid sha256:ee44534c6f348481b700c9bcceb4760ae21d4beb9ee10d542e1f8420e4c44fa9
 size 70667778

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75607a89082519b75f8d05cbeba7e0ae5e5a774af3ba1d7d0d58f41fb6752647
+oid sha256:83361e520816e05e7f16754438edf4c9a8891eb40fbd7325ea6aeff6f814573e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.4446890354156494,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0007124156232746184,
+  "best_metric": 2.165391683578491,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0014248312465492369,
   "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": 47.807,
       "eval_steps_per_second": 23.908,
       "step": 10
+    },
+    {
+      "epoch": 0.0008548987479295421,
+      "grad_norm": 4.437066078186035,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 2.4558,
+      "step": 12
+    },
+    {
+      "epoch": 0.0010686234349119275,
+      "grad_norm": 6.945307731628418,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 2.3293,
+      "step": 15
+    },
+    {
+      "epoch": 0.0010686234349119275,
+      "eval_loss": 2.2446939945220947,
+      "eval_runtime": 124.6029,
+      "eval_samples_per_second": 47.439,
+      "eval_steps_per_second": 23.723,
+      "step": 15
+    },
+    {
+      "epoch": 0.0012823481218943132,
+      "grad_norm": 3.3825199604034424,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.0153,
+      "step": 18
+    },
+    {
+      "epoch": 0.0014248312465492369,
+      "eval_loss": 2.165391683578491,
+      "eval_runtime": 124.0293,
+      "eval_samples_per_second": 47.658,
+      "eval_steps_per_second": 23.833,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 180238575206400.0,
+  "total_flos": 360477150412800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null