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:c5db0ac9d795161c042943df64c8ff0d1a4526afcb454cc6d733aeee160f22c4
+oid sha256:5c9e2d6ca2cfdea6a28a84d60973c98b945cdbec3ac091793d2366b4b8681255
 size 63592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28874e5bf5f6b6e5a23c4bca65638f98e12afcea3c6461d8d0fda714e24c4236
+oid sha256:03c44349348d24bf95d09ef7d1035086157349a66574a920e8c2be4cd7fcd587
 size 136814

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:572c5653b97399d6dc550389d4e48df5479adab7c80147f357d4d04c0f7252da
+oid sha256:b6c308f72e634c6d4709c1a706d150b00f5df05813f2ee8017457cbf49afc5af
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.079708099365234,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.000161809679455025,
+  "best_metric": 11.06680965423584,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.00032361935891005,
   "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": 52.79,
       "eval_steps_per_second": 26.395,
       "step": 10
+    },
+    {
+      "epoch": 0.00019417161534603,
+      "grad_norm": 0.37414026260375977,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 11.0796,
+      "step": 12
+    },
+    {
+      "epoch": 0.0002427145191825375,
+      "grad_norm": 0.41052693128585815,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 11.0806,
+      "step": 15
+    },
+    {
+      "epoch": 0.0002427145191825375,
+      "eval_loss": 11.072711944580078,
+      "eval_runtime": 121.4738,
+      "eval_samples_per_second": 53.559,
+      "eval_steps_per_second": 26.779,
+      "step": 15
+    },
+    {
+      "epoch": 0.000291257423019045,
+      "grad_norm": 0.3889458477497101,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 11.0734,
+      "step": 18
+    },
+    {
+      "epoch": 0.00032361935891005,
+      "eval_loss": 11.06680965423584,
+      "eval_runtime": 122.2106,
+      "eval_samples_per_second": 53.236,
+      "eval_steps_per_second": 26.618,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4679270400.0,
+  "total_flos": 9358540800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null