Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5540e18c403a3dacc0370c77e7493c437c73e0497fb22e7fdde5b6afc245d37
+oid sha256:ea5f72cd800cb34fe37fce825e69fa6b5e90ac70a3d721a9d867a3246db2a12d
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:793d813e961699d901d527779bc552e512d2594db2372328a95363d52bdecaad
+oid sha256:6dafcfbc990e3c27ce484a3d8b95ea22f59d2a844cf2d19d8c50914f7e8c7b42
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f776b0dddb15b2dfca0c421779d026ff90ca078d632c0ede9e661a4f27ff76a
+oid sha256:48f78407387bc0d5cc74e42fdea4df89f1f8f7190e2048b58df83ab6c6fa0d19
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efceaa5c248a4d80b63fee15b42b7a10a2394777ecd3ca622c0d4a7cf33eef18
+oid sha256:697eb5c311706d748c20f07b0521bb9d1f71aee638eb745112aecf80a82e51da
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0977070331573486,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.004722327162825841,
+  "best_metric": 1.0563247203826904,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.009444654325651681,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 17.4,
       "eval_steps_per_second": 4.352,
       "step": 50
+    },
+    {
+      "epoch": 0.0056667925953910086,
+      "grad_norm": 0.8779242634773254,
+      "learning_rate": 0.00021773448147832086,
+      "loss": 1.0668,
+      "step": 60
+    },
+    {
+      "epoch": 0.0066112580279561765,
+      "grad_norm": 1.3890700340270996,
+      "learning_rate": 0.0002169392194928312,
+      "loss": 1.0106,
+      "step": 70
+    },
+    {
+      "epoch": 0.007555723460521345,
+      "grad_norm": 0.963046669960022,
+      "learning_rate": 0.00021561808847998484,
+      "loss": 1.0095,
+      "step": 80
+    },
+    {
+      "epoch": 0.008500188893086513,
+      "grad_norm": 1.1754647493362427,
+      "learning_rate": 0.00021377752485727676,
+      "loss": 0.9492,
+      "step": 90
+    },
+    {
+      "epoch": 0.009444654325651681,
+      "grad_norm": 1.9377000331878662,
+      "learning_rate": 0.00021142649566566402,
+      "loss": 0.7452,
+      "step": 100
+    },
+    {
+      "epoch": 0.009444654325651681,
+      "eval_loss": 1.0563247203826904,
+      "eval_runtime": 256.3063,
+      "eval_samples_per_second": 17.393,
+      "eval_steps_per_second": 4.35,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -86,7 +129,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8495158001664000.0,
+  "total_flos": 1.6906205528064e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null