Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c54318a129d2bfb968c087f752e4d95cd3f0004b30968cb875a2778e5f0e481
+oid sha256:741037faa293e3aa4a6ebc59e6eb82f8cfdfbd835422fee2eef2b885261c2068
 size 1006723888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da7f87caec4f3842915b670c494e6a86b348ca61fb4b1991d2150635d4a50106
+oid sha256:0c9438c304665342120801741a06ff28dd1d8b6f58198ce62882db40c2e4589f
 size 511971028

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed5fbb022247df380404f1877112e8f3f6949dbaaf85150be2b231eb6b73472f
+oid sha256:366c57510a86bf35b1e3b13316f699f46eaf375c8282646c54f791554ba45dea
 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": 0.5830835103988647,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.010398253093480296,
+  "best_metric": 0.553749680519104,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.020796506186960592,
   "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": 6.265,
       "eval_steps_per_second": 1.569,
       "step": 50
+    },
+    {
+      "epoch": 0.012477903712176355,
+      "grad_norm": 1.4801353216171265,
+      "learning_rate": 0.00021773448147832086,
+      "loss": 0.5768,
+      "step": 60
+    },
+    {
+      "epoch": 0.014557554330872413,
+      "grad_norm": 1.2638306617736816,
+      "learning_rate": 0.0002169392194928312,
+      "loss": 0.585,
+      "step": 70
+    },
+    {
+      "epoch": 0.01663720494956847,
+      "grad_norm": 1.3111450672149658,
+      "learning_rate": 0.00021561808847998484,
+      "loss": 0.6144,
+      "step": 80
+    },
+    {
+      "epoch": 0.01871685556826453,
+      "grad_norm": 1.4548810720443726,
+      "learning_rate": 0.00021377752485727676,
+      "loss": 0.5459,
+      "step": 90
+    },
+    {
+      "epoch": 0.020796506186960592,
+      "grad_norm": 1.1708745956420898,
+      "learning_rate": 0.00021142649566566402,
+      "loss": 0.6452,
+      "step": 100
+    },
+    {
+      "epoch": 0.020796506186960592,
+      "eval_loss": 0.553749680519104,
+      "eval_runtime": 80.7517,
+      "eval_samples_per_second": 6.279,
+      "eval_steps_per_second": 1.573,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -86,7 +129,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6934243288547328.0,
+  "total_flos": 1.3601784912150528e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null