Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aeadd452fcb4d211b4578fc9c096270755a1340d533c5a4798145c5eae3d9fbb
+oid sha256:309916b1006f2d69f89b39ff846e74b101329323107dc2f35283754a6abe6c34
 size 72396376

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b26df5634a4b1f9f8651c6c2b8d9176684eff4a4e43e0bcf729c553d5b6548f
+oid sha256:2ae69ad05cb0b6cc75b7cfa5fb775bfd1adb953043a1ba6eed53f697b432e592
 size 37134420

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:670a21c48e7af636310774afe9303e33287af3995a6a4ab6ff30a820851c6f79
+oid sha256:6364bb22c9c54e3924593b01d82be5f132212590d147a8728fef20641b8e19f2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:596785cc644037bdf9b1374ba5340995054de5f4bde563878d8bc4f03a7aa10e
+oid sha256:d10d0fa96665f6b4af4824faec3d1d9f4e8b4343723a14d86cab932da6ce3225
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.267966389656067,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.0979431929480901,
+  "best_metric": 1.2385743856430054,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.1305909239307868,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 60.978,
       "eval_steps_per_second": 15.25,
       "step": 150
+    },
+    {
+      "epoch": 0.10447273914462944,
+      "grad_norm": 0.07010999321937561,
+      "learning_rate": 0.0001697631521134985,
+      "loss": 1.1417,
+      "step": 160
+    },
+    {
+      "epoch": 0.1110022853411688,
+      "grad_norm": 0.10216495394706726,
+      "learning_rate": 0.00016585113790650388,
+      "loss": 1.238,
+      "step": 170
+    },
+    {
+      "epoch": 0.11753183153770813,
+      "grad_norm": 0.12675678730010986,
+      "learning_rate": 0.0001617524614946192,
+      "loss": 1.3154,
+      "step": 180
+    },
+    {
+      "epoch": 0.12406137773424747,
+      "grad_norm": 0.31328052282333374,
+      "learning_rate": 0.0001574787410214407,
+      "loss": 1.3155,
+      "step": 190
+    },
+    {
+      "epoch": 0.1305909239307868,
+      "grad_norm": 1.081733226776123,
+      "learning_rate": 0.00015304209081197425,
+      "loss": 1.3807,
+      "step": 200
+    },
+    {
+      "epoch": 0.1305909239307868,
+      "eval_loss": 1.2385743856430054,
+      "eval_runtime": 42.1021,
+      "eval_samples_per_second": 61.256,
+      "eval_steps_per_second": 15.32,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -172,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.4377913105186816e+16,
+  "total_flos": 3.250388414024909e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null