Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41243680d4927e23fefa9af71b223b2784c8f881e5c4ba4f248a0783bd61000b
+oid sha256:ac72a611dbdd40cd22d0efc47dae14039dc8e22679dcd347abd441651f53c848
 size 216151256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:638876fdd1f7778ee970d319e6473879efe1b7d3f37c6dc71032618cd6cc81bb
+oid sha256:e93706835554a2710f8dd181f3a732d95b49b56c01d06eed448c40f3a006f1a1
 size 432492970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edbfbdfbc1fa7f9bb4a6d97babb8df20ef6e2c315594d5cd53ea96685c74a2c9
+oid sha256:2e6d3d9d32f12a1efe3c64b65843add4181ba040cb939f02cd1d690662cff498
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d46ef0f8a7945706ef65ae5e8be31402361869b6b4c8ecb8ef0263696377404
+oid sha256:e2eb657255baf6b1420bbcfab19529abd45c6011f0c415bddb3c278a51f7f142
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.791510820388794,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0003226274781823168,
+  "best_metric": 2.6314613819122314,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0006452549563646336,
   "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": 5.057,
       "eval_steps_per_second": 2.529,
       "step": 10
+    },
+    {
+      "epoch": 0.00038715297381878015,
+      "grad_norm": 1.2754595279693604,
+      "learning_rate": 8.18711994874345e-05,
+      "loss": 2.8637,
+      "step": 12
+    },
+    {
+      "epoch": 0.0004839412172734752,
+      "grad_norm": 1.3381720781326294,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 2.6175,
+      "step": 15
+    },
+    {
+      "epoch": 0.0004839412172734752,
+      "eval_loss": 2.6785662174224854,
+      "eval_runtime": 2581.1799,
+      "eval_samples_per_second": 5.056,
+      "eval_steps_per_second": 2.528,
+      "step": 15
+    },
+    {
+      "epoch": 0.0005807294607281702,
+      "grad_norm": 1.039152979850769,
+      "learning_rate": 4.6860474023534335e-05,
+      "loss": 2.4836,
+      "step": 18
+    },
+    {
+      "epoch": 0.0006452549563646336,
+      "eval_loss": 2.6314613819122314,
+      "eval_runtime": 2581.419,
+      "eval_samples_per_second": 5.056,
+      "eval_steps_per_second": 2.528,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4221014277881856.0,
+  "total_flos": 8339076988010496.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null