Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4be90fbc579345dea17bf3682299dee655d26fe4488209d80228e39825c3ec04
+oid sha256:819e785a9980818c83c4b249bb714c2dbb71810466554b0ca9f0d2e1ec9c0c40
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:635065664a8d9468424850c4c2bad755fc89629549ca37ae5f11fdc9b71e58fa
+oid sha256:1d8676b70101b430215e22b340ce45cc7b617d94d343716ed381586f9b1bb225
 size 170920532

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7574c4df2d781c0c0af3dbe90aaac583bcf7d60d9284c123001605967a6ba7e7
+oid sha256:113738d73b2993a738a284b6571514b8789145a9c46430bfbd59e9ec6ea0f8d7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9c4f24febed8904edd77d7c3dfeceec80ce8ac46f187c13cc543808d5fa2a7b
+oid sha256:3b222f50cf4019bf2a4af9801ee61ced983584829f5aab356a024b6284fbfaea
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 2.3906490802764893,
   "best_model_checkpoint": "miner_id_24/checkpoint-300",
-  "epoch": 0.040958427196395655,
+  "epoch": 0.05461123626186088,
   "eval_steps": 100,
-  "global_step": 300,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -81,6 +81,28 @@
       "eval_samples_per_second": 35.183,
       "eval_steps_per_second": 8.796,
       "step": 300
+    },
+    {
+      "epoch": 0.04778483172912827,
+      "grad_norm": 48.440155029296875,
+      "learning_rate": 0.00025,
+      "loss": 8.7073,
+      "step": 350
+    },
+    {
+      "epoch": 0.05461123626186088,
+      "grad_norm": 143.95608520507812,
+      "learning_rate": 0.00025,
+      "loss": 8.7399,
+      "step": 400
+    },
+    {
+      "epoch": 0.05461123626186088,
+      "eval_loss": 2.447601318359375,
+      "eval_runtime": 175.5057,
+      "eval_samples_per_second": 35.144,
+      "eval_steps_per_second": 8.786,
+      "step": 400
     }
   ],
   "logging_steps": 50,
@@ -95,7 +117,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -109,7 +131,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.060879000928256e+17,
+  "total_flos": 1.414505334571008e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null