Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b113f75af4e4edacfa29917f37d4572f6c7ccb0adbc816f88f9095f1cca1c610
+oid sha256:4be90fbc579345dea17bf3682299dee655d26fe4488209d80228e39825c3ec04
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfe9f635df323949a5dfdf43f2a438a6009f6788308f45333979f8e69f4da6e3
-size 170920084
+oid sha256:635065664a8d9468424850c4c2bad755fc89629549ca37ae5f11fdc9b71e58fa
+size 170920532

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7c4c6aeb73e031b64934fbc4f87c0bedf54f8a6dbe4be586cce9651fa910fe2
+oid sha256:7574c4df2d781c0c0af3dbe90aaac583bcf7d60d9284c123001605967a6ba7e7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0a2c2d65c81d2f1a44c97f02ce25b3c742ec1ac58296e9ead6efbd6f748d93f
+oid sha256:f9c4f24febed8904edd77d7c3dfeceec80ce8ac46f187c13cc543808d5fa2a7b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.4184000492095947,
-  "best_model_checkpoint": "miner_id_24/checkpoint-200",
-  "epoch": 0.02730561813093044,
+  "best_metric": 2.3906490802764893,
+  "best_model_checkpoint": "miner_id_24/checkpoint-300",
+  "epoch": 0.040958427196395655,
   "eval_steps": 100,
-  "global_step": 200,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -59,6 +59,28 @@
       "eval_samples_per_second": 35.166,
       "eval_steps_per_second": 8.792,
       "step": 200
+    },
+    {
+      "epoch": 0.034132022663663046,
+      "grad_norm": 123.4080810546875,
+      "learning_rate": 0.00025,
+      "loss": 9.002,
+      "step": 250
+    },
+    {
+      "epoch": 0.040958427196395655,
+      "grad_norm": 60.00017547607422,
+      "learning_rate": 0.00025,
+      "loss": 8.804,
+      "step": 300
+    },
+    {
+      "epoch": 0.040958427196395655,
+      "eval_loss": 2.3906490802764893,
+      "eval_runtime": 175.3105,
+      "eval_samples_per_second": 35.183,
+      "eval_steps_per_second": 8.796,
+      "step": 300
     }
   ],
   "logging_steps": 50,
@@ -87,7 +109,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.07252667285504e+16,
+  "total_flos": 1.060879000928256e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null