Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:774cfebe2763204b2445b18775f80def80e3950d9da0869711b13c1454507968
+oid sha256:13f138ba6167106093aa397d7dded2d846b6f422673fe8fad30cac7880e1e4b5
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82dda7aece667fd46fba56abc965f2e0c8600e97ad83b81a9b1c8a494ef1c56e
+oid sha256:5c36784fdbf48a98b761da6365177bc9bc38c0827a14eef6e03d8d78e71480d1
 size 85723732

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e16deb1582ca001dbb180f37009aca74673c34c1897aa485ebd6b2881634a482
+oid sha256:e2e2b5f8430e50053db1f0e53189e7ac7abc289b048f9d1df1b0464a7eebb1e9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77c9b643e87499abdfb160399a4a6e4965274897c037cf91e4cd5d5d65b2b404
+oid sha256:fe0a47cc675a5d4ba5fe8c0d42564476e1fe842799977ab67bf2a8317adef53f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.9585822820663452,
-  "best_model_checkpoint": "miner_id_24/checkpoint-350",
-  "epoch": 0.09556966345825654,
+  "best_metric": 1.8981908559799194,
+  "best_model_checkpoint": "miner_id_24/checkpoint-400",
+  "epoch": 0.10922247252372176,
   "eval_steps": 50,
-  "global_step": 350,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -316,6 +316,49 @@
       "eval_samples_per_second": 25.17,
       "eval_steps_per_second": 6.293,
       "step": 350
+    },
+    {
+      "epoch": 0.09830022527134959,
+      "grad_norm": 10.882676124572754,
+      "learning_rate": 7.113080526603792e-05,
+      "loss": 7.953,
+      "step": 360
+    },
+    {
+      "epoch": 0.10103078708444263,
+      "grad_norm": 10.572400093078613,
+      "learning_rate": 6.607611338819697e-05,
+      "loss": 7.8085,
+      "step": 370
+    },
+    {
+      "epoch": 0.10376134889753567,
+      "grad_norm": 12.119694709777832,
+      "learning_rate": 6.111758245266794e-05,
+      "loss": 7.6887,
+      "step": 380
+    },
+    {
+      "epoch": 0.10649191071062872,
+      "grad_norm": 15.668352127075195,
+      "learning_rate": 5.626926795411447e-05,
+      "loss": 7.7462,
+      "step": 390
+    },
+    {
+      "epoch": 0.10922247252372176,
+      "grad_norm": 22.603986740112305,
+      "learning_rate": 5.1544912966734994e-05,
+      "loss": 7.8605,
+      "step": 400
+    },
+    {
+      "epoch": 0.10922247252372176,
+      "eval_loss": 1.8981908559799194,
+      "eval_runtime": 245.2102,
+      "eval_samples_per_second": 25.154,
+      "eval_steps_per_second": 6.288,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -344,7 +387,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.460953245384704e+17,
+  "total_flos": 2.812517994725376e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null