Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28f86ce227582de0408f4fd5baf2337a15d141bb027322e3669c3757df557890
+oid sha256:1920f8c571933f387f8ec7d606e7671d9d8d814ac7fee9d7ea0b3259c9e61db7
 size 1157746040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af2956d0ebe9b5d4bde783eac5815d626ec42b0c4b4707fbd6743b7211c18344
+oid sha256:4b8e1f9c2814ada4cc2941c2f239c9f875c037e65e9f8eb1533ae01078ff1a68
 size 588700500

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e18d050e19e31686aec08431c138506d0182de191c19ad118328ec0a322ea615
+oid sha256:da029d306d5935dd72183ce162ddaebbaf1460e4f1049d17fe9222fec1918c1e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89df26d2648b7bbd96c19b1cc0947215f3b7f788b7b6e7a6d1179c8d03cbffea
+oid sha256:23d0c4fcd75282d05c3ecf542229a263cdfdea966c314071913c5dc6faf85a25
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2067750692367554,
-  "best_model_checkpoint": "miner_id_24/checkpoint-350",
-  "epoch": 0.06791171477079797,
+  "best_metric": 1.1962662935256958,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.07640067911714771,
   "eval_steps": 50,
-  "global_step": 400,
+  "global_step": 450,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -359,6 +359,49 @@
       "eval_samples_per_second": 5.263,
       "eval_steps_per_second": 1.316,
       "step": 400
+    },
+    {
+      "epoch": 0.06960950764006792,
+      "grad_norm": 0.7046334743499756,
+      "learning_rate": 1.9671249579380422e-05,
+      "loss": 1.2294,
+      "step": 410
+    },
+    {
+      "epoch": 0.07130730050933787,
+      "grad_norm": 0.6611829400062561,
+      "learning_rate": 1.5651046095888127e-05,
+      "loss": 1.1951,
+      "step": 420
+    },
+    {
+      "epoch": 0.0730050933786078,
+      "grad_norm": 0.5956356525421143,
+      "learning_rate": 1.205639793553052e-05,
+      "loss": 1.1891,
+      "step": 430
+    },
+    {
+      "epoch": 0.07470288624787776,
+      "grad_norm": 0.6220433115959167,
+      "learning_rate": 8.904817862812098e-06,
+      "loss": 1.1773,
+      "step": 440
+    },
+    {
+      "epoch": 0.07640067911714771,
+      "grad_norm": 0.7181682586669922,
+      "learning_rate": 6.211660059051443e-06,
+      "loss": 1.2383,
+      "step": 450
+    },
+    {
+      "epoch": 0.07640067911714771,
+      "eval_loss": 1.1962662935256958,
+      "eval_runtime": 235.3359,
+      "eval_samples_per_second": 5.269,
+      "eval_steps_per_second": 1.317,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -373,7 +416,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.274180220789719e+17,
+  "total_flos": 1.439229472187351e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null