Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6aeaccaf15d9cc905756383f4d5dc0bc26f9ef298ed5479c32a3032eaf843504
+oid sha256:b3b369ba5bf5db4948fc34917486321d0e7fbb0bbb3d900a03edb03487fcf35f
 size 25192688

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7026a902d899090a80dd51ccbfc74cfec268b79a877b96ff256662b6cd6a4ba0
+oid sha256:4df35a66ceda92604003b374b1dc18d0d466b50b425bdac6b4ebfdf619271c32
 size 50445306

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:326b940c26441f9cc805b55861d6ba1368323749e2ade38b0a118c4c7d409c57
+oid sha256:705deedf796b313cb76cd6c14cb7b94da899d809f9d9c1109db82fbb592f3b6c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2eb657255baf6b1420bbcfab19529abd45c6011f0c415bddb3c278a51f7f142
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 4.605849742889404,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.00032073641079919497,
+  "best_metric": 4.549448013305664,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.00048110461619879245,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 29.344,
       "eval_steps_per_second": 14.672,
       "step": 20
+    },
+    {
+      "epoch": 0.0003367732313391547,
+      "grad_norm": 9.476841926574707,
+      "learning_rate": 2.8711035421746367e-05,
+      "loss": 18.1777,
+      "step": 21
+    },
+    {
+      "epoch": 0.00038488369295903394,
+      "grad_norm": 12.611469268798828,
+      "learning_rate": 1.3551568628929434e-05,
+      "loss": 19.379,
+      "step": 24
+    },
+    {
+      "epoch": 0.0004009205134989937,
+      "eval_loss": 4.5646562576293945,
+      "eval_runtime": 893.5971,
+      "eval_samples_per_second": 29.382,
+      "eval_steps_per_second": 14.691,
+      "step": 25
+    },
+    {
+      "epoch": 0.00043299415457891317,
+      "grad_norm": 8.356888771057129,
+      "learning_rate": 3.511175705587433e-06,
+      "loss": 18.3493,
+      "step": 27
+    },
+    {
+      "epoch": 0.00048110461619879245,
+      "grad_norm": 9.053627014160156,
+      "learning_rate": 0.0,
+      "loss": 18.3131,
+      "step": 30
+    },
+    {
+      "epoch": 0.00048110461619879245,
+      "eval_loss": 4.549448013305664,
+      "eval_runtime": 891.0399,
+      "eval_samples_per_second": 29.467,
+      "eval_steps_per_second": 14.733,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 303370988421120.0,
+  "total_flos": 455056482631680.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null