Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80d98c93ec7ced66da46f99be6b9ec81705cbfc7a85f9123bbb3648ce84d3484
+oid sha256:62be9c98fef19196145079257ad11299c4452cad170ca0a60fcd22fc803799ad
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4d68044cc45ceb3742fda11c536c83d7efe4dd55dfb3367beca50c18d382a70
+oid sha256:b8101dd5a367f4bab7ba66427c1e4dce14ffbf19e894c4ca69fbe21c51c0bda5
 size 323290986

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f982312819f7ba83277ed5f975a5fb52fa2bab58358a330190eae45e4eec760
+oid sha256:7fe3ff3a7b44d8df173fa472ee3a11bfb451d93cd1cd8165e7749377f8118891
 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": 2.0450284481048584,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0010095146758195997,
+  "best_metric": 2.036959648132324,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0015142720137293997,
   "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": 4.047,
       "eval_steps_per_second": 2.024,
       "step": 20
+    },
+    {
+      "epoch": 0.0010599904096105796,
+      "grad_norm": 0.26455485820770264,
+      "learning_rate": 2.8711035421746367e-05,
+      "loss": 2.0786,
+      "step": 21
+    },
+    {
+      "epoch": 0.0012114176109835196,
+      "grad_norm": 0.2742301821708679,
+      "learning_rate": 1.3551568628929434e-05,
+      "loss": 2.0293,
+      "step": 24
+    },
+    {
+      "epoch": 0.0012618933447744996,
+      "eval_loss": 2.038295030593872,
+      "eval_runtime": 2063.0318,
+      "eval_samples_per_second": 4.044,
+      "eval_steps_per_second": 2.022,
+      "step": 25
+    },
+    {
+      "epoch": 0.0013628448123564597,
+      "grad_norm": 0.2601815164089203,
+      "learning_rate": 3.511175705587433e-06,
+      "loss": 1.9709,
+      "step": 27
+    },
+    {
+      "epoch": 0.0015142720137293997,
+      "grad_norm": 0.29170453548431396,
+      "learning_rate": 0.0,
+      "loss": 2.1255,
+      "step": 30
+    },
+    {
+      "epoch": 0.0015142720137293997,
+      "eval_loss": 2.036959648132324,
+      "eval_runtime": 2058.5562,
+      "eval_samples_per_second": 4.052,
+      "eval_steps_per_second": 2.026,
+      "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": 1.4155533539868672e+16,
+  "total_flos": 2.1320680146468864e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null