Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:024ec522820021456056770199a6e69a1cb16404da6a6ed85d5c57714746e440
+oid sha256:73478c9c2c7b40cb352d74cc0256d2b86488dbb6718de1792bac8f6dbaa709db
 size 100690184

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e59255bfba12a432921e4206413a16f99ffe14e24344f0840bd213a7846ddf2
+oid sha256:6fd508b42aa7761c51a1f865cd59018a61b6281a4b11f989dd7787a8dd580243
 size 51345082

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a8879ab1af878426e10fbad6694eb15cd02e8603536fc02026e1ffecbc8e901
+oid sha256:41ee02fa0c1e4910acaa24b0e4524a53f0a2b2a306066536ff2bc2218e8e97da
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea278ffcc402f8731d694a21dbc5a96671a02299dc57c40b61a02431bc8aed26
+oid sha256:200a199971193d5b4ec602093f689606117a65db31ca244b618fc0f0cd969846
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8364555239677429,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.21500238891543239,
+  "best_metric": 0.832525908946991,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.23889154323936931,
   "eval_steps": 50,
-  "global_step": 450,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -402,6 +402,49 @@
       "eval_samples_per_second": 77.215,
       "eval_steps_per_second": 19.347,
       "step": 450
+    },
+    {
+      "epoch": 0.21978021978021978,
+      "grad_norm": 26.848785400390625,
+      "learning_rate": 4.2031059906924e-06,
+      "loss": 1.0386,
+      "step": 460
+    },
+    {
+      "epoch": 0.22455805064500717,
+      "grad_norm": 13.840141296386719,
+      "learning_rate": 2.3709853203820825e-06,
+      "loss": 1.2618,
+      "step": 470
+    },
+    {
+      "epoch": 0.22933588150979456,
+      "grad_norm": 37.794471740722656,
+      "learning_rate": 1.0559145415396157e-06,
+      "loss": 1.6539,
+      "step": 480
+    },
+    {
+      "epoch": 0.23411371237458195,
+      "grad_norm": 38.33562088012695,
+      "learning_rate": 2.643005468090745e-07,
+      "loss": 1.7703,
+      "step": 490
+    },
+    {
+      "epoch": 0.23889154323936931,
+      "grad_norm": 19.850322723388672,
+      "learning_rate": 0.0,
+      "loss": 2.0542,
+      "step": 500
+    },
+    {
+      "epoch": 0.23889154323936931,
+      "eval_loss": 0.832525908946991,
+      "eval_runtime": 11.6134,
+      "eval_samples_per_second": 75.947,
+      "eval_steps_per_second": 19.03,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -425,12 +468,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4191310105804800.0,
+  "total_flos": 4657011228672000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null