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:aa894ee32425518a3ee9a468ac21c436055bb2433a014cb978e6085c5ba57aa9
+oid sha256:20e3302429c9fc6d50a0a46df3493a1392c5593df4aaa8a62aed4ea476549039
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d249d02bd710b3b3de8f049e739adeb5e7a445f7d5ee9527135bf24c656c0761
+oid sha256:7371768f95e6d874380e1bf2858852ed98daf5f0d439f384f88501babfc3376d
 size 70667778

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb5474b8229a1c766aba0c2731c5d108f3b3249228ece3b9cf0d9dbaba3e98a6
+oid sha256:f057376ff1135fac33ce0c3e9ad0497b4f3c667c44284d0da32f48104ad5c6dd
 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": 1.9425504207611084,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0020751731472594746,
+  "best_metric": 1.9352331161499023,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0031127597208892117,
   "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": 18.55,
       "eval_steps_per_second": 9.275,
       "step": 20
+    },
+    {
+      "epoch": 0.0021789318046224484,
+      "grad_norm": 1.1187844276428223,
+      "learning_rate": 2.8711035421746367e-05,
+      "loss": 2.0046,
+      "step": 21
+    },
+    {
+      "epoch": 0.002490207776711369,
+      "grad_norm": 0.737541675567627,
+      "learning_rate": 1.3551568628929434e-05,
+      "loss": 1.921,
+      "step": 24
+    },
+    {
+      "epoch": 0.002593966434074343,
+      "eval_loss": 1.9361823797225952,
+      "eval_runtime": 217.4207,
+      "eval_samples_per_second": 18.664,
+      "eval_steps_per_second": 9.332,
+      "step": 25
+    },
+    {
+      "epoch": 0.0028014837488002904,
+      "grad_norm": 0.7507085204124451,
+      "learning_rate": 3.511175705587433e-06,
+      "loss": 1.9561,
+      "step": 27
+    },
+    {
+      "epoch": 0.0031127597208892117,
+      "grad_norm": 1.059324860572815,
+      "learning_rate": 0.0,
+      "loss": 1.9411,
+      "step": 30
+    },
+    {
+      "epoch": 0.0031127597208892117,
+      "eval_loss": 1.9352331161499023,
+      "eval_runtime": 218.3545,
+      "eval_samples_per_second": 18.584,
+      "eval_steps_per_second": 9.292,
+      "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": 720954300825600.0,
+  "total_flos": 1081431451238400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null