Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c5e315eae7aadf57c4f69ad5d89a929539a6a7a764790e832b11f884d5760ec
+oid sha256:c1f65b8b864f6a7e856e440e612f834d9fb3b3162105e7a4a76282ac63bdf7ee
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7be2edbad2004afeeb2dd039b906c1a51fd5f0c22fa1436ebc804433337479d
+oid sha256:7ef4deaae480d34df32adce46602e61aa686a47c5d1a13efdd0162acb421455b
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dac6304c3d282c68b3b54b02e10f7ccb87b4af7f30bf7c763231322312d8a778
+oid sha256:4f474396eecfe9e2fdb32279c7633ecfaa4a13ca05fa0d113fea1216d0a56fc5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
+oid sha256:4521b8db9cc205e54aa606d85e707c024abd2d8ad4a20bec4b2cff365dc59cdf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3795337677001953,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0042739608932578265,
+  "best_metric": 1.3710354566574097,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.005342451116572284,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,49 @@
       "eval_samples_per_second": 7.092,
       "eval_steps_per_second": 3.548,
       "step": 20
+    },
+    {
+      "epoch": 0.004487658937920718,
+      "grad_norm": 0.8185605406761169,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 1.2575,
+      "step": 21
+    },
+    {
+      "epoch": 0.004701356982583609,
+      "grad_norm": 0.8754450678825378,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.3122,
+      "step": 22
+    },
+    {
+      "epoch": 0.004915055027246501,
+      "grad_norm": 0.9416663646697998,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 1.4327,
+      "step": 23
+    },
+    {
+      "epoch": 0.005128753071909392,
+      "grad_norm": 0.9618386626243591,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 1.2672,
+      "step": 24
+    },
+    {
+      "epoch": 0.005342451116572284,
+      "grad_norm": 0.8629248738288879,
+      "learning_rate": 0.0,
+      "loss": 1.3367,
+      "step": 25
+    },
+    {
+      "epoch": 0.005342451116572284,
+      "eval_loss": 1.3710354566574097,
+      "eval_runtime": 274.6611,
+      "eval_samples_per_second": 7.176,
+      "eval_steps_per_second": 3.59,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -210,12 +253,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3257466271825920.0,
+  "total_flos": 4071832839782400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null