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:b151c332b7e64084fa3cb9ff7541f9e9b96048de8adc321807092a8187785439
+oid sha256:f06fc72ffbf6e78baf566af23891110228480fb132c21e90c05747020688a5e4
 size 50365768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf282d2bbe0cc76fd1be03e0053272667a815943fba557f2871639640dbbc28d
+oid sha256:c1bf86963d3ea68618c07ac9d961b4f631ca58c32576d1b7cc6478930f39271a
 size 25859156

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d10cb6967c268919dfd4a5f35da79aa6e60d991b3515055573321cc9d7a28efa
+oid sha256:55d7d77540a7b556d05d80c1dbf201b744b3d07ba2c842942609ae688290b630
 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": 1.4616883993148804,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.00031486146095717883,
+  "best_metric": 1.4441759586334229,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.00039357682619647357,
   "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": 9.183,
       "eval_steps_per_second": 4.591,
       "step": 20
+    },
+    {
+      "epoch": 0.0003306045340050378,
+      "grad_norm": 6.7112016677856445,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 4.0752,
+      "step": 21
+    },
+    {
+      "epoch": 0.0003463476070528967,
+      "grad_norm": 5.199258327484131,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 4.6156,
+      "step": 22
+    },
+    {
+      "epoch": 0.0003620906801007557,
+      "grad_norm": 9.658928871154785,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 9.0947,
+      "step": 23
+    },
+    {
+      "epoch": 0.0003778337531486146,
+      "grad_norm": 5.810834884643555,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 3.6453,
+      "step": 24
+    },
+    {
+      "epoch": 0.00039357682619647357,
+      "grad_norm": 5.152379035949707,
+      "learning_rate": 0.0,
+      "loss": 4.1136,
+      "step": 25
+    },
+    {
+      "epoch": 0.00039357682619647357,
+      "eval_loss": 1.4441759586334229,
+      "eval_runtime": 2886.351,
+      "eval_samples_per_second": 9.266,
+      "eval_steps_per_second": 4.633,
+      "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": 2409627616542720.0,
+  "total_flos": 3075143815397376.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null