Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b3d47f6b2eaf8ac38ff79e6b691f596908efa8d28f6e2c06ef23dd354f23c66
+oid sha256:68f926e7cd77b13f068f8fc60a2754b4b05a9c81249a15cf4e4632ff6fb784ff
 size 5327496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97c0bc32e89cb94331c817a11a0bfcddcfc60de9de45ddd981b16e90356187f9
+oid sha256:d39db7b94d52ce88643b4bbb8c491a017a2cdbe51dfe3cc748c22a2d964e90e4
 size 2857722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:baaeac5901b2682244555b41f3691b0c12a5b03c2d0cb08398ce2ecda3ff3740
+oid sha256:20158c559844cf8bdecbabd15904d72dbcfc0f58a640a1692249664b10e6922a
 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": 2.847720146179199,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.007963368504877564,
+  "best_metric": 2.8438894748687744,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.009954210631096954,
   "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": 26.718,
       "eval_steps_per_second": 13.359,
       "step": 20
+    },
+    {
+      "epoch": 0.008361536930121441,
+      "grad_norm": 0.6781258583068848,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 10.9849,
+      "step": 21
+    },
+    {
+      "epoch": 0.00875970535536532,
+      "grad_norm": 0.6742913722991943,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 11.2705,
+      "step": 22
+    },
+    {
+      "epoch": 0.009157873780609197,
+      "grad_norm": 0.7851435542106628,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 12.2947,
+      "step": 23
+    },
+    {
+      "epoch": 0.009556042205853077,
+      "grad_norm": 0.7483974695205688,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 11.2183,
+      "step": 24
+    },
+    {
+      "epoch": 0.009954210631096954,
+      "grad_norm": 0.7268701791763306,
+      "learning_rate": 0.0,
+      "loss": 10.7387,
+      "step": 25
+    },
+    {
+      "epoch": 0.009954210631096954,
+      "eval_loss": 2.8438894748687744,
+      "eval_runtime": 39.4822,
+      "eval_samples_per_second": 26.797,
+      "eval_steps_per_second": 13.398,
+      "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": 83829731622912.0,
+  "total_flos": 105052448489472.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null