Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d78c1ecc039b64c213bb152c19404064ae74e058be5f43a3dea47af7d62fe0c
+oid sha256:1d4ff07c28cba396ec39b9242ee1681be52491dceb122de7173f53a12155a7e9
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:361276cffbcaebaa40bf06e6a642644130e32fb03e533795188777fb4dc34ab4
+oid sha256:f9d2d9eaabd55a880a140606e6a4af3c131ade25a00be94b1fd2446c135bf337
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dc3e5265caade9b4765ce3bea88afed07b875a6b1b6dbe83b1b96d505d55d4b
+oid sha256:c70a576494e56c909be11c04fa488ebbe191aee3195b0dd47c32f36094b31b77
 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": 1.1402697563171387,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.010256410256410256,
+  "best_metric": 1.1001967191696167,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.01282051282051282,
   "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": 4.861,
       "eval_steps_per_second": 2.431,
       "step": 20
+    },
+    {
+      "epoch": 0.010769230769230769,
+      "grad_norm": 32.67024230957031,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 3.6896,
+      "step": 21
+    },
+    {
+      "epoch": 0.011282051282051283,
+      "grad_norm": 28.793724060058594,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 5.4251,
+      "step": 22
+    },
+    {
+      "epoch": 0.011794871794871795,
+      "grad_norm": 52.28025817871094,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 4.2507,
+      "step": 23
+    },
+    {
+      "epoch": 0.012307692307692308,
+      "grad_norm": 34.58713912963867,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 5.2803,
+      "step": 24
+    },
+    {
+      "epoch": 0.01282051282051282,
+      "grad_norm": 41.41437911987305,
+      "learning_rate": 0.0,
+      "loss": 5.446,
+      "step": 25
+    },
+    {
+      "epoch": 0.01282051282051282,
+      "eval_loss": 1.1001967191696167,
+      "eval_runtime": 159.3672,
+      "eval_samples_per_second": 5.158,
+      "eval_steps_per_second": 2.579,
+      "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": 3505339571896320.0,
+  "total_flos": 4381674464870400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null