Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c022268ed178d293663732db9402b65a56222d170d7eab35f9f47a027dda43c
+oid sha256:2916ee5209d8d745e5dc6dbfcafef656cc1dd41a05b967ea39529acc2b4962ce
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a865ebe54ade78fbbf64d8dcb1d1e170dce4e865de3b66d676787e8301376e90
+oid sha256:ba9f1284e06b17efe556d80b84e8525bdf279a42e40c9fb0b6e7502de043d181
 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": 0.004052300937473774,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.07476635514018691,
+  "best_metric": 0.0022247470915317535,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.09345794392523364,
   "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": 3.795,
       "eval_steps_per_second": 1.914,
       "step": 20
+    },
+    {
+      "epoch": 0.07850467289719626,
+      "grad_norm": 0.003418724285438657,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.0001,
+      "step": 21
+    },
+    {
+      "epoch": 0.08224299065420561,
+      "grad_norm": 13.917028427124023,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.309,
+      "step": 22
+    },
+    {
+      "epoch": 0.08598130841121496,
+      "grad_norm": 0.0038088576402515173,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.0001,
+      "step": 23
+    },
+    {
+      "epoch": 0.08971962616822429,
+      "grad_norm": 0.005070657003670931,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.0001,
+      "step": 24
+    },
+    {
+      "epoch": 0.09345794392523364,
+      "grad_norm": 0.03886491060256958,
+      "learning_rate": 0.0,
+      "loss": 0.0002,
+      "step": 25
+    },
+    {
+      "epoch": 0.09345794392523364,
+      "eval_loss": 0.0022247470915317535,
+      "eval_runtime": 29.8119,
+      "eval_samples_per_second": 3.79,
+      "eval_steps_per_second": 1.912,
+      "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