Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15d01f6f2ce990041e96f7b603b712b7ecc458eba40b88fb32b1439fced493e5
+oid sha256:c1ce8d70b452d34853544abe548e499fddaaeb22ad8621a83bb7e169a929142a
 size 47724600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d48503d098a83d76b7724c261bf714ad151c3c965aa43ec17b5e18ce152e4b7
+oid sha256:402e6dcd3edd60c21fccef83b4843b807de7bf85c9cb7dcbccdeb1bc03baeb8f
 size 25331516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63d9bff343b7803fcf3db9e4e4d683e8999572bd1f5de37d364a48fa1087f4f3
+oid sha256:20f978044a6d83281021f604fa936c22823d5c94cd67b96bf7497cde7ffc837b
 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": 1.7913482189178467,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0032665060634518802,
+  "best_metric": 1.7827017307281494,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.00408313257931485,
   "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": 7.449,
       "eval_steps_per_second": 3.725,
       "step": 20
+    },
+    {
+      "epoch": 0.003429831366624474,
+      "grad_norm": 10.473787307739258,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 14.4631,
+      "step": 21
+    },
+    {
+      "epoch": 0.003593156669797068,
+      "grad_norm": 13.125104904174805,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 14.6268,
+      "step": 22
+    },
+    {
+      "epoch": 0.003756481972969662,
+      "grad_norm": 10.47437572479248,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 13.3864,
+      "step": 23
+    },
+    {
+      "epoch": 0.003919807276142257,
+      "grad_norm": 11.305819511413574,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 12.3434,
+      "step": 24
+    },
+    {
+      "epoch": 0.00408313257931485,
+      "grad_norm": 12.866353034973145,
+      "learning_rate": 0.0,
+      "loss": 12.8434,
+      "step": 25
+    },
+    {
+      "epoch": 0.00408313257931485,
+      "eval_loss": 1.7827017307281494,
+      "eval_runtime": 347.3993,
+      "eval_samples_per_second": 7.421,
+      "eval_steps_per_second": 3.71,
+      "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": 2167222768238592.0,
+  "total_flos": 2611325794516992.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null