Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ba51009c92a9e928d344568710ef7ce7a429dcb0f7c4992fb1450c2e7ae0f40
+oid sha256:9c61c33359707979da1784a5d043074d68a5d39636a4d58c56fea0e6b7c1e3cf
 size 25192496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd192f0af181f67e5d948646fcc9e9d76bebf9f10999aecc7a5e57ed8463631
+oid sha256:781b49db2435e5dac9da247adbc225a8e82b9d0f4676f316c4ba4e089814a8ea
 size 13005178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:326b940c26441f9cc805b55861d6ba1368323749e2ade38b0a118c4c7d409c57
+oid sha256:db7358aa0d1acbba0f631354f26b2935a02b7fc39c23af4dc0b77534a51a3557
 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": 0.21308887004852295,
   "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.016824395373291272,
+  "epoch": 0.02103049421661409,
   "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": 15.389,
       "eval_steps_per_second": 7.71,
       "step": 20
+    },
+    {
+      "epoch": 0.017665615141955835,
+      "grad_norm": 20.2840576171875,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 1.176,
+      "step": 21
+    },
+    {
+      "epoch": 0.0185068349106204,
+      "grad_norm": 10.489984512329102,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.6443,
+      "step": 22
+    },
+    {
+      "epoch": 0.01934805467928496,
+      "grad_norm": 13.999197006225586,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 1.1505,
+      "step": 23
+    },
+    {
+      "epoch": 0.02018927444794953,
+      "grad_norm": 4.992821216583252,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.6334,
+      "step": 24
+    },
+    {
+      "epoch": 0.02103049421661409,
+      "grad_norm": 4.176143646240234,
+      "learning_rate": 0.0,
+      "loss": 0.8215,
+      "step": 25
+    },
+    {
+      "epoch": 0.02103049421661409,
+      "eval_loss": 0.21602469682693481,
+      "eval_runtime": 33.5718,
+      "eval_samples_per_second": 14.923,
+      "eval_steps_per_second": 7.477,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -201,7 +244,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -210,12 +253,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 597144738201600.0,
+  "total_flos": 746430922752000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null