Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a7ba2eebe874f091291dffecfe55b7332dae4d8d63e11c416e308af73d1f2d1
+oid sha256:18fbcef5e715db89ebee3d48304ba9f05c4fa1e46d61cb15e9cfa395a220116f
 size 4731640

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12a0f339da764fb5739ae255569973720c18b05bfa7b9a2ff78256f8bb3d5bbc
+oid sha256:bd69886f1e6ed7479847ce950f42df83876378a98e2423c9725b1e892b8f96cf
 size 2505722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:994034717e12e40cf8684521a3d2529d09c2397c5a8d5800aa2a30d80556de58
+oid sha256:a1f1b8e2eecce5ee7106652b3e63a17b0bf5df4234fa2b264d2c597b50146369
 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": 3.155805826187134,
   "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.055865921787709494,
+  "epoch": 0.06983240223463687,
   "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": 30.089,
       "eval_steps_per_second": 15.144,
       "step": 20
+    },
+    {
+      "epoch": 0.05865921787709497,
+      "grad_norm": 665.962646484375,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 13.8204,
+      "step": 21
+    },
+    {
+      "epoch": 0.061452513966480445,
+      "grad_norm": 1509.6649169921875,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 13.2364,
+      "step": 22
+    },
+    {
+      "epoch": 0.06424581005586592,
+      "grad_norm": 1729.46875,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 13.1418,
+      "step": 23
+    },
+    {
+      "epoch": 0.0670391061452514,
+      "grad_norm": 1822.8065185546875,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 11.3855,
+      "step": 24
+    },
+    {
+      "epoch": 0.06983240223463687,
+      "grad_norm": 1578.525146484375,
+      "learning_rate": 0.0,
+      "loss": 12.9873,
+      "step": 25
+    },
+    {
+      "epoch": 0.06983240223463687,
+      "eval_loss": 3.159228563308716,
+      "eval_runtime": 4.9163,
+      "eval_samples_per_second": 30.714,
+      "eval_steps_per_second": 15.459,
+      "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": 61375669862400.0,
+  "total_flos": 76719587328000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null