Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56c11b896781abad49e2f36f9b813a9dcde656281d7dbc81c57ec0a800b6cbd0
+oid sha256:243990c7d7ec3d1e500e1d569853373ee5a00d6f4659c2111f833f0e961b32ac
 size 50365768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba1d1beacc297719f0a8e681227c291b01c3179f3cf5764464213929ec0a9336
+oid sha256:87fdd7c095fe9db1c640eaa55533c1a0a6c9572553647f3a601a9b1662d61c78
 size 25859156

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6400b71c58d8852d97ee274f2c0c19d268ee7995aa59f21416a02749a9c55550
+oid sha256:46ed7ce373dd1448f22bb7460bf33b60dce1841e1f0e7eb2308263bebadb8789
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0015322735108216816,
+  "epoch": 0.0030645470216433632,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,92 @@
       "eval_samples_per_second": 10.654,
       "eval_steps_per_second": 5.327,
       "step": 10
+    },
+    {
+      "epoch": 0.0016855008619038499,
+      "grad_norm": 8.324821472167969,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 13.3406,
+      "step": 11
+    },
+    {
+      "epoch": 0.001838728212986018,
+      "grad_norm": 12.34853458404541,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 12.9688,
+      "step": 12
+    },
+    {
+      "epoch": 0.0019919555640681864,
+      "grad_norm": 12.710118293762207,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 10.9828,
+      "step": 13
+    },
+    {
+      "epoch": 0.002145182915150354,
+      "grad_norm": 10.844730377197266,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 18.4505,
+      "step": 14
+    },
+    {
+      "epoch": 0.0022984102662325224,
+      "grad_norm": 11.561506271362305,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 6.0802,
+      "step": 15
+    },
+    {
+      "epoch": 0.0022984102662325224,
+      "eval_loss": NaN,
+      "eval_runtime": 255.8755,
+      "eval_samples_per_second": 10.74,
+      "eval_steps_per_second": 5.37,
+      "step": 15
+    },
+    {
+      "epoch": 0.0024516376173146907,
+      "grad_norm": 6.431066036224365,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.5329,
+      "step": 16
+    },
+    {
+      "epoch": 0.002604864968396859,
+      "grad_norm": 11.73428726196289,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 7.6338,
+      "step": 17
+    },
+    {
+      "epoch": 0.002758092319479027,
+      "grad_norm": 8.838054656982422,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 7.2587,
+      "step": 18
+    },
+    {
+      "epoch": 0.002911319670561195,
+      "grad_norm": 10.580836296081543,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 17.5154,
+      "step": 19
+    },
+    {
+      "epoch": 0.0030645470216433632,
+      "grad_norm": 8.958062171936035,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 12.1425,
+      "step": 20
+    },
+    {
+      "epoch": 0.0030645470216433632,
+      "eval_loss": NaN,
+      "eval_runtime": 271.2795,
+      "eval_samples_per_second": 10.13,
+      "eval_steps_per_second": 5.065,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -115,7 +201,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 2
       }
     },
     "TrainerControl": {
@@ -124,12 +210,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 917953377730560.0,
+  "total_flos": 1881804424347648.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null