Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d734213c1d3edf8ed0d835d2a8d377695771d873203e89cdf70559a5e3a0a324
+oid sha256:64084a9725d59c6371d8336d29bfe8b2ee6566617481dc54ab05673b1eb1f22a
 size 1157746040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:745a2beb0dcd15322bc8d71b417d3ef8c874fe1fe70e880b5a112d51812bc312
+oid sha256:f1bd75dc1ad6db0dbce8794730c2272ea2603b6c558995ce9300b6b946739958
 size 588699796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76a6cf6602c25065955dd9f642809679e1356a7da6b6b32f2374fcbb8ccfb6a9
+oid sha256:59e234dbc433528225047a7291fc816ceaa0a60efa14f2cb57dddb9e76d08088
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f05a07b776abc173978a0e887e7c70d773d3b63ce9e1342d6d78880c1684ac0
+oid sha256:a760ba92960f08f363394eee4df1edc2c66e6b8b22489dbac9e6aa0f5ae478e1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.8087369203567505,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.014210601108426887,
+  "epoch": 0.028421202216853774,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 9.073,
       "eval_steps_per_second": 2.277,
       "step": 50
+    },
+    {
+      "epoch": 0.017052721330112264,
+      "grad_norm": 3.674773931503296,
+      "learning_rate": 0.0002057490971767619,
+      "loss": 1.7821,
+      "step": 60
+    },
+    {
+      "epoch": 0.019894841551797642,
+      "grad_norm": 3.0321569442749023,
+      "learning_rate": 0.00020499761108038175,
+      "loss": 1.6055,
+      "step": 70
+    },
+    {
+      "epoch": 0.022736961773483017,
+      "grad_norm": 2.507596254348755,
+      "learning_rate": 0.00020374920287558198,
+      "loss": 1.3591,
+      "step": 80
+    },
+    {
+      "epoch": 0.025579081995168396,
+      "grad_norm": 8.490031242370605,
+      "learning_rate": 0.00020200995468164684,
+      "loss": 1.2845,
+      "step": 90
+    },
+    {
+      "epoch": 0.028421202216853774,
+      "grad_norm": 42.760581970214844,
+      "learning_rate": 0.00019978833994094855,
+      "loss": 1.8626,
+      "step": 100
+    },
+    {
+      "epoch": 0.028421202216853774,
+      "eval_loss": 2.087491750717163,
+      "eval_runtime": 81.5271,
+      "eval_samples_per_second": 9.089,
+      "eval_steps_per_second": 2.281,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -72,7 +115,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -86,7 +129,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9325282703966208.0,
+  "total_flos": 1.7577745273847808e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null