Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64084a9725d59c6371d8336d29bfe8b2ee6566617481dc54ab05673b1eb1f22a
+oid sha256:2ff95c29d1750d92a3787e765189a9e7f0c7161de50fd9b17b1461c9ee081338
 size 1157746040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1bd75dc1ad6db0dbce8794730c2272ea2603b6c558995ce9300b6b946739958
+oid sha256:e978b1f869052d53aeb288937e36ccf34d3742d19c7a52bd2cba36af35bcac61
 size 588699796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59e234dbc433528225047a7291fc816ceaa0a60efa14f2cb57dddb9e76d08088
+oid sha256:c3b126f4b4e5c2909be5eb79075beb49bba1c2edf89b512969d055a9d65fcfad
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a760ba92960f08f363394eee4df1edc2c66e6b8b22489dbac9e6aa0f5ae478e1
+oid sha256:9a7c1078eb5a1a7c3016e3bc1b27b5075c61ea30d4750bf448abc31716e92a9c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.8087369203567505,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.028421202216853774,
+  "best_metric": 1.7171608209609985,
+  "best_model_checkpoint": "miner_id_24/checkpoint-150",
+  "epoch": 0.04263180332528066,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 9.089,
       "eval_steps_per_second": 2.281,
       "step": 100
+    },
+    {
+      "epoch": 0.03126332243853915,
+      "grad_norm": 2.0331203937530518,
+      "learning_rate": 0.00019709518213718787,
+      "loss": 1.708,
+      "step": 110
+    },
+    {
+      "epoch": 0.03410544266022453,
+      "grad_norm": 4.635890007019043,
+      "learning_rate": 0.00019394360206446948,
+      "loss": 1.6543,
+      "step": 120
+    },
+    {
+      "epoch": 0.0369475628819099,
+      "grad_norm": 2.990798234939575,
+      "learning_rate": 0.00019034895390411186,
+      "loss": 1.8625,
+      "step": 130
+    },
+    {
+      "epoch": 0.039789683103595284,
+      "grad_norm": 3.2386255264282227,
+      "learning_rate": 0.0001863287504206196,
+      "loss": 1.7414,
+      "step": 140
+    },
+    {
+      "epoch": 0.04263180332528066,
+      "grad_norm": 1.6220500469207764,
+      "learning_rate": 0.00018190257764125471,
+      "loss": 1.7585,
+      "step": 150
+    },
+    {
+      "epoch": 0.04263180332528066,
+      "eval_loss": 1.7171608209609985,
+      "eval_runtime": 82.0601,
+      "eval_samples_per_second": 9.03,
+      "eval_steps_per_second": 2.267,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -115,7 +158,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -129,7 +172,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.7577745273847808e+16,
+  "total_flos": 2.657292947501875e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null