Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:671678d7dba30b87bcd3079e44864b61aed7cbf0eea9ac3e6ab102f9de913f6f
+oid sha256:5a84d066f7d90de2d6179c45becb5b84e2ce4fafcc0af9d76546b63b770fea9e
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebe3d2b023a8215f6a320e605916cba8ea44497d7bbe104b7acff0d799771c8f
+oid sha256:ed4342468c2b36f166e8fc5b89521cc1472f53a41c87fef27070cbf278c47932
 size 160172858

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ea2a312f1b8c04a72fd99088711bbbc598702a183b1e975bfad4d3e09d41f45
+oid sha256:e06564cbcf069978325595b525a9a700560d13778f3b042e8c46849759c57d03
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7af249df5fe11a9896f83a1f972a51ac4c516f61ca7fde0473cca60d389d7ec
+oid sha256:4677d15317405bcdd600dfdae9d04715d81517a0dbc7789a073149e371184d8c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9468892216682434,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.002733454060887689,
+  "best_metric": 0.9351497292518616,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.0034168175761096113,
   "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": 4.723,
       "eval_steps_per_second": 2.362,
       "step": 20
+    },
+    {
+      "epoch": 0.0028701267639320736,
+      "grad_norm": 0.6563827991485596,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.9682,
+      "step": 21
+    },
+    {
+      "epoch": 0.003006799466976458,
+      "grad_norm": 0.5494142770767212,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.8056,
+      "step": 22
+    },
+    {
+      "epoch": 0.0031434721700208425,
+      "grad_norm": 0.3957728147506714,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.734,
+      "step": 23
+    },
+    {
+      "epoch": 0.003280144873065227,
+      "grad_norm": 0.6835604906082153,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.7604,
+      "step": 24
+    },
+    {
+      "epoch": 0.0034168175761096113,
+      "grad_norm": 0.8520634174346924,
+      "learning_rate": 0.0,
+      "loss": 0.7742,
+      "step": 25
+    },
+    {
+      "epoch": 0.0034168175761096113,
+      "eval_loss": 0.9351497292518616,
+      "eval_runtime": 649.7327,
+      "eval_samples_per_second": 4.742,
+      "eval_steps_per_second": 2.372,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -210,12 +253,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6138140389539840.0,
+  "total_flos": 7785963312906240.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null