Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ec7ad1487d7ba340f0071fe736fba04e521851efbd26c15af1d0eb150e68790
+oid sha256:06b2723243a238921db00d6ba234c9ad5ef5c544e0a1f4013895db6292a510fd
 size 101752088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a7c2d5ffdc8f429fd894c9816c10a66ce028f7ac0515cb12a6a3e6e603c7d4a
+oid sha256:915aaf96ea4cdfae0f1e948b511b381e5c73976fd372bdb4b5e60816481b6418
 size 203713238

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f5748f4723fe5f27bd1c7021b459b651579ba81fba9506f294d4743c664285d
+oid sha256:6dd0e6f0633cba3b87b5f2c464b01d32aa2a270b3f84a5297c2b6f3e16b3725b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.7892918586730957,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.053763440860215055,
+  "best_metric": 2.766298294067383,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.08064516129032258,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 16.525,
       "eval_steps_per_second": 4.158,
       "step": 20
+    },
+    {
+      "epoch": 0.056451612903225805,
+      "grad_norm": 0.425810307264328,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 2.751,
+      "step": 21
+    },
+    {
+      "epoch": 0.06451612903225806,
+      "grad_norm": 0.4043796956539154,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 2.8102,
+      "step": 24
+    },
+    {
+      "epoch": 0.06720430107526881,
+      "eval_loss": 2.7712013721466064,
+      "eval_runtime": 18.5863,
+      "eval_samples_per_second": 16.894,
+      "eval_steps_per_second": 4.25,
+      "step": 25
+    },
+    {
+      "epoch": 0.07258064516129033,
+      "grad_norm": 0.47676122188568115,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 2.6888,
+      "step": 27
+    },
+    {
+      "epoch": 0.08064516129032258,
+      "grad_norm": 0.8812837600708008,
+      "learning_rate": 0.0,
+      "loss": 2.6662,
+      "step": 30
+    },
+    {
+      "epoch": 0.08064516129032258,
+      "eval_loss": 2.766298294067383,
+      "eval_runtime": 18.9878,
+      "eval_samples_per_second": 16.537,
+      "eval_steps_per_second": 4.161,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6832335916892160.0,
+  "total_flos": 1.012502792503296e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null