Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79b3a8adb495844460687cdda7393b7f6882253643fe5c3e502ba09e9e9a7eae
+oid sha256:dcc3a1723ed954220e273770acbb92541d9274077796c8d93246c4540a640a00
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e15cbd9c4290d97da5f63770a17d342607e37354129ed5e894a1cf2ba85fde7
+oid sha256:3281bac24cd20e6a2d61ba706d6fe2d60dda4893b335bee0871c17848fa42178
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2402ffa6243bb683b0930892d69f33711f15bf87d32f7c393ad127e2ae07522e
+oid sha256:da0568708a2b1856620436eb173112b8ddbc54af8ae772db3fa249dc0579747a
 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": 10.345518112182617,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.001191096553264349,
+  "best_metric": 10.34113883972168,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0017866448298965235,
   "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": 76.488,
       "eval_steps_per_second": 38.244,
       "step": 20
+    },
+    {
+      "epoch": 0.0012506513809275664,
+      "grad_norm": 0.5899909138679504,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 10.3461,
+      "step": 21
+    },
+    {
+      "epoch": 0.0014293158639172188,
+      "grad_norm": 0.6252912878990173,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 10.3438,
+      "step": 24
+    },
+    {
+      "epoch": 0.0014888706915804361,
+      "eval_loss": 10.341778755187988,
+      "eval_runtime": 92.4785,
+      "eval_samples_per_second": 76.45,
+      "eval_steps_per_second": 38.225,
+      "step": 25
+    },
+    {
+      "epoch": 0.0016079803469068712,
+      "grad_norm": 0.7194218635559082,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 10.3413,
+      "step": 27
+    },
+    {
+      "epoch": 0.0017866448298965235,
+      "grad_norm": 0.5840440392494202,
+      "learning_rate": 0.0,
+      "loss": 10.3425,
+      "step": 30
+    },
+    {
+      "epoch": 0.0017866448298965235,
+      "eval_loss": 10.34113883972168,
+      "eval_runtime": 92.4377,
+      "eval_samples_per_second": 76.484,
+      "eval_steps_per_second": 38.242,
+      "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": 1046048931840.0,
+  "total_flos": 1569073397760.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null