Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25b741c219456f5c0897df1b410a563f503678034057bbe2e71f4c2f7f7520be
+oid sha256:4fa1a1b0c4935169082bbda138863c6449c290bd462133eb78c930759c70d443
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:884bee2a7dc2b9a524984b1d103b3abe783afd4089d59a1a6a569a4a4c8a2bd9
+oid sha256:9e04db57828133ac8d648d8136bee7f87c45a04a3a2370cfb079fda86f86687b
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c0cad57676d282037ca3ab77062b282474c1dffdefc39525ec854426ab32c79
+oid sha256:31d55330266146f1be4d0d3a083d5bb4e8e2d93fc4176aa2c3b77e0b24f87890
 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": 10.362568855285645,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0030128422400482057,
+  "best_metric": 10.361613273620605,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.004519263360072308,
   "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": 279.738,
       "eval_steps_per_second": 69.96,
       "step": 20
+    },
+    {
+      "epoch": 0.003163484352050616,
+      "grad_norm": 0.11058437079191208,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 10.3638,
+      "step": 21
+    },
+    {
+      "epoch": 0.0036154106880578467,
+      "grad_norm": 0.1200045794248581,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 10.3641,
+      "step": 24
+    },
+    {
+      "epoch": 0.003766052800060257,
+      "eval_loss": 10.361776351928711,
+      "eval_runtime": 19.728,
+      "eval_samples_per_second": 283.353,
+      "eval_steps_per_second": 70.864,
+      "step": 25
+    },
+    {
+      "epoch": 0.004067337024065077,
+      "grad_norm": 0.11940017342567444,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 10.3617,
+      "step": 27
+    },
+    {
+      "epoch": 0.004519263360072308,
+      "grad_norm": 0.12489710003137589,
+      "learning_rate": 0.0,
+      "loss": 10.3614,
+      "step": 30
+    },
+    {
+      "epoch": 0.004519263360072308,
+      "eval_loss": 10.361613273620605,
+      "eval_runtime": 20.2969,
+      "eval_samples_per_second": 275.412,
+      "eval_steps_per_second": 68.878,
+      "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": 4,
   "trial_name": null,
   "trial_params": null