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:e554fe0576476e10d81b30240b7ebb6bf7e11918985a67e48c7c8cc9837e79c1
+oid sha256:12dc73d79ff244656efdbb8200e9c5d31b1a41ae91fc9daf87d2e625a5433730
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50288d58a8d08bd24d1f68eacae08eea637c1d00944122fd1caf838d65343bb7
+oid sha256:f7a121c3b13af0b7b149dd6fad0266e5ca14652e89e4160effd1089d75c9777e
 size 70667778

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7398c4730b443a556b0f3765250cdc5b60e639de3117d0b5766017dd403aff5
+oid sha256:873089a2adf68cf04a7e9797373dc70809b923187989a221416a3f0b6004a882
 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": 2.750244379043579,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.023121387283236993,
+  "best_metric": 2.689387321472168,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.03468208092485549,
   "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": 37.636,
       "eval_steps_per_second": 18.87,
       "step": 20
+    },
+    {
+      "epoch": 0.024277456647398842,
+      "grad_norm": 12.756491661071777,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 2.7991,
+      "step": 21
+    },
+    {
+      "epoch": 0.027745664739884393,
+      "grad_norm": 8.277565956115723,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 2.1547,
+      "step": 24
+    },
+    {
+      "epoch": 0.028901734104046242,
+      "eval_loss": 2.698179244995117,
+      "eval_runtime": 9.9751,
+      "eval_samples_per_second": 36.591,
+      "eval_steps_per_second": 18.346,
+      "step": 25
+    },
+    {
+      "epoch": 0.03121387283236994,
+      "grad_norm": 7.9303297996521,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 2.4543,
+      "step": 27
+    },
+    {
+      "epoch": 0.03468208092485549,
+      "grad_norm": 8.284680366516113,
+      "learning_rate": 0.0,
+      "loss": 2.401,
+      "step": 30
+    },
+    {
+      "epoch": 0.03468208092485549,
+      "eval_loss": 2.689387321472168,
+      "eval_runtime": 9.9846,
+      "eval_samples_per_second": 36.556,
+      "eval_steps_per_second": 18.328,
+      "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": 360477150412800.0,
+  "total_flos": 540715725619200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null