Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fe9d39bc518a75a195c8f8f6e2c11b9b030825c9ce17b49e9372fd16240bd00
+oid sha256:b5a362caa98a7cf0ca7d27fb8bca93cead867a831a107b41c3ef7382c69806d1
 size 56662952

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2303afb9b04ed4e6cc55df48abd92bbf2dff385ff3c6066c0932d241ac826f9
+oid sha256:cff63bb3b1536b754656dd6d7e7702bae88e73eacfd2dd5360f3844bf5ba06f8
 size 113488058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3a3e00948e7d286aa05a4ef254b50b044807a0452eb4cb18ca83be3d8d907f5
+oid sha256:41d7fde013ba490618b122befb4a78e9f7e85df69c4c8198d8dbe0cbb6f00574
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4145777225494385,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0016454134101192926,
+  "best_metric": 1.4071842432022095,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0024681201151789387,
   "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": 24.542,
       "eval_steps_per_second": 12.271,
       "step": 20
+    },
+    {
+      "epoch": 0.001727684080625257,
+      "grad_norm": 3.4575071334838867,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 6.1962,
+      "step": 21
+    },
+    {
+      "epoch": 0.001974496092143151,
+      "grad_norm": 2.291224479675293,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 5.9208,
+      "step": 24
+    },
+    {
+      "epoch": 0.0020567667626491155,
+      "eval_loss": 1.4084250926971436,
+      "eval_runtime": 208.4803,
+      "eval_samples_per_second": 24.549,
+      "eval_steps_per_second": 12.275,
+      "step": 25
+    },
+    {
+      "epoch": 0.002221308103661045,
+      "grad_norm": 2.2885515689849854,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 5.5707,
+      "step": 27
+    },
+    {
+      "epoch": 0.0024681201151789387,
+      "grad_norm": 2.3244194984436035,
+      "learning_rate": 0.0,
+      "loss": 5.6968,
+      "step": 30
+    },
+    {
+      "epoch": 0.0024681201151789387,
+      "eval_loss": 1.4071842432022095,
+      "eval_runtime": 208.401,
+      "eval_samples_per_second": 24.558,
+      "eval_steps_per_second": 12.279,
+      "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": 1397348735385600.0,
+  "total_flos": 2088510475468800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null