Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7752f69ba164a2570104c7fb0fa3f28f9beccfe2f304f092bd4015e8114bfda9
+oid sha256:838d6a35106037bb66ec960d2247a89a54cf34f6755b7b51359a070995db3986
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09f475de03b5c500b27ca92275afb841fd65404e0ed532175e8b280d1536aed1
+oid sha256:90e69a26bed78f20ea4653c49b2301d2785632aff0e91dad4900895081a07240
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d12592dc3aba6f81c74b84c11bf1d2b97d0ccb6eabb8c5c9a092116682e65a0e
+oid sha256:311d5fee5221d888b18de931f211a2a40b7e63eb5412718f59049a35c2d9f4b6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2eb657255baf6b1420bbcfab19529abd45c6011f0c415bddb3c278a51f7f142
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.098618268966675,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.02735042735042735,
+  "best_metric": 2.083953619003296,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.041025641025641026,
   "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": 3.477,
       "eval_steps_per_second": 0.869,
       "step": 20
+    },
+    {
+      "epoch": 0.028717948717948718,
+      "grad_norm": 0.4366650879383087,
+      "learning_rate": 2.8711035421746367e-05,
+      "loss": 2.0629,
+      "step": 21
+    },
+    {
+      "epoch": 0.03282051282051282,
+      "grad_norm": 0.3760336637496948,
+      "learning_rate": 1.3551568628929434e-05,
+      "loss": 2.1286,
+      "step": 24
+    },
+    {
+      "epoch": 0.03418803418803419,
+      "eval_loss": 2.0853018760681152,
+      "eval_runtime": 177.7083,
+      "eval_samples_per_second": 3.466,
+      "eval_steps_per_second": 0.867,
+      "step": 25
+    },
+    {
+      "epoch": 0.036923076923076927,
+      "grad_norm": 0.4071442484855652,
+      "learning_rate": 3.511175705587433e-06,
+      "loss": 2.1581,
+      "step": 27
+    },
+    {
+      "epoch": 0.041025641025641026,
+      "grad_norm": 0.39064133167266846,
+      "learning_rate": 0.0,
+      "loss": 2.1107,
+      "step": 30
+    },
+    {
+      "epoch": 0.041025641025641026,
+      "eval_loss": 2.083953619003296,
+      "eval_runtime": 177.7311,
+      "eval_samples_per_second": 3.466,
+      "eval_steps_per_second": 0.866,
+      "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": 2.967549134241792e+16,
+  "total_flos": 4.451323701362688e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null