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:e3f120b96979ecbb2ca038d76f01539382bfef121d55fce8b965e9f11e7b6adf
+oid sha256:38bb8f763494cc7b878f66a0695afc57f6fde0a168b6689fff931ab736c70d4c
 size 25192592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2aedc89e7f839d56459df77848d3ab8accc99e8a3bac67a82a8197eba138bd37
+oid sha256:9f0de629111c8847d0f2a06e1a91ac5905bc0a34e0bba49fbb052f73de38bb77
 size 50493050

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e05c2f00b16264c1b9737259d7063bd2c3b44593871532775599fff8027b07aa
+oid sha256:5902dbaf7c98bf2b69a3093c16dd77f00b9dacb433cca2e7c08b0273e8d347a5
 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": 1.32905113697052,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.00909194226616661,
+  "best_metric": 1.1657742261886597,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.013637913399249914,
   "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": 50.317,
       "eval_steps_per_second": 25.186,
       "step": 20
+    },
+    {
+      "epoch": 0.00954653937947494,
+      "grad_norm": 73.37672424316406,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 5.3644,
+      "step": 21
+    },
+    {
+      "epoch": 0.010910330719399931,
+      "grad_norm": 99.907470703125,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 5.429,
+      "step": 24
+    },
+    {
+      "epoch": 0.011364927832708262,
+      "eval_loss": 1.1906145811080933,
+      "eval_runtime": 18.3446,
+      "eval_samples_per_second": 50.533,
+      "eval_steps_per_second": 25.294,
+      "step": 25
+    },
+    {
+      "epoch": 0.012274122059324924,
+      "grad_norm": 113.60340118408203,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 4.7822,
+      "step": 27
+    },
+    {
+      "epoch": 0.013637913399249914,
+      "grad_norm": 84.72586059570312,
+      "learning_rate": 0.0,
+      "loss": 5.0929,
+      "step": 30
+    },
+    {
+      "epoch": 0.013637913399249914,
+      "eval_loss": 1.1657742261886597,
+      "eval_runtime": 18.4659,
+      "eval_samples_per_second": 50.201,
+      "eval_steps_per_second": 25.127,
+      "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": 354006639575040.0,
+  "total_flos": 531009959362560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null