Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a42ebfb2242bf6b2c0bb0eb787c3c54aef9268f7500ce931f3ab389208c620b
+oid sha256:b2fe3ce425faa0c58da0d545e734ea7ad8f77a59263d3cdbe811ffb25904cb31
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe572073872d1d3dd4747b2a41559a10bd0048703f86f3d7a9eb2bbf7df57937
+oid sha256:f7c084c95a04a3c58643705f24cfa2657ec404294053246597bb62304c370a90
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7c1700cb1f556e4bf9f478fe45a08f379817072e65ab986da440073e77a1831
+oid sha256:7f1ba1951f9260d22b2b5a3e32e31cc9e7e3c391338cd8a39ce870b488f4d0b7
 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": 1.2140933275222778,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.004847309743092583,
+  "best_metric": 1.1935049295425415,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.007270964614638876,
   "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": 2.621,
       "eval_steps_per_second": 1.311,
       "step": 20
+    },
+    {
+      "epoch": 0.005089675230247213,
+      "grad_norm": 0.8807026743888855,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 4.7322,
+      "step": 21
+    },
+    {
+      "epoch": 0.0058167716917111,
+      "grad_norm": 0.8174957036972046,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 4.7154,
+      "step": 24
+    },
+    {
+      "epoch": 0.0060591371788657295,
+      "eval_loss": 1.1966049671173096,
+      "eval_runtime": 661.7771,
+      "eval_samples_per_second": 2.626,
+      "eval_steps_per_second": 1.313,
+      "step": 25
+    },
+    {
+      "epoch": 0.006543868153174988,
+      "grad_norm": 0.7282043695449829,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 4.802,
+      "step": 27
+    },
+    {
+      "epoch": 0.007270964614638876,
+      "grad_norm": 0.7617349028587341,
+      "learning_rate": 0.0,
+      "loss": 4.8155,
+      "step": 30
+    },
+    {
+      "epoch": 0.007270964614638876,
+      "eval_loss": 1.1935049295425415,
+      "eval_runtime": 662.4667,
+      "eval_samples_per_second": 2.624,
+      "eval_steps_per_second": 1.312,
+      "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": 2.5391158788096e+16,
+  "total_flos": 3.8086738182144e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null