Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4812f2ca359adcaac0d16aaec75e4bc8a20f940f695dc2dd1aea9ad34c586555
+oid sha256:f5e91768308573bd2ba1d41b04621f085f0508b238bda42f49ac53b0a4df9371
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ae56c2dc4f9e1e31e0d759abbbb6772de550412525046743e885fbf667268a8
+oid sha256:1d29c805bebc0bd6a52940e4dc72ca1d753f4a97ede5fdd9f8f31b40916ef48e
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49de370ac54225c7243186cc559aced1036fab31ef98861b24fe84d7ec44bd0b
+oid sha256:83eb5cdc8dd621b9d3b7cf06b9b893f32eef10d148e5187947364f07998add5d
 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": 0.941416323184967,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.003772161448509996,
+  "best_metric": 0.9134324193000793,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.005658242172764994,
   "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": 8.037,
       "eval_steps_per_second": 4.02,
       "step": 20
+    },
+    {
+      "epoch": 0.003960769520935496,
+      "grad_norm": 7.903290271759033,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 4.116,
+      "step": 21
+    },
+    {
+      "epoch": 0.004526593738211996,
+      "grad_norm": 10.213263511657715,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 3.6046,
+      "step": 24
+    },
+    {
+      "epoch": 0.004715201810637495,
+      "eval_loss": 0.9226500391960144,
+      "eval_runtime": 277.7881,
+      "eval_samples_per_second": 8.039,
+      "eval_steps_per_second": 4.021,
+      "step": 25
+    },
+    {
+      "epoch": 0.005092417955488495,
+      "grad_norm": 9.46810531616211,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 3.6933,
+      "step": 27
+    },
+    {
+      "epoch": 0.005658242172764994,
+      "grad_norm": 10.925247192382812,
+      "learning_rate": 0.0,
+      "loss": 3.6785,
+      "step": 30
+    },
+    {
+      "epoch": 0.005658242172764994,
+      "eval_loss": 0.9134324193000793,
+      "eval_runtime": 277.7965,
+      "eval_samples_per_second": 8.038,
+      "eval_steps_per_second": 4.021,
+      "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": 7031303039877120.0,
+  "total_flos": 1.054695455981568e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null