Training in progress, step 263, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b84400837bef983cc3abec69ee1a32ef4ca5fdd992aed4368f742208087954f2
+oid sha256:df9231c70dee7e32ded47caf5663af30dde5230a32544540abb78487c1d4aedd
 size 72936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:478083457920f8c762d943d8406b493cb7eeb8a86abafa26deb6098eb89b9543
+oid sha256:6eb7bb014eba9a50dc99631309e24993cb53ef6f4400a355740166a50052dfa2
 size 151106

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53c6141d9349cbeee031d01ce56ea60718c6e315d601bf731c74a0ca690f5afb
+oid sha256:3fbc1de8416f86affe82bd96e37b50e56fc74868b9c9b5cdff5ee4416dd4d240
 size 14180

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99573f786b471698147a90bca9832c01f3a6051546b34cf62733f3000c01a587
+oid sha256:ce50c1db2e1ed1848dbc95405ff8f729fea88553cef218c8a2f3ff7b61aead36
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 12.254945755004883,
   "best_model_checkpoint": "miner_id_24/checkpoint-250",
-  "epoch": 0.9505703422053232,
+  "epoch": 1.0,
   "eval_steps": 50,
-  "global_step": 250,
+  "global_step": 263,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,13 @@
       "eval_samples_per_second": 151.566,
       "eval_steps_per_second": 38.233,
       "step": 250
+    },
+    {
+      "epoch": 0.9885931558935361,
+      "grad_norm": 0.38638147711753845,
+      "learning_rate": 1.0277121540277156e-07,
+      "loss": 12.2669,
+      "step": 260
     }
   ],
   "logging_steps": 10,
@@ -253,12 +260,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 120520704000.0,
+  "total_flos": 126787780608.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null