Training in progress, step 215, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0d5c50d2c33c106ffc7bcef17abc1dc92fc784bdb2d1535a64d4f1599816a78
+oid sha256:aa31e0c04737dffe22538073d9316cfd821eaf012819b9bea8ffb3ec5fc66ca0
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0d90ab26e6308141bdfce115ed1b3807e058e705497a18f339d53ebe7b3ebf8
+oid sha256:c1d9388d3daa5d604f1c4a8d48628b8595b6d9fa1c86d0823f161fd7a7e2dce9
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b85d7929045084134b889784eef34e0e5af0f46c6e105ec53a14076a7104a7c7
+oid sha256:4e7604134df7412bdf380ef7b8c68cd1cd099787de9c8ce50697d5c0eeefe66e
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9278c25bdc7a4b8b955d6f9b199c1b4e6f130f5b3c186b613a7d94eb07a35641
+oid sha256:fba0ece0a3bd74a804614ecbef95481ef502faf660bcc53af17cae95d4eee65a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.43841221928596497,
   "best_model_checkpoint": "miner_id_24/checkpoint-200",
-  "epoch": 0.9324009324009324,
+  "epoch": 1.0023310023310024,
   "eval_steps": 50,
-  "global_step": 200,
+  "global_step": 215,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,13 @@
       "eval_samples_per_second": 13.129,
       "eval_steps_per_second": 3.318,
       "step": 200
+    },
+    {
+      "epoch": 0.9790209790209791,
+      "grad_norm": 0.7910031676292419,
+      "learning_rate": 4.777121685395759e-07,
+      "loss": 0.4308,
+      "step": 210
     }
   ],
   "logging_steps": 10,
@@ -210,12 +217,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.457160843775181e+16,
+  "total_flos": 4.789784787340493e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null