Training in progress, step 231, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef7f0fad730e3c155b2f2aae3ee105686b93e38344500d6f03063e352146d6c2
+oid sha256:9d2dfd4110ef6f56b97ef97a311a4f90dd7cc9b02c19e6a246a936057c6836ba
 size 1001465824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cf7ce1a73395df4a872b0c0488f38be5a61aa3e042055c03ecd73350a3b9ad1
+oid sha256:e7d2e65438a9fa51d83fdd509d7f1f9f5b73bf9bae72586cf781ed7e1ab88d0d
 size 509176980

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:981e3e2bf19f4f6643e7f0698ef70dc1a6211ffddfe00577b674ea1d80a40631
+oid sha256:b016dc24b5948febd7e7cce97750c4bc22492b4553a4b7d0e3fa79930c2e73fe
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85ccddf9762e997dae2c9521506b8bc72930af80f87f56267232033157400544
+oid sha256:06066a3a83d769b381a5a7e399768bea015088ea4ce309b1d881347f13e443b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.6297968626022339,
   "best_model_checkpoint": "miner_id_24/checkpoint-200",
-  "epoch": 0.8676789587852495,
+  "epoch": 1.002169197396963,
   "eval_steps": 50,
-  "global_step": 200,
+  "global_step": 231,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,27 @@
       "eval_samples_per_second": 10.642,
       "eval_steps_per_second": 2.715,
       "step": 200
+    },
+    {
+      "epoch": 0.911062906724512,
+      "grad_norm": 0.8719707131385803,
+      "learning_rate": 6.8980594795698644e-06,
+      "loss": 1.3979,
+      "step": 210
+    },
+    {
+      "epoch": 0.9544468546637744,
+      "grad_norm": 0.9977815747261047,
+      "learning_rate": 1.907952711130355e-06,
+      "loss": 1.4726,
+      "step": 220
+    },
+    {
+      "epoch": 0.9978308026030369,
+      "grad_norm": 2.6150546073913574,
+      "learning_rate": 1.5815793867467453e-08,
+      "loss": 1.8101,
+      "step": 230
     }
   ],
   "logging_steps": 10,
@@ -210,12 +231,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6.68158072455168e+16,
+  "total_flos": 7.724068319526912e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null