Training in progress, step 219, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36c515db32d3d7f09379932d8af8a180603557ea1ceb0780e1597e26233f2d44
+oid sha256:a3b2678287b7c7ef4f6654abac8603d0ce7a466cab7c09e008a66b5345600e4b
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:901764707d693145d88f726ca25c4ebcf5a68f2f4445887acb0bdbb8135f4ad4
+oid sha256:bab68acaceb01f23f60015123483035808654ef4e1d525149158036836fdaf50
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4d565184f9f5cda7759630e9b34000ae1d43c3424fb3dfd30d7bf55a7baafda
+oid sha256:f0cae3ee409db3bdf9e402fd2df770d0dec0a2a308b35538b2bf87b8effeccd2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75f8713d9f688bebdbd86b1fb4350ff186e7695576b2c8da59fde7edc7e2e209
+oid sha256:cb42eaa476d66164742d8e57c54ee1c2ea541bedefcf1ea63778a36c221c9563
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7080769538879395,
   "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.6857142857142857,
+  "epoch": 1.0022857142857142,
   "eval_steps": 150,
-  "global_step": 150,
+  "global_step": 219,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -128,6 +128,48 @@
       "eval_samples_per_second": 14.012,
       "eval_steps_per_second": 3.532,
       "step": 150
+    },
+    {
+      "epoch": 0.7314285714285714,
+      "grad_norm": 3.1380746364593506,
+      "learning_rate": 2.717633947550651e-05,
+      "loss": 3.0081,
+      "step": 160
+    },
+    {
+      "epoch": 0.7771428571428571,
+      "grad_norm": 3.2932016849517822,
+      "learning_rate": 1.934730363037237e-05,
+      "loss": 3.0259,
+      "step": 170
+    },
+    {
+      "epoch": 0.8228571428571428,
+      "grad_norm": 3.7868399620056152,
+      "learning_rate": 1.257446259144494e-05,
+      "loss": 3.1174,
+      "step": 180
+    },
+    {
+      "epoch": 0.8685714285714285,
+      "grad_norm": 3.2612147331237793,
+      "learning_rate": 7.0911870039138015e-06,
+      "loss": 2.7663,
+      "step": 190
+    },
+    {
+      "epoch": 0.9142857142857143,
+      "grad_norm": 22.563203811645508,
+      "learning_rate": 3.0864131729807398e-06,
+      "loss": 1.9854,
+      "step": 200
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 3.5667941570281982,
+      "learning_rate": 6.98132917350991e-07,
+      "loss": 3.0253,
+      "step": 210
     }
   ],
   "logging_steps": 10,
@@ -151,12 +193,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.9497347872456704e+17,
+  "total_flos": 2.8530522804191232e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null