Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e13e22c22368bcb343cbe77971a47be0345fbeb2ca24a44850169222398e0fc
+oid sha256:fd5caf2248386581800ff0a1ace087820f211c97a9ce91ae902c174d38963eb9
 size 140815952

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f79b089a2c9ac6f8a1db436a7eb7af9f2f115b84624e71616d14a507601d2875
+oid sha256:ce5af1e5d0dde25c2991610a787118a128ee397124e7e22efbaf2ad634b63b98
 size 71878996

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70617e03ad082acd3f54a3db61fac6510896f0e1efd57742c6cca947f8b939d5
+oid sha256:5ae621faf5f7b7c925100a9c32375de444af97498403cf496ff28e7876269247
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30565d7b1986ad1c3966f0f9b850f0ae7d4cfe76be60a78deb1442c25c9c950e
+oid sha256:693af3889e4633c932ce337b10348752049de987b4153b6619512b489850fe7b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.9397493600845337,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.19929140832595216,
+  "best_metric": 1.936856746673584,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.22143489813994685,
   "eval_steps": 50,
-  "global_step": 450,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -402,6 +402,49 @@
       "eval_samples_per_second": 48.819,
       "eval_steps_per_second": 12.218,
       "step": 450
+    },
+    {
+      "epoch": 0.20372010628875112,
+      "grad_norm": 5.670279502868652,
+      "learning_rate": 4.028783622414835e-06,
+      "loss": 2.0925,
+      "step": 460
+    },
+    {
+      "epoch": 0.20814880425155005,
+      "grad_norm": 5.244168758392334,
+      "learning_rate": 2.272649523684208e-06,
+      "loss": 1.9074,
+      "step": 470
+    },
+    {
+      "epoch": 0.21257750221434898,
+      "grad_norm": 6.256269454956055,
+      "learning_rate": 1.0121208508766823e-06,
+      "loss": 1.9008,
+      "step": 480
+    },
+    {
+      "epoch": 0.21700620017714792,
+      "grad_norm": 4.406463623046875,
+      "learning_rate": 2.533387729782834e-07,
+      "loss": 1.8705,
+      "step": 490
+    },
+    {
+      "epoch": 0.22143489813994685,
+      "grad_norm": 4.487159729003906,
+      "learning_rate": 0.0,
+      "loss": 1.7626,
+      "step": 500
+    },
+    {
+      "epoch": 0.22143489813994685,
+      "eval_loss": 1.936856746673584,
+      "eval_runtime": 19.5548,
+      "eval_samples_per_second": 48.633,
+      "eval_steps_per_second": 12.171,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -425,12 +468,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4361762272444416.0,
+  "total_flos": 4844792424431616.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null