Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51d5d8002a67737950eb0f093c1490cbaab74a909ce93467f47f4a8cbee3ea72
+oid sha256:9bdb9001e4990b52771595d5b760b533af2f0eaa84a40552d691757c6c902745
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9d893da0aaa20dec6d65b4d1e1fe8ef4f8d8015d82810957b3c96b484a56af6
+oid sha256:023f4620597f446a4fb03821d16966940de3b64790984272ca69946f0c883921
 size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:838098534274084aacdb2c3a85c52b42144ac8c570ede5167943969e82ec5617
+oid sha256:5d8e715c2229f6312731a29d73d1e211563d7af320d1c9431139119eb4a0711d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f03fffc232f1b8a6305d6fa9076c1e1bca28e4d7666df088caa1812431cf9135
+oid sha256:b3488300cc890b0bf0becbfdd6a3cc8770e6656a66feed4ec387a72a2b445721
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.21818479895591736,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.27590435315757206,
+  "best_metric": 0.21616657078266144,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.30656039239730226,
   "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": 16.162,
       "eval_steps_per_second": 4.046,
       "step": 450
+    },
+    {
+      "epoch": 0.2820355610055181,
+      "grad_norm": 1.0270682573318481,
+      "learning_rate": 3.931937862260632e-06,
+      "loss": 0.2239,
+      "step": 460
+    },
+    {
+      "epoch": 0.28816676885346415,
+      "grad_norm": 0.9114255905151367,
+      "learning_rate": 2.2180185255187225e-06,
+      "loss": 0.2367,
+      "step": 470
+    },
+    {
+      "epoch": 0.29429797670141017,
+      "grad_norm": 0.9456692934036255,
+      "learning_rate": 9.877910227306082e-07,
+      "loss": 0.1774,
+      "step": 480
+    },
+    {
+      "epoch": 0.30042918454935624,
+      "grad_norm": 1.6775851249694824,
+      "learning_rate": 2.472488986278439e-07,
+      "loss": 0.2112,
+      "step": 490
+    },
+    {
+      "epoch": 0.30656039239730226,
+      "grad_norm": 1.8468588590621948,
+      "learning_rate": 0.0,
+      "loss": 0.2557,
+      "step": 500
+    },
+    {
+      "epoch": 0.30656039239730226,
+      "eval_loss": 0.21616657078266144,
+      "eval_runtime": 42.6269,
+      "eval_samples_per_second": 16.117,
+      "eval_steps_per_second": 4.035,
+      "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": 8.494817090312602e+16,
+  "total_flos": 9.437638077028762e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null