Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cfca774e0e4b15eb3d5db468fb58dba8558863d5dd85202fa6b18e632f5362b
+oid sha256:6201c0d2062da39659f919c8acdb18b2ed3803245ffdbf6961026d6a28f309ef
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3ec5e7c7a66f68d52640ed1ec2601d9ee9952d803f4403489599063c3e13fdf
+oid sha256:cbc052aafca7cb6434fe9702c6f6bec029c7a3d4fab066302bd49ef3a24adddb
 size 42608772

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b3f655ff85d03725f60fb2deecc05d59c493267c3f8f6447c5180c7397f52dc
+oid sha256:aeeeddb71155c9c73ba3399b6c46dff1d8bc3e982a6ca87630a445174ecbcf48
 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": 1.1311696767807007,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.3487020534676482,
+  "best_metric": 1.1309583187103271,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.38744672607516467,
   "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": 28.065,
       "eval_steps_per_second": 7.016,
       "step": 450
+    },
+    {
+      "epoch": 0.3564509879891515,
+      "grad_norm": 1.141700267791748,
+      "learning_rate": 3.931937862260632e-06,
+      "loss": 1.0473,
+      "step": 460
+    },
+    {
+      "epoch": 0.3641999225106548,
+      "grad_norm": 1.412896752357483,
+      "learning_rate": 2.2180185255187225e-06,
+      "loss": 1.0821,
+      "step": 470
+    },
+    {
+      "epoch": 0.3719488570321581,
+      "grad_norm": 1.5113487243652344,
+      "learning_rate": 9.877910227306082e-07,
+      "loss": 1.112,
+      "step": 480
+    },
+    {
+      "epoch": 0.37969779155366135,
+      "grad_norm": 1.848333477973938,
+      "learning_rate": 2.472488986278439e-07,
+      "loss": 1.203,
+      "step": 490
+    },
+    {
+      "epoch": 0.38744672607516467,
+      "grad_norm": 2.7838962078094482,
+      "learning_rate": 0.0,
+      "loss": 1.0458,
+      "step": 500
+    },
+    {
+      "epoch": 0.38744672607516467,
+      "eval_loss": 1.1309583187103271,
+      "eval_runtime": 19.576,
+      "eval_samples_per_second": 27.789,
+      "eval_steps_per_second": 6.947,
+      "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": 2.344858262647603e+16,
+  "total_flos": 2.6037225724575744e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null