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:dc7fa99fdd4d6c31b329b1be72e788d9f167967026cbccc1742776961f71112f
+oid sha256:28c7aeb305f1ac8ea2fd2e9626cb45972aac4cad39c1728eabe8b215615bb3a6
 size 25192592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64d74fbd491a79b79033eee61686b1179a70c12150e1a47c3de6fcd6d9a0f974
+oid sha256:bf512c082f6212f136aed2666ad838ad370e37669102ff9a69564e3fc7d8f656
 size 13005370

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50200231444aa1f757768f96ac0fd114116e02d48b0d3a0cea9fc67de5069f9f
+oid sha256:aa1f2260c462dc772db3036234a699826ee3ef0ec54bbcfae11eb4c0b7694f99
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23d0c4fcd75282d05c3ecf542229a263cdfdea966c314071913c5dc6faf85a25
+oid sha256:ddd16399db35d8a29f2ca6eadbdcd4462c58bf5886d5df4eb74f5a14652bb30c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.874143123626709,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.004344593877019029,
+  "best_metric": 2.872375965118408,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.004827326530021144,
   "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": 72.329,
       "eval_steps_per_second": 18.082,
       "step": 450
+    },
+    {
+      "epoch": 0.004441140407619453,
+      "grad_norm": 12.285646438598633,
+      "learning_rate": 3.990045318353154e-06,
+      "loss": 5.1388,
+      "step": 460
+    },
+    {
+      "epoch": 0.004537686938219875,
+      "grad_norm": 9.6546049118042,
+      "learning_rate": 2.250797124418014e-06,
+      "loss": 5.3243,
+      "step": 470
+    },
+    {
+      "epoch": 0.004634233468820298,
+      "grad_norm": 15.964618682861328,
+      "learning_rate": 1.0023889196182526e-06,
+      "loss": 5.4568,
+      "step": 480
+    },
+    {
+      "epoch": 0.004730779999420721,
+      "grad_norm": 16.29486656188965,
+      "learning_rate": 2.5090282323810766e-07,
+      "loss": 6.1612,
+      "step": 490
+    },
+    {
+      "epoch": 0.004827326530021144,
+      "grad_norm": 21.052181243896484,
+      "learning_rate": 0.0,
+      "loss": 6.7968,
+      "step": 500
+    },
+    {
+      "epoch": 0.004827326530021144,
+      "eval_loss": 2.872375965118408,
+      "eval_runtime": 592.4933,
+      "eval_samples_per_second": 73.608,
+      "eval_steps_per_second": 18.402,
+      "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": 4610936480464896.0,
+  "total_flos": 5128671190843392.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null