Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea86a1ab6262ea640f9a6d27090edfc246f6a07418b281494f642460d00ec911
+oid sha256:982fcee59ec684574e54f8db6d982cdae0847ab546bb74de7c18599d04455922
 size 912336848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5baf2d64b3bfddde66c4fa2491255f53466e62972b130ea8a5398d69578308f3
+oid sha256:17820da8e21068c65acfc2c91ef6e07e39666c3454e42ee4de2ec1100e52b14e
 size 463916180

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc9d3500674a5c3e1216d67d490fdf1ccc5b42aab24568cc2d025e555b1470e4
+oid sha256:0a54508f9777a908cec330dbc41708af3eb66e01380aaf01f3bf181ea0b00d5f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4c9c807f0681c8b7e53ada9b6ec3dba530d303de7da0d0a0562a3d8d0bbba08
+oid sha256:d2d754412c61116546142914503e7369d0cc35d3c380a07e5218f595d76b6d96
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8167033791542053,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.05697464628240433,
+  "best_metric": 0.7954394221305847,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.07596619504320577,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 9.447,
       "eval_steps_per_second": 2.363,
       "step": 150
+    },
+    {
+      "epoch": 0.06077295603456462,
+      "grad_norm": 8.532111167907715,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 3.3664,
+      "step": 160
+    },
+    {
+      "epoch": 0.06457126578672491,
+      "grad_norm": 15.966036796569824,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 3.0575,
+      "step": 170
+    },
+    {
+      "epoch": 0.0683695755388852,
+      "grad_norm": 16.28304100036621,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 3.0103,
+      "step": 180
+    },
+    {
+      "epoch": 0.07216788529104548,
+      "grad_norm": 19.59560775756836,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 3.1984,
+      "step": 190
+    },
+    {
+      "epoch": 0.07596619504320577,
+      "grad_norm": 23.846603393554688,
+      "learning_rate": 0.0,
+      "loss": 3.4317,
+      "step": 200
+    },
+    {
+      "epoch": 0.07596619504320577,
+      "eval_loss": 0.7954394221305847,
+      "eval_runtime": 469.4851,
+      "eval_samples_per_second": 9.444,
+      "eval_steps_per_second": 2.362,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -167,12 +210,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.48136509800448e+17,
+  "total_flos": 4.64182013067264e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null