Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84ee1b0ac9ad0ca6318d6967002836198c69dd66feb7af701ab451677e3ad384
+oid sha256:d0c086fb9264961d3a332b1d63665049178214be294f7de703b0a9eb0a6df7ca
 size 2373352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad363297650ab1ab75083b40156ec7439de76c88391ac8ea95c883bf55eec2ed
+oid sha256:bf82cc68a85abe06e9d1b3309f370d93229b046d81b4a78d40e3cfbc6fdd198e
 size 4830970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5344459ca9c9bca6903522a0168137fc555a29918568ef23b9caea9ed33a3023
+oid sha256:cbb3880ad52205ec08013a458855f70540eb3a06537201e25b36f566881a14b3
 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": 11.485980987548828,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.017502236396872935,
+  "best_metric": 11.485908508300781,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.019446929329858816,
   "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": 72.577,
       "eval_steps_per_second": 18.148,
       "step": 450
+    },
+    {
+      "epoch": 0.01789117498347011,
+      "grad_norm": 0.15914027392864227,
+      "learning_rate": 3.931937862260632e-06,
+      "loss": 11.4254,
+      "step": 460
+    },
+    {
+      "epoch": 0.018280113570067286,
+      "grad_norm": 0.15812014043331146,
+      "learning_rate": 2.2180185255187225e-06,
+      "loss": 11.4253,
+      "step": 470
+    },
+    {
+      "epoch": 0.01866905215666446,
+      "grad_norm": 0.5148617625236511,
+      "learning_rate": 9.877910227306082e-07,
+      "loss": 11.4479,
+      "step": 480
+    },
+    {
+      "epoch": 0.01905799074326164,
+      "grad_norm": 0.4983697235584259,
+      "learning_rate": 2.472488986278439e-07,
+      "loss": 11.5441,
+      "step": 490
+    },
+    {
+      "epoch": 0.019446929329858816,
+      "grad_norm": 1.8472503423690796,
+      "learning_rate": 0.0,
+      "loss": 11.5952,
+      "step": 500
+    },
+    {
+      "epoch": 0.019446929329858816,
+      "eval_loss": 11.485908508300781,
+      "eval_runtime": 149.1843,
+      "eval_samples_per_second": 72.568,
+      "eval_steps_per_second": 18.145,
+      "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": 61975756800000.0,
+  "total_flos": 68861952000000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null