Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58ddf88442d5da04843508b839f5ed4cceb3e2dbac14b9e505a72a690b599e57
+oid sha256:a77dff875e119672b8c2c56d33fa2a0ea38c89c6a630dcc4ecb98c7cb3702e7d
 size 2373352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26cd9291c14ce76b27953c93368206bcfbb78567ef42628ea8446e546378252e
+oid sha256:c081ced7f7066f42bc1dd8b17d9cf5384839437d1b236b371ec1cf6ed176a60c
 size 4830970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c8a07db830191f4cfeb64cd6d1076638ef8215ce3c616b585b9197f873e4019
+oid sha256:fb4bf1363a44eccd187560fc76092f0486940298e712218e569c475deb068ecf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb0db0205cf37887636e31665ab1051856b2efe4ed0485b1a8cad32db1f6dfbb
+oid sha256:1173c3cbf86b725051d7e94252382f4f9be9dc9f6afe0d4b01afed08d5bf2028
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.4863862991333,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.017502236396872935,
+  "best_metric": 11.486281394958496,
+  "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": 72.662,
       "eval_steps_per_second": 18.169,
       "step": 450
+    },
+    {
+      "epoch": 0.01789117498347011,
+      "grad_norm": 0.17912495136260986,
+      "learning_rate": 3.9513070142914725e-06,
+      "loss": 11.4265,
+      "step": 460
+    },
+    {
+      "epoch": 0.018280113570067286,
+      "grad_norm": 0.2025713324546814,
+      "learning_rate": 2.2289447251518195e-06,
+      "loss": 11.4265,
+      "step": 470
+    },
+    {
+      "epoch": 0.01866905215666446,
+      "grad_norm": 0.41863512992858887,
+      "learning_rate": 9.92656988359823e-07,
+      "loss": 11.4487,
+      "step": 480
+    },
+    {
+      "epoch": 0.01905799074326164,
+      "grad_norm": 0.49227550625801086,
+      "learning_rate": 2.4846687349793185e-07,
+      "loss": 11.5459,
+      "step": 490
+    },
+    {
+      "epoch": 0.019446929329858816,
+      "grad_norm": 1.6223171949386597,
+      "learning_rate": 0.0,
+      "loss": 11.5967,
+      "step": 500
+    },
+    {
+      "epoch": 0.019446929329858816,
+      "eval_loss": 11.486281394958496,
+      "eval_runtime": 148.9899,
+      "eval_samples_per_second": 72.663,
+      "eval_steps_per_second": 18.169,
+      "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