Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84b8a6e310b29f09abb36a63e8e0a4c35058a03cba4428a815fb0a25eda88030
+oid sha256:452efa01b77b5655a3091b1425a50e1a51617dc98cf69fe25f11bf9d44f80eec
 size 186962

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c81a512b898df4f16c20dc3b22c0139d5f9744db8fe17b4fabfedf6b9255bfe2
+oid sha256:2c985da3587da3da04c790a55956477d2551082d213808e185be4ab210c876eb
 size 121430

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1157e5240c426b56ee3086073367cf94075ef91e634b2ce849609c4e659f5b09
+oid sha256:26aa772fd222893eb87d8088c750edc7689d5c071c52f9e205babb837651e5ba
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6da9db9fb6671f70d2a4e7001f6523f325b24520bef80a5a7ba3fc8703a924b
+oid sha256:d1acf7518eaa83a30405413555139e93a2eb8b9085597afc9a51f69cd1ccf771
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 6.933520317077637,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.003771805752003772,
+  "best_metric": 6.9331231117248535,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.005657708628005658,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 592.144,
       "eval_steps_per_second": 148.102,
       "step": 20
+    },
+    {
+      "epoch": 0.0039603960396039604,
+      "grad_norm": 0.1168089509010315,
+      "learning_rate": 1.4355517710873184e-05,
+      "loss": 6.9334,
+      "step": 21
+    },
+    {
+      "epoch": 0.004526166902404526,
+      "grad_norm": 0.1270003467798233,
+      "learning_rate": 6.775784314464717e-06,
+      "loss": 6.9332,
+      "step": 24
+    },
+    {
+      "epoch": 0.004714757190004715,
+      "eval_loss": 6.933193683624268,
+      "eval_runtime": 7.4833,
+      "eval_samples_per_second": 596.797,
+      "eval_steps_per_second": 149.266,
+      "step": 25
+    },
+    {
+      "epoch": 0.005091937765205092,
+      "grad_norm": 0.1317366510629654,
+      "learning_rate": 1.7555878527937164e-06,
+      "loss": 6.9339,
+      "step": 27
+    },
+    {
+      "epoch": 0.005657708628005658,
+      "grad_norm": 0.12219498306512833,
+      "learning_rate": 0.0,
+      "loss": 6.9338,
+      "step": 30
+    },
+    {
+      "epoch": 0.005657708628005658,
+      "eval_loss": 6.9331231117248535,
+      "eval_runtime": 7.463,
+      "eval_samples_per_second": 598.419,
+      "eval_steps_per_second": 149.672,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 138486202368.0,
+  "total_flos": 197416501248.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null