Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79aaf981f5ff45f8751bd3a98b389e4b8f1c527071ff57cb570174486153d73c
+oid sha256:7949efa3e56346bf812246f6aef825d49070d70fd99063c3390a049d06861ad2
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:811bc5646c521eaa3ae5450ac22520b725f6122c7a7e5151134478d679368a0c
+oid sha256:4f6235243e2b92e447236f2cd85f12e6b78f8d20ae5938d0c2d2b37fe829ce5b
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e31e0fdb3869a241061ca27b64da9fbd0a58f71586f852b6544558cc627e89db
+oid sha256:4f6c5bab6ae8774aeebffa8dddc975bf72a5f3fd3457a6b6abec6d7fbf0e1997
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
+oid sha256:4521b8db9cc205e54aa606d85e707c024abd2d8ad4a20bec4b2cff365dc59cdf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3214565515518188,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.05273566249176005,
+  "best_metric": 1.3085263967514038,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.06591957811470006,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,49 @@
       "eval_samples_per_second": 2.531,
       "eval_steps_per_second": 1.265,
       "step": 20
+    },
+    {
+      "epoch": 0.055372445616348055,
+      "grad_norm": 1.0872224569320679,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 1.2648,
+      "step": 21
+    },
+    {
+      "epoch": 0.05800922874093606,
+      "grad_norm": 1.3703272342681885,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.4033,
+      "step": 22
+    },
+    {
+      "epoch": 0.06064601186552406,
+      "grad_norm": 1.1510192155838013,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 1.5813,
+      "step": 23
+    },
+    {
+      "epoch": 0.06328279499011207,
+      "grad_norm": 1.166670560836792,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 1.4211,
+      "step": 24
+    },
+    {
+      "epoch": 0.06591957811470006,
+      "grad_norm": 1.470617651939392,
+      "learning_rate": 0.0,
+      "loss": 1.4893,
+      "step": 25
+    },
+    {
+      "epoch": 0.06591957811470006,
+      "eval_loss": 1.3085263967514038,
+      "eval_runtime": 63.0894,
+      "eval_samples_per_second": 2.536,
+      "eval_steps_per_second": 1.268,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -210,12 +253,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7644365665075200.0,
+  "total_flos": 9555457081344000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null