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:d94b0e61ca62333c8edceaca9061be8b33191d2dd03c0f7004e3d35e6b540140
+oid sha256:76523ca8af4fbaeaa8d82795fcba9fc8adbabc8ade001cd46d462d82b46bc83f
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f79ca6da8f60adbc0310cbfd09164f9c654b0935cf02a14fcdf5f54b4f70064a
+oid sha256:e7b58c87d7b420f8fdc4414dd03b3f98c262038899112e0adabd67699fdf9ad2
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ceffdaae13eedb884e9296ba957ab0ae09810cd43fe18f1e2c2f24d777ddd96d
+oid sha256:b3d94d260eed754c3e2b2ecd25f807bb612a5c2fee4fddd3267416a9b6370aa0
 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": 0.8442187905311584,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.002733454060887689,
+  "best_metric": 0.8274755477905273,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.0034168175761096113,
   "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": 5.694,
       "eval_steps_per_second": 2.848,
       "step": 20
+    },
+    {
+      "epoch": 0.0028701267639320736,
+      "grad_norm": 0.7676703929901123,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.9019,
+      "step": 21
+    },
+    {
+      "epoch": 0.003006799466976458,
+      "grad_norm": 0.44339215755462646,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.7555,
+      "step": 22
+    },
+    {
+      "epoch": 0.0031434721700208425,
+      "grad_norm": 0.45984727144241333,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.6824,
+      "step": 23
+    },
+    {
+      "epoch": 0.003280144873065227,
+      "grad_norm": 0.4886281192302704,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.6757,
+      "step": 24
+    },
+    {
+      "epoch": 0.0034168175761096113,
+      "grad_norm": 0.4310750365257263,
+      "learning_rate": 0.0,
+      "loss": 0.7122,
+      "step": 25
+    },
+    {
+      "epoch": 0.0034168175761096113,
+      "eval_loss": 0.8274755477905273,
+      "eval_runtime": 539.1656,
+      "eval_samples_per_second": 5.714,
+      "eval_steps_per_second": 2.858,
+      "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": 6138140389539840.0,
+  "total_flos": 7785963312906240.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null