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:c9c75f58952914e41f3fae7e70cc225100635cdf07955dbcc28d4c1ed8d9a100
+oid sha256:7e0b7d7e2f9998380d37451042e8ab27b94f3f15aa51c3211a29d1aa82565332
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:903f6dca362cc5bf772b3d657ad10beac9a1683271942864a4cfc906576366af
+oid sha256:2b9c9a9338a14faa08d78a34bf9ccf49268c47d708162795684275e7f8256cf5
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dc3e5265caade9b4765ce3bea88afed07b875a6b1b6dbe83b1b96d505d55d4b
+oid sha256:c70a576494e56c909be11c04fa488ebbe191aee3195b0dd47c32f36094b31b77
 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": 0.6068727970123291,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.023154848046309694,
+  "best_metric": 0.599331259727478,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.02894356005788712,
   "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": 6.932,
       "eval_steps_per_second": 3.466,
       "step": 20
+    },
+    {
+      "epoch": 0.02431259044862518,
+      "grad_norm": 0.9153821468353271,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.6307,
+      "step": 21
+    },
+    {
+      "epoch": 0.025470332850940667,
+      "grad_norm": 0.8894202709197998,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.6875,
+      "step": 22
+    },
+    {
+      "epoch": 0.02662807525325615,
+      "grad_norm": 0.9421468377113342,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.6768,
+      "step": 23
+    },
+    {
+      "epoch": 0.027785817655571636,
+      "grad_norm": 0.7827662229537964,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.6265,
+      "step": 24
+    },
+    {
+      "epoch": 0.02894356005788712,
+      "grad_norm": 0.6836793422698975,
+      "learning_rate": 0.0,
+      "loss": 0.5231,
+      "step": 25
+    },
+    {
+      "epoch": 0.02894356005788712,
+      "eval_loss": 0.599331259727478,
+      "eval_runtime": 52.3464,
+      "eval_samples_per_second": 6.954,
+      "eval_steps_per_second": 3.477,
+      "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": 3699128496291840.0,
+  "total_flos": 4623910620364800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null