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:ad9fbbc73bba2333d187b9eb50a7c275ed607ecf4f85cb4507660887f5c0e826
+oid sha256:bdb140e5b6485528c6f26ac1809160ede1af0e8a0faf6327e99a1599d2ffa4ab
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb50967f6cfd1dfdb6a20bbc8fcac6a1fa54744246c51a78e8d654ed93c24a14
+oid sha256:f047cfc6d6269dd9710e4309b037eef75afec2b82149124e90f7e1a9074bae8b
 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": 1.760087490081787,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.015958507879513265,
+  "best_metric": 1.733582854270935,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.01994813484939158,
   "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": 6.966,
       "eval_steps_per_second": 3.483,
       "step": 20
+    },
+    {
+      "epoch": 0.016756433273488927,
+      "grad_norm": 3.524348020553589,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 1.9754,
+      "step": 21
+    },
+    {
+      "epoch": 0.017554358667464593,
+      "grad_norm": 3.734744071960449,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 2.0051,
+      "step": 22
+    },
+    {
+      "epoch": 0.018352284061440256,
+      "grad_norm": 2.849287509918213,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 1.6124,
+      "step": 23
+    },
+    {
+      "epoch": 0.019150209455415918,
+      "grad_norm": 3.2284393310546875,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 1.8731,
+      "step": 24
+    },
+    {
+      "epoch": 0.01994813484939158,
+      "grad_norm": 2.4725162982940674,
+      "learning_rate": 0.0,
+      "loss": 1.4547,
+      "step": 25
+    },
+    {
+      "epoch": 0.01994813484939158,
+      "eval_loss": 1.733582854270935,
+      "eval_runtime": 75.6746,
+      "eval_samples_per_second": 6.977,
+      "eval_steps_per_second": 3.489,
+      "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