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:dd270768c41a2ab826048c71663e00f2297e41e48c2bae61933cbbf40c8bf60a
+oid sha256:162f401fdbc4beb0e60f6aeb1d0a50131284840916d763f0d46d6c4d54b10bd3
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30148ecfbb11ba7e979068f6b960e33d7ffba1b2da010354307f03e52948683b
+oid sha256:f1550709e4c23431bbef52405141e3dd8139ecfe9cecbf6badb481ffc37f2eab
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:508e5d3280c56c65f6e278c6d068a6f3673a2febb4917f0855fdd4f288bcdb54
+oid sha256:ca82cf0c79e7b6be23232be83df7d5601efce4a1f28b01a653991f8bb8b0c410
 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": 0.18228429555892944,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.021923814743765414,
+  "best_metric": 0.17687520384788513,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.02740476842970677,
   "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": 6.01,
       "eval_steps_per_second": 3.013,
       "step": 20
+    },
+    {
+      "epoch": 0.023020005480953686,
+      "grad_norm": 1.2112597227096558,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.0757,
+      "step": 21
+    },
+    {
+      "epoch": 0.024116196218141955,
+      "grad_norm": 1.0107488632202148,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.0229,
+      "step": 22
+    },
+    {
+      "epoch": 0.025212386955330228,
+      "grad_norm": 0.845774233341217,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.1407,
+      "step": 23
+    },
+    {
+      "epoch": 0.026308577692518497,
+      "grad_norm": 0.36997902393341064,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.0443,
+      "step": 24
+    },
+    {
+      "epoch": 0.02740476842970677,
+      "grad_norm": 1.0737884044647217,
+      "learning_rate": 0.0,
+      "loss": 0.1671,
+      "step": 25
+    },
+    {
+      "epoch": 0.02740476842970677,
+      "eval_loss": 0.17687520384788513,
+      "eval_runtime": 64.0824,
+      "eval_samples_per_second": 6.008,
+      "eval_steps_per_second": 3.012,
+      "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": 5363736319623168.0,
+  "total_flos": 6658431293325312.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null