Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38cf426c06810618dad0f9354819bb9e06933be9acd519a6fd895205f2839b2a
+oid sha256:2e745e2df1c003aad7938c172cf31368baf20daab3bcbcccb253eed9005a4247
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:175a8398a6baea8e2551a8e486e53a1a58494305cc35ce2c16116a0fd33bb275
+oid sha256:5a73c3082ef075c591d7610116acbcf5df550a71e4b6768c7f5cc22fb600e224
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0fe8548f93d4d2ba2061a5ff853229d8c4fc7065f047b09d11c7fb046ff6964
+oid sha256:18a29ec56a1a3b100e718ab1b1741b5b6f32e14d241f19151030f726e86decd1
 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": 0.2597002685070038,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0012773227315546615,
+  "best_metric": 0.253146231174469,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.0015966534144433268,
   "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": 6.298,
       "eval_steps_per_second": 3.149,
       "step": 20
+    },
+    {
+      "epoch": 0.0013411888681323944,
+      "grad_norm": 0.6128504872322083,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.2518,
+      "step": 21
+    },
+    {
+      "epoch": 0.0014050550047101276,
+      "grad_norm": 0.6355711817741394,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.2522,
+      "step": 22
+    },
+    {
+      "epoch": 0.0014689211412878607,
+      "grad_norm": 0.6158922910690308,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.3557,
+      "step": 23
+    },
+    {
+      "epoch": 0.0015327872778655937,
+      "grad_norm": 0.565183162689209,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.3031,
+      "step": 24
+    },
+    {
+      "epoch": 0.0015966534144433268,
+      "grad_norm": 0.6277245283126831,
+      "learning_rate": 0.0,
+      "loss": 0.4473,
+      "step": 25
+    },
+    {
+      "epoch": 0.0015966534144433268,
+      "eval_loss": 0.253146231174469,
+      "eval_runtime": 1036.8027,
+      "eval_samples_per_second": 6.359,
+      "eval_steps_per_second": 3.18,
+      "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": 4485193301753856.0,
+  "total_flos": 5594931850641408.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null