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:ec239a543312836241297d29efd4a6407634fb337ee1d859fdd346e6b1289bf6
+oid sha256:fd63c042714eb04d59a3b74a33a7c825e95dfafc493262408c8f989ce7311961
 size 5327744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee12e64235107a4b43a6ebec38327d6a7440bedd1893df3bf114c38941433953
+oid sha256:43ce788b988c1551f93ca0105dea8270026b5e2d332f35a9a8b89a0846201f02
 size 2857722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc846304558ae6b579eb3f62d9546198fad593f46ad20907d5f0712dc3f01eb3
+oid sha256:489873e7fa320f2b96afb2772784c05b78b89350364dca8a6d957e503e22fafe
 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": 3.0219674110412598,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0014698046997005272,
+  "best_metric": 3.0045323371887207,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.001837255874625659,
   "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": 24.823,
       "eval_steps_per_second": 12.412,
       "step": 20
+    },
+    {
+      "epoch": 0.0015432949346855537,
+      "grad_norm": 8.05355453491211,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 12.4798,
+      "step": 21
+    },
+    {
+      "epoch": 0.00161678516967058,
+      "grad_norm": 7.80503511428833,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 12.0225,
+      "step": 22
+    },
+    {
+      "epoch": 0.0016902754046556063,
+      "grad_norm": 7.3944621086120605,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 12.1289,
+      "step": 23
+    },
+    {
+      "epoch": 0.0017637656396406328,
+      "grad_norm": 6.86484956741333,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 12.3028,
+      "step": 24
+    },
+    {
+      "epoch": 0.001837255874625659,
+      "grad_norm": 7.060364723205566,
+      "learning_rate": 0.0,
+      "loss": 12.4101,
+      "step": 25
+    },
+    {
+      "epoch": 0.001837255874625659,
+      "eval_loss": 3.0045323371887207,
+      "eval_runtime": 226.9661,
+      "eval_samples_per_second": 25.246,
+      "eval_steps_per_second": 12.623,
+      "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": 42459023278080.0,
+  "total_flos": 53073779097600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null