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:e0d683097420445ae2da7ae9bd76187929932263fba955aafc473f15f6763f34
+oid sha256:a03c037eab2a960794f31859a2256f477617ebf31696bb6dfb7bb4d476bab30e
 size 65309632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1db7773a45f6e1fd92a6632c0312bbec8bb7abc442c18fbf412d506775af22b
+oid sha256:c2a0c7a1bc45aedc5ba63c6b1122c6c987722afcbd0ffc89af3eaa6b80d659eb
 size 33424212

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bd0f89b229cfeaa8b1bf1cf4a142955879943acc15ca9084fb458bceded42a4
+oid sha256:658b2b3cb1995956370e0a9bb9c53830d69e33b468560f003a97b18b010082f5
 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": 3.892979621887207,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.009285051067780872,
+  "best_metric": 3.832766532897949,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.01160631383472609,
   "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": 10.749,
       "eval_steps_per_second": 5.38,
       "step": 20
+    },
+    {
+      "epoch": 0.009749303621169917,
+      "grad_norm": 23.413921356201172,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 15.7083,
+      "step": 21
+    },
+    {
+      "epoch": 0.01021355617455896,
+      "grad_norm": 21.420833587646484,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 15.653,
+      "step": 22
+    },
+    {
+      "epoch": 0.010677808727948004,
+      "grad_norm": 23.68743896484375,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 16.02,
+      "step": 23
+    },
+    {
+      "epoch": 0.011142061281337047,
+      "grad_norm": 21.59772491455078,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 16.3291,
+      "step": 24
+    },
+    {
+      "epoch": 0.01160631383472609,
+      "grad_norm": 22.66767692565918,
+      "learning_rate": 0.0,
+      "loss": 15.0576,
+      "step": 25
+    },
+    {
+      "epoch": 0.01160631383472609,
+      "eval_loss": 3.832766532897949,
+      "eval_runtime": 84.4064,
+      "eval_samples_per_second": 10.746,
+      "eval_steps_per_second": 5.379,
+      "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": 3264956061450240.0,
+  "total_flos": 4081195076812800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null