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:c428806e093f716af8dd1515923f715ad7e92b69cb2bf0e374dff26a180e72f1
+oid sha256:efedb5e501bab55a2e8ceb46147d6db08b7cc997c5ce5c48ab8b15ed239d6af2
 size 15182728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa1fe64a0534828181806f4ef7aeb2b5d327772044f6d8b2d246d8fd7939b16b
+oid sha256:f64f6161ef45b68f727301b9fa5f8afe444401f99254404a21d2d5d37ca3cd94
 size 8075796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86d013c907ff188e94dfd0d1e7126019857ca06b44469974d820abeb40345f6f
+oid sha256:edd4a82d2448afe5207c51dd48302a25b8446a2023c187887d7e86977295bcf7
 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": 3.7121365070343018,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.011665208515602217,
+  "best_metric": 3.686284065246582,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.014581510644502771,
   "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": 4.505,
       "eval_steps_per_second": 2.259,
       "step": 20
+    },
+    {
+      "epoch": 0.012248468941382326,
+      "grad_norm": 3.9215962886810303,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 3.5542,
+      "step": 21
+    },
+    {
+      "epoch": 0.012831729367162438,
+      "grad_norm": 3.8719942569732666,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 2.9972,
+      "step": 22
+    },
+    {
+      "epoch": 0.013414989792942549,
+      "grad_norm": 2.3772614002227783,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 2.862,
+      "step": 23
+    },
+    {
+      "epoch": 0.01399825021872266,
+      "grad_norm": 3.5683820247650146,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 3.3125,
+      "step": 24
+    },
+    {
+      "epoch": 0.014581510644502771,
+      "grad_norm": 4.269540309906006,
+      "learning_rate": 0.0,
+      "loss": 4.8594,
+      "step": 25
+    },
+    {
+      "epoch": 0.014581510644502771,
+      "eval_loss": 3.686284065246582,
+      "eval_runtime": 94.1055,
+      "eval_samples_per_second": 3.836,
+      "eval_steps_per_second": 1.923,
+      "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": 76723802603520.0,
+  "total_flos": 95904753254400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null