Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac72a611dbdd40cd22d0efc47dae14039dc8e22679dcd347abd441651f53c848
+oid sha256:37b0cc0369905f20cf7f0e96dfb580885e7367da66f9643c303d9c5a0e010ec7
 size 216151256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e93706835554a2710f8dd181f3a732d95b49b56c01d06eed448c40f3a006f1a1
+oid sha256:79a5fafa4ad32c9641ff934cd78cd2a6cf3ffdef5f60ed00ec1ce84cd00d356a
 size 432492970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e6d3d9d32f12a1efe3c64b65843add4181ba040cb939f02cd1d690662cff498
+oid sha256:a3fc27c1c4d4d4cb006159cd5ee7a8531b2eb23885d51fb91999b71bb098f625
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2eb657255baf6b1420bbcfab19529abd45c6011f0c415bddb3c278a51f7f142
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.6314613819122314,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0006452549563646336,
+  "best_metric": 2.614351987838745,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0009678824345469504,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 5.056,
       "eval_steps_per_second": 2.528,
       "step": 20
+    },
+    {
+      "epoch": 0.0006775177041828652,
+      "grad_norm": 1.0345968008041382,
+      "learning_rate": 2.8711035421746367e-05,
+      "loss": 2.4778,
+      "step": 21
+    },
+    {
+      "epoch": 0.0007743059476375603,
+      "grad_norm": 34.092132568359375,
+      "learning_rate": 1.3551568628929434e-05,
+      "loss": 2.4162,
+      "step": 24
+    },
+    {
+      "epoch": 0.0008065686954557919,
+      "eval_loss": 2.617173433303833,
+      "eval_runtime": 2582.2997,
+      "eval_samples_per_second": 5.054,
+      "eval_steps_per_second": 2.527,
+      "step": 25
+    },
+    {
+      "epoch": 0.0008710941910922553,
+      "grad_norm": 0.993025541305542,
+      "learning_rate": 3.511175705587433e-06,
+      "loss": 2.7704,
+      "step": 27
+    },
+    {
+      "epoch": 0.0009678824345469504,
+      "grad_norm": 1.1003926992416382,
+      "learning_rate": 0.0,
+      "loss": 2.5651,
+      "step": 30
+    },
+    {
+      "epoch": 0.0009678824345469504,
+      "eval_loss": 2.614351987838745,
+      "eval_runtime": 2582.0015,
+      "eval_samples_per_second": 5.055,
+      "eval_steps_per_second": 2.527,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8339076988010496.0,
+  "total_flos": 1.2457139698139136e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null