Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e997fd92c23b16c1847ea0235155b01d39aed098f423b74fd9545f19368e153
+oid sha256:013a588f6ffcd5efdaa7a2bdac8c650d07b29c79b2f02522caeee80db7497ace
 size 216151256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25cb88f6d5162cab626e33cdc256ca823c234f7be9739ffcf1e08b562dad9fd1
+oid sha256:373312d809b12eb64d15d60ea98174a1f573b69c6388ece791e90ea52e15058b
 size 432640054

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac4c4d3e2a63413186fdc624383f0085bcb1896dfa4dd2647931a2a1e5d987b6
+oid sha256:2ad636d5cf633a906fc3f3ccc5e2d0efef31060640b5f5a43055356e4a3ba83f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.9803951978683472,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.002889233991837914,
+  "best_metric": 1.8989101648330688,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.004333850987756871,
   "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": 5.037,
       "eval_steps_per_second": 2.519,
       "step": 20
+    },
+    {
+      "epoch": 0.0030336956914298096,
+      "grad_norm": 1.6175708770751953,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 2.0652,
+      "step": 21
+    },
+    {
+      "epoch": 0.003467080790205497,
+      "grad_norm": 1.6678763628005981,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.9437,
+      "step": 24
+    },
+    {
+      "epoch": 0.0036115424897973925,
+      "eval_loss": 1.9103515148162842,
+      "eval_runtime": 578.7241,
+      "eval_samples_per_second": 5.037,
+      "eval_steps_per_second": 2.519,
+      "step": 25
+    },
+    {
+      "epoch": 0.003900465888981184,
+      "grad_norm": 1.599976658821106,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 2.0294,
+      "step": 27
+    },
+    {
+      "epoch": 0.004333850987756871,
+      "grad_norm": 1.5578798055648804,
+      "learning_rate": 0.0,
+      "loss": 1.9395,
+      "step": 30
+    },
+    {
+      "epoch": 0.004333850987756871,
+      "eval_loss": 1.8989101648330688,
+      "eval_runtime": 578.7233,
+      "eval_samples_per_second": 5.037,
+      "eval_steps_per_second": 2.519,
+      "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": 8236125420257280.0,
+  "total_flos": 1.235418813038592e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null