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:c599eec3e2e158bb22b90b8ca7fc28b7e89fa1edb4cb73a7555aed4001f78da4
+oid sha256:b6de030889757cb85e38c9a0c484ededc0c8f07287cf017670315d2da5e8f546
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48e8fca09612b417f7ce5de0d36e9d59045a45b7e081fe350f8de61053ef203f
+oid sha256:671b428a59d6ecf8d3eaf9d72a95da9a28f29c6a64efdfdac670294896861042
 size 323193274

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:579ff65084d5a6871003b5c72f1a43b2cea20c2b1f5e6527c949a1614e979453
+oid sha256:3ddecedc509ac6227f365f0e2119c635034fa95b81c35efb0dbceaef191dcbd3
 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": 1.4095332622528076,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.003711952487008166,
+  "best_metric": 1.3942714929580688,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.005567928730512249,
   "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": 5.946,
       "eval_steps_per_second": 2.974,
       "step": 20
+    },
+    {
+      "epoch": 0.0038975501113585748,
+      "grad_norm": 0.403789758682251,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 1.0619,
+      "step": 21
+    },
+    {
+      "epoch": 0.004454342984409799,
+      "grad_norm": 0.28407254815101624,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.1882,
+      "step": 24
+    },
+    {
+      "epoch": 0.0046399406087602076,
+      "eval_loss": 1.396458625793457,
+      "eval_runtime": 381.5216,
+      "eval_samples_per_second": 5.947,
+      "eval_steps_per_second": 2.975,
+      "step": 25
+    },
+    {
+      "epoch": 0.005011135857461025,
+      "grad_norm": 0.2439851015806198,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 1.2485,
+      "step": 27
+    },
+    {
+      "epoch": 0.005567928730512249,
+      "grad_norm": 0.2325333207845688,
+      "learning_rate": 0.0,
+      "loss": 0.9855,
+      "step": 30
+    },
+    {
+      "epoch": 0.005567928730512249,
+      "eval_loss": 1.3942714929580688,
+      "eval_runtime": 381.464,
+      "eval_samples_per_second": 5.948,
+      "eval_steps_per_second": 2.975,
+      "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": 9961301379907584.0,
+  "total_flos": 1.4941952069861376e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null