Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51ebbe267f65d74e251d940d9c6544d168c19d19c49748d3667b4b2b7c710cef
+oid sha256:d1263ce25c062033227a27b008a9cbcf8ee08cb6c828d6abc3b25a1c5d5cd1e7
 size 598799664

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63bd2c5e647bf8ab3e535bad8e9b980dd95e955ac68605c58aa850280251ebfa
+oid sha256:9251618313c6d31fcb4d51fbb8ed41a01e626f15ce28fe49bf67036334813e40
 size 167923706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ca669e357aa0e15c87e40a1da0e0ab9476977a64e76ef375c8f5d113bdeafa4
+oid sha256:30cda0b27cf6fee72b357d7d86bb3fe52cec4804e887e8f609a05a6e4fcccd62
 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": 2.5447235107421875,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.010755579456843238,
+  "best_metric": 2.458465576171875,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.016133369185264857,
   "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": 17.692,
       "eval_steps_per_second": 8.857,
       "step": 20
+    },
+    {
+      "epoch": 0.0112933584296854,
+      "grad_norm": 8.198662757873535,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 10.4708,
+      "step": 21
+    },
+    {
+      "epoch": 0.012906695348211886,
+      "grad_norm": 6.4804582595825195,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 10.4489,
+      "step": 24
+    },
+    {
+      "epoch": 0.013444474321054048,
+      "eval_loss": 2.470919132232666,
+      "eval_runtime": 44.4226,
+      "eval_samples_per_second": 17.626,
+      "eval_steps_per_second": 8.824,
+      "step": 25
+    },
+    {
+      "epoch": 0.01452003226673837,
+      "grad_norm": 8.004265785217285,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 10.1526,
+      "step": 27
+    },
+    {
+      "epoch": 0.016133369185264857,
+      "grad_norm": 6.694253444671631,
+      "learning_rate": 0.0,
+      "loss": 9.8513,
+      "step": 30
+    },
+    {
+      "epoch": 0.016133369185264857,
+      "eval_loss": 2.458465576171875,
+      "eval_runtime": 44.2895,
+      "eval_samples_per_second": 17.679,
+      "eval_steps_per_second": 8.851,
+      "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": 2622105216614400.0,
+  "total_flos": 3933157824921600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null