Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fdf11626b774500ac61b9db4329ac0557b288ba30f980bde93036b4f85de094
+oid sha256:522be8925ae3abd02ebf0655c31c7b794673c49fcc8e35767f3715f98cd6b192
 size 94412008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b702dece5eca43c70775d874e6b3597152e4ba87e5e46ff44e0a74d446b65746
+oid sha256:8d4bf9473cca3400449de638536bcd1e74a2ff16584935c01770fa372515c696
 size 48260756

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53857b31065290226097899a29c43817f42b59cc1033072766ec46b6e8e362ce
+oid sha256:42036262ea4bbad26ea1e795db8adf3a0299b516fa5578996873ed26415a195d
 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": 2.3354403972625732,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.011585807385952208,
+  "best_metric": 2.3117122650146484,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.01448225923244026,
   "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": 7.177,
       "eval_steps_per_second": 3.593,
       "step": 20
+    },
+    {
+      "epoch": 0.012165097755249819,
+      "grad_norm": 4.596272945404053,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 9.8555,
+      "step": 21
+    },
+    {
+      "epoch": 0.01274438812454743,
+      "grad_norm": 6.18507194519043,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 10.8075,
+      "step": 22
+    },
+    {
+      "epoch": 0.01332367849384504,
+      "grad_norm": 3.897860288619995,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 9.3181,
+      "step": 23
+    },
+    {
+      "epoch": 0.013902968863142651,
+      "grad_norm": 4.420831680297852,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 10.5026,
+      "step": 24
+    },
+    {
+      "epoch": 0.01448225923244026,
+      "grad_norm": 4.4558892250061035,
+      "learning_rate": 0.0,
+      "loss": 10.2569,
+      "step": 25
+    },
+    {
+      "epoch": 0.01448225923244026,
+      "eval_loss": 2.3117122650146484,
+      "eval_runtime": 101.5659,
+      "eval_samples_per_second": 7.158,
+      "eval_steps_per_second": 3.584,
+      "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": 5705610716774400.0,
+  "total_flos": 7203333529927680.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null