Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:422fc7fb1f4c1447a76adee7f22da33b4f8e1b28683c62233846136983570607
+oid sha256:3ade4531d7075e446b5abfb8f7a792db0d4b6df5e0666f155e0b2128164eaded
 size 239536272

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cf8c0d5e303fa166047eb7d23a00cf5e52e1b257d91cb9b096ed9c29ffedc54
+oid sha256:3c91282ee6496a96270d7a60827750e26dc332d312a966d76174a1552c42e83f
 size 479362682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8b405384bd19a04ca1fe24166319b32f66a94b1e90d225072a98fb1e6c19561
+oid sha256:6435782d8702461a630ed7039de82ca6f4fa951381db68d5988493c7024dfdc2
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c30329ec356368cfeb4c3e75cb12f8fdb4b7c6eac7d578b0ccdff006b8d31b3
+oid sha256:963954a55891191191423ce4d0d84fc82929708aa24af4ec4a9a26050a287127
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27fe6d7aafb7bffd082cb8ea74999cea103074fe92c2a4ac7da0f5637e5fe562
+oid sha256:b629dfc77576b629658d8fc5e34218b70f8e9e0ac46ea8ab6a6a12e6a06a08e0
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f0c7cd8e5b8eefe3f8993632bcdbd04dfd781234c37f9192312e0a5ef7d3dcb
+oid sha256:d47ec2e2c15650311877880587e142456a90b98a5f72076537a8bd4c1d2689a7
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.2630291283130646,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.05143371480005143,
+  "best_metric": 0.2118401825428009,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.10286742960010287,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 54.768,
       "eval_steps_per_second": 6.856,
       "step": 25
+    },
+    {
+      "epoch": 0.05349106339205349,
+      "grad_norm": 1.2607532739639282,
+      "learning_rate": 5e-05,
+      "loss": 0.2536,
+      "step": 26
+    },
+    {
+      "epoch": 0.05554841198405555,
+      "grad_norm": 1.7164984941482544,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.2831,
+      "step": 27
+    },
+    {
+      "epoch": 0.0576057605760576,
+      "grad_norm": 1.2234079837799072,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.2514,
+      "step": 28
+    },
+    {
+      "epoch": 0.05966310916805966,
+      "grad_norm": 1.5196576118469238,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.2487,
+      "step": 29
+    },
+    {
+      "epoch": 0.06172045776006172,
+      "grad_norm": 1.3040461540222168,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.1965,
+      "step": 30
+    },
+    {
+      "epoch": 0.06377780635206377,
+      "grad_norm": 1.2185879945755005,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.1903,
+      "step": 31
+    },
+    {
+      "epoch": 0.06583515494406583,
+      "grad_norm": 1.5354326963424683,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.2661,
+      "step": 32
+    },
+    {
+      "epoch": 0.06789250353606789,
+      "grad_norm": 1.1375501155853271,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.2333,
+      "step": 33
+    },
+    {
+      "epoch": 0.06994985212806995,
+      "grad_norm": 1.3790736198425293,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.2282,
+      "step": 34
+    },
+    {
+      "epoch": 0.07200720072007201,
+      "grad_norm": 1.3943748474121094,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.1862,
+      "step": 35
+    },
+    {
+      "epoch": 0.07406454931207407,
+      "grad_norm": 1.5339925289154053,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.1971,
+      "step": 36
+    },
+    {
+      "epoch": 0.07612189790407613,
+      "grad_norm": 1.1921143531799316,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.187,
+      "step": 37
+    },
+    {
+      "epoch": 0.07817924649607817,
+      "grad_norm": 1.4345558881759644,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.2647,
+      "step": 38
+    },
+    {
+      "epoch": 0.08023659508808023,
+      "grad_norm": 0.9180118441581726,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.188,
+      "step": 39
+    },
+    {
+      "epoch": 0.08229394368008229,
+      "grad_norm": 1.0113478899002075,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.2044,
+      "step": 40
+    },
+    {
+      "epoch": 0.08435129227208435,
+      "grad_norm": 1.0066574811935425,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.1613,
+      "step": 41
+    },
+    {
+      "epoch": 0.08640864086408641,
+      "grad_norm": 1.037188172340393,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.1469,
+      "step": 42
+    },
+    {
+      "epoch": 0.08846598945608847,
+      "grad_norm": 0.9326758980751038,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.1744,
+      "step": 43
+    },
+    {
+      "epoch": 0.09052333804809053,
+      "grad_norm": 1.1875767707824707,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.1808,
+      "step": 44
+    },
+    {
+      "epoch": 0.09258068664009259,
+      "grad_norm": 1.5260714292526245,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.2268,
+      "step": 45
+    },
+    {
+      "epoch": 0.09463803523209464,
+      "grad_norm": 1.1303261518478394,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.1575,
+      "step": 46
+    },
+    {
+      "epoch": 0.09669538382409669,
+      "grad_norm": 1.0901081562042236,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.1743,
+      "step": 47
+    },
+    {
+      "epoch": 0.09875273241609875,
+      "grad_norm": 1.070528507232666,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.1514,
+      "step": 48
+    },
+    {
+      "epoch": 0.10081008100810081,
+      "grad_norm": 1.0241568088531494,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.1777,
+      "step": 49
+    },
+    {
+      "epoch": 0.10286742960010287,
+      "grad_norm": 1.1783432960510254,
+      "learning_rate": 0.0,
+      "loss": 0.2056,
+      "step": 50
+    },
+    {
+      "epoch": 0.10286742960010287,
+      "eval_loss": 0.2118401825428009,
+      "eval_runtime": 59.7697,
+      "eval_samples_per_second": 54.794,
+      "eval_steps_per_second": 6.86,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.1153227982569472e+17,
+  "total_flos": 2.2306455965138944e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null