Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:332b79cc3067f63e50cfa170cb3307b00e70cc791a8ef25ba2df40faa3d60fb3
+oid sha256:76f54532fabc7c038bd32ff460cf9e4e1c4d1bcf0340602476ec4f2ab52831bb
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fa85ae4684dd7c5e7c52d8e14d7a7bdad6b27ba7cb8a75e2dcf93ae98f8555d
+oid sha256:86bcb5ea61f48d73f4e8a0f0952e97320f888a98ce14da800edeea6d4fe97196
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b0c5ca09b09a8398912aac840c94e7d64e8a8f07870da4149d2711081e073ed
+oid sha256:6f1b35a55e0d41404f8302b6d4b55fed87296fb66601ba659e829a8fd1e11d9d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49c77db858ba758763d2d58ba301903ec8f09c296e95b482c3deb10bf9799e80
+oid sha256:c2f65a0bb469f701cb553ba401fe2e117f19464d01e2edaeb85c0e2c00a3c476
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b55651ab8c20bd98f7aac72245ea467b490038d761dcce6a95121e5e8c18efa
+oid sha256:740f3afa2190def768adc64d079c3c11d0674d86b25664feb4b638a8bcca684d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:098c32c6e51c16b5f2d961f4e3396f08ce9641387f6608dca3e73b3e9ed463d6
+oid sha256:1c3edb212663a4c31cdf7a744b8f8b0d968d91910095c16de926c7dce44ae4ac
 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": 1.3848936557769775,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.17006802721088435,
+  "best_metric": 1.0777992010116577,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.3401360544217687,
   "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": 20.498,
       "eval_steps_per_second": 2.567,
       "step": 25
+    },
+    {
+      "epoch": 0.17687074829931973,
+      "grad_norm": 263.2676696777344,
+      "learning_rate": 5e-05,
+      "loss": 1.5215,
+      "step": 26
+    },
+    {
+      "epoch": 0.1836734693877551,
+      "grad_norm": 136.86534118652344,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.2886,
+      "step": 27
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "grad_norm": 68.25189208984375,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.2215,
+      "step": 28
+    },
+    {
+      "epoch": 0.19727891156462585,
+      "grad_norm": 53.51959228515625,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.2119,
+      "step": 29
+    },
+    {
+      "epoch": 0.20408163265306123,
+      "grad_norm": 81.20413208007812,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.2189,
+      "step": 30
+    },
+    {
+      "epoch": 0.2108843537414966,
+      "grad_norm": 87.15968322753906,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.1506,
+      "step": 31
+    },
+    {
+      "epoch": 0.21768707482993196,
+      "grad_norm": 78.61097717285156,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.1764,
+      "step": 32
+    },
+    {
+      "epoch": 0.22448979591836735,
+      "grad_norm": 69.10588836669922,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.1398,
+      "step": 33
+    },
+    {
+      "epoch": 0.23129251700680273,
+      "grad_norm": 22.39168930053711,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.0795,
+      "step": 34
+    },
+    {
+      "epoch": 0.23809523809523808,
+      "grad_norm": 42.56079864501953,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.1041,
+      "step": 35
+    },
+    {
+      "epoch": 0.24489795918367346,
+      "grad_norm": 59.99042510986328,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.1952,
+      "step": 36
+    },
+    {
+      "epoch": 0.25170068027210885,
+      "grad_norm": 25.075746536254883,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.1129,
+      "step": 37
+    },
+    {
+      "epoch": 0.2585034013605442,
+      "grad_norm": 16.67337989807129,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.1065,
+      "step": 38
+    },
+    {
+      "epoch": 0.2653061224489796,
+      "grad_norm": 21.959392547607422,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.0687,
+      "step": 39
+    },
+    {
+      "epoch": 0.272108843537415,
+      "grad_norm": 21.31378173828125,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.0832,
+      "step": 40
+    },
+    {
+      "epoch": 0.2789115646258503,
+      "grad_norm": 21.72305679321289,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.0934,
+      "step": 41
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 14.651026725769043,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.0633,
+      "step": 42
+    },
+    {
+      "epoch": 0.2925170068027211,
+      "grad_norm": 24.642000198364258,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.0877,
+      "step": 43
+    },
+    {
+      "epoch": 0.29931972789115646,
+      "grad_norm": 80.92622375488281,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.1321,
+      "step": 44
+    },
+    {
+      "epoch": 0.30612244897959184,
+      "grad_norm": 28.691543579101562,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.0745,
+      "step": 45
+    },
+    {
+      "epoch": 0.3129251700680272,
+      "grad_norm": 29.16392707824707,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.0768,
+      "step": 46
+    },
+    {
+      "epoch": 0.3197278911564626,
+      "grad_norm": 18.52094841003418,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.0671,
+      "step": 47
+    },
+    {
+      "epoch": 0.32653061224489793,
+      "grad_norm": 27.642658233642578,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.101,
+      "step": 48
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 26.79389190673828,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.1145,
+      "step": 49
+    },
+    {
+      "epoch": 0.3401360544217687,
+      "grad_norm": 35.00909423828125,
+      "learning_rate": 0.0,
+      "loss": 1.1167,
+      "step": 50
+    },
+    {
+      "epoch": 0.3401360544217687,
+      "eval_loss": 1.0777992010116577,
+      "eval_runtime": 48.3094,
+      "eval_samples_per_second": 20.493,
+      "eval_steps_per_second": 2.567,
+      "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": 2.9527798798771814e+17,
+  "total_flos": 5.889646573062717e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null