Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91955e477c9ca63caa14865cd6c62a84188e8928b79933a789e8e107274f6443
+oid sha256:c60457995b8bae5cbd031f6b4968ba5138f3d78d19fefb83027412365e75fa5d
 size 500770656

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb22f5bf5261377b1a42d542325cf48ee17b83ea139c492c0b7c5b41d2596f52
+oid sha256:c01decca5c5d5086c5bd4cdd9fa989490fd5f8d5c8434e984f8670a69d659489
 size 1001863522

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16c538c078d83dbf6cf3c6d6bd8188385c51ad5064a76a0e84667fabbabbfb32
+oid sha256:686fd977141d9497b4b7d610848f79990922885d881b3bc51f568386eae09821
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f50d49fdfe63be1a533c8a8b77ebcc1cfa26fd897cf9d767a2654c8254d75a51
+oid sha256:a4f4a4f19839d4ac059bd99301c20c6cedb7bdb9b34cf5db3e653716cce56c68
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fb5f2d394082a0f2cd42d9567d531e38346401bd99eb2281ef273f26eb9b99e
+oid sha256:bbbc56ffbe20e14b7e5728d7ff4cf04a3131167d058005bea2159844384db5ff
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2b10f2f39dc03a608fc845274e3dcf65371a18e2dd6f40d9ec92de411b1247d
+oid sha256:d6e31d2d9166ff6b3701e804ceb2637a80a75485637b9f8a34548a4a0c552f18
 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": 1.1426749229431152,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.2805049088359046,
+  "best_metric": 1.129067301750183,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.5610098176718092,
   "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": 14.705,
       "eval_steps_per_second": 1.86,
       "step": 25
+    },
+    {
+      "epoch": 0.2917251051893408,
+      "grad_norm": 6.840883255004883,
+      "learning_rate": 5e-05,
+      "loss": 1.1596,
+      "step": 26
+    },
+    {
+      "epoch": 0.302945301542777,
+      "grad_norm": 11.515652656555176,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.1579,
+      "step": 27
+    },
+    {
+      "epoch": 0.3141654978962132,
+      "grad_norm": 9.219208717346191,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.1314,
+      "step": 28
+    },
+    {
+      "epoch": 0.32538569424964936,
+      "grad_norm": 6.959238052368164,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.1417,
+      "step": 29
+    },
+    {
+      "epoch": 0.33660589060308554,
+      "grad_norm": 9.272762298583984,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.165,
+      "step": 30
+    },
+    {
+      "epoch": 0.34782608695652173,
+      "grad_norm": 5.884149074554443,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.1467,
+      "step": 31
+    },
+    {
+      "epoch": 0.3590462833099579,
+      "grad_norm": 7.155044078826904,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.1392,
+      "step": 32
+    },
+    {
+      "epoch": 0.3702664796633941,
+      "grad_norm": 7.817929744720459,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.1468,
+      "step": 33
+    },
+    {
+      "epoch": 0.3814866760168303,
+      "grad_norm": 5.918971538543701,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.1328,
+      "step": 34
+    },
+    {
+      "epoch": 0.39270687237026647,
+      "grad_norm": 5.975762844085693,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.1179,
+      "step": 35
+    },
+    {
+      "epoch": 0.40392706872370265,
+      "grad_norm": 6.991667747497559,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.1391,
+      "step": 36
+    },
+    {
+      "epoch": 0.41514726507713884,
+      "grad_norm": 6.5501322746276855,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.0932,
+      "step": 37
+    },
+    {
+      "epoch": 0.426367461430575,
+      "grad_norm": 7.059451580047607,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.1087,
+      "step": 38
+    },
+    {
+      "epoch": 0.4375876577840112,
+      "grad_norm": 6.76327657699585,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.1367,
+      "step": 39
+    },
+    {
+      "epoch": 0.4488078541374474,
+      "grad_norm": 5.15268611907959,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.1455,
+      "step": 40
+    },
+    {
+      "epoch": 0.4600280504908836,
+      "grad_norm": 7.797684669494629,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.1518,
+      "step": 41
+    },
+    {
+      "epoch": 0.47124824684431976,
+      "grad_norm": 6.6517205238342285,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.1512,
+      "step": 42
+    },
+    {
+      "epoch": 0.48246844319775595,
+      "grad_norm": 4.980301380157471,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.1459,
+      "step": 43
+    },
+    {
+      "epoch": 0.49368863955119213,
+      "grad_norm": 5.792754173278809,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.148,
+      "step": 44
+    },
+    {
+      "epoch": 0.5049088359046283,
+      "grad_norm": 4.484447956085205,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.1291,
+      "step": 45
+    },
+    {
+      "epoch": 0.5161290322580645,
+      "grad_norm": 6.743837833404541,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.1486,
+      "step": 46
+    },
+    {
+      "epoch": 0.5273492286115007,
+      "grad_norm": 6.317599296569824,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.1474,
+      "step": 47
+    },
+    {
+      "epoch": 0.5385694249649369,
+      "grad_norm": 6.558826446533203,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.137,
+      "step": 48
+    },
+    {
+      "epoch": 0.5497896213183731,
+      "grad_norm": 5.561692237854004,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.126,
+      "step": 49
+    },
+    {
+      "epoch": 0.5610098176718092,
+      "grad_norm": 6.571597099304199,
+      "learning_rate": 0.0,
+      "loss": 0.9847,
+      "step": 50
+    },
+    {
+      "epoch": 0.5610098176718092,
+      "eval_loss": 1.129067301750183,
+      "eval_runtime": 40.8822,
+      "eval_samples_per_second": 14.701,
+      "eval_steps_per_second": 1.859,
+      "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": 5.102874266697728e+17,
+  "total_flos": 1.0205748533395456e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null