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:c4f0a4dd4f253c2ae7629379c8259ac775b1c79f25c0c7fab527f16dedc5c132
+oid sha256:7a37677bf2472d495e5d7f3345622ba1520e802b66ceeefb65b3b6b4b0f3283e
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a5455422c490652397303b87ce7bd7016cc2d79e6f5703a6769c1ccd22b388c
+oid sha256:0a39a2f7d3e89fac33a71a8c112d96d42d60a014e1d274f93880aab8cc83d43b
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:928213ab2e09763e116d1bfb478aad8f4139c963ed129d921a2501493e30efdd
+oid sha256:19ba59754b31e5e79014ce130754a8a3fdf9772677ff18499997328c0d9c7146
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:004d7c9b66ee0132acc47b6d5e9cb18d0a333840a025bac015ed1d6ed63c4eb2
+oid sha256:a7de3ad2b13e4a7ba5f0a10459abaecc1f8b8fd8b60df9729954c4f5b657c917
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dd4edda31bf9d44bcea92ce7553db96d7effb20ed51068a52ee0d69285b7d6f
+oid sha256:e36a52e22bbc9b8b07d332783d70b5d67be7c5d641e448758d33c9fb54f4a57d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6656893e56520b745793e71047f05cb9279d9ef3478b134f3967730170f391bc
+oid sha256:4d38ebc3e63761f676d20556f4357162d5180abd6204d3d2f4a79245e233103a
 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": 0.1367332488298416,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.33783783783783783,
+  "best_metric": 0.1061437726020813,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6756756756756757,
   "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": 33.985,
       "eval_steps_per_second": 4.291,
       "step": 25
+    },
+    {
+      "epoch": 0.35135135135135137,
+      "grad_norm": 1.1153565645217896,
+      "learning_rate": 5e-05,
+      "loss": 0.1049,
+      "step": 26
+    },
+    {
+      "epoch": 0.36486486486486486,
+      "grad_norm": 2.0206172466278076,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.2674,
+      "step": 27
+    },
+    {
+      "epoch": 0.3783783783783784,
+      "grad_norm": 1.362246036529541,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.1538,
+      "step": 28
+    },
+    {
+      "epoch": 0.3918918918918919,
+      "grad_norm": 2.0055975914001465,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.2147,
+      "step": 29
+    },
+    {
+      "epoch": 0.40540540540540543,
+      "grad_norm": 2.0882041454315186,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.2495,
+      "step": 30
+    },
+    {
+      "epoch": 0.4189189189189189,
+      "grad_norm": 2.093991279602051,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.2051,
+      "step": 31
+    },
+    {
+      "epoch": 0.43243243243243246,
+      "grad_norm": 1.5407034158706665,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.2374,
+      "step": 32
+    },
+    {
+      "epoch": 0.44594594594594594,
+      "grad_norm": 1.5210086107254028,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.2486,
+      "step": 33
+    },
+    {
+      "epoch": 0.4594594594594595,
+      "grad_norm": 1.4573367834091187,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.2546,
+      "step": 34
+    },
+    {
+      "epoch": 0.47297297297297297,
+      "grad_norm": 1.430071473121643,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.2391,
+      "step": 35
+    },
+    {
+      "epoch": 0.4864864864864865,
+      "grad_norm": 1.4362925291061401,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.1405,
+      "step": 36
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.9847790002822876,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.1705,
+      "step": 37
+    },
+    {
+      "epoch": 0.5135135135135135,
+      "grad_norm": 0.6195996403694153,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.1056,
+      "step": 38
+    },
+    {
+      "epoch": 0.527027027027027,
+      "grad_norm": 0.6867031455039978,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.102,
+      "step": 39
+    },
+    {
+      "epoch": 0.5405405405405406,
+      "grad_norm": 0.8032393455505371,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.1015,
+      "step": 40
+    },
+    {
+      "epoch": 0.5540540540540541,
+      "grad_norm": 0.7433449029922485,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0801,
+      "step": 41
+    },
+    {
+      "epoch": 0.5675675675675675,
+      "grad_norm": 0.8760620355606079,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.166,
+      "step": 42
+    },
+    {
+      "epoch": 0.581081081081081,
+      "grad_norm": 1.1115021705627441,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.2006,
+      "step": 43
+    },
+    {
+      "epoch": 0.5945945945945946,
+      "grad_norm": 1.569411277770996,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.2112,
+      "step": 44
+    },
+    {
+      "epoch": 0.6081081081081081,
+      "grad_norm": 1.140554666519165,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.1916,
+      "step": 45
+    },
+    {
+      "epoch": 0.6216216216216216,
+      "grad_norm": 1.0531151294708252,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.1669,
+      "step": 46
+    },
+    {
+      "epoch": 0.6351351351351351,
+      "grad_norm": 0.7130922079086304,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.1098,
+      "step": 47
+    },
+    {
+      "epoch": 0.6486486486486487,
+      "grad_norm": 1.31761634349823,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.1967,
+      "step": 48
+    },
+    {
+      "epoch": 0.6621621621621622,
+      "grad_norm": 0.7688131332397461,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.1144,
+      "step": 49
+    },
+    {
+      "epoch": 0.6756756756756757,
+      "grad_norm": 1.0444402694702148,
+      "learning_rate": 0.0,
+      "loss": 0.1457,
+      "step": 50
+    },
+    {
+      "epoch": 0.6756756756756757,
+      "eval_loss": 0.1061437726020813,
+      "eval_runtime": 14.6835,
+      "eval_samples_per_second": 33.984,
+      "eval_steps_per_second": 4.291,
+      "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": 2.66009604784128e+17,
+  "total_flos": 5.32019209568256e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null