Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a855a003371a3ce520771561f8329660fc2bfd5e510960937ba2bcd6b38829b
+oid sha256:5cdb4e762744386dbb61755644334bfc505f774b6ac3a71573c5b4eb60254aa5
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2898cbe11d81343c69752bedd970a05e4670bd44140273dfca0741322b5969a8
+oid sha256:5ef63687969d0f4b013830a784df43700379c91d1ba420bee1d28e206b652f7e
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a2d8e9503da68d2a6d8bc884f0fad04832fdedfd97aee73c1866d056ff323dc
+oid sha256:61b9c831c3c84a5a962dc61d29916d05573ded231fd9534adee944123d59feb9
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68e18f79ab57ed1e4d842322b83b92e34ea574742a264f35c21994cb63f0c2d1
+oid sha256:584989b235e2cac0a211da3516e75308b459d5fb3b735aa8e648266b76baa051
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ed1c1f09d8f741e0838cbca81a69ddf230e7b9a627281f17284609211b6501c
+oid sha256:3613f909c8e17fcd83e37d72a71fb3f65f075982a13e4b13d86d36a850218abd
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04454aaffdfb99b40482a9340d958c9fbd3fed121de999b7b0467a74baf27391
+oid sha256:b6c52f243229693fa830f221557ab34aea674f35f9fddd826e226e55dcbac7df
 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": 1.0803272724151611,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.13527223537368954,
+  "best_metric": 1.0481798648834229,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.2705444707473791,
   "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": 35.158,
       "eval_steps_per_second": 4.405,
       "step": 25
+    },
+    {
+      "epoch": 0.14068312478863712,
+      "grad_norm": 0.15966030955314636,
+      "learning_rate": 5e-05,
+      "loss": 1.2557,
+      "step": 26
+    },
+    {
+      "epoch": 0.14609401420358473,
+      "grad_norm": 0.1860065907239914,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.1753,
+      "step": 27
+    },
+    {
+      "epoch": 0.1515049036185323,
+      "grad_norm": 0.17951346933841705,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.1365,
+      "step": 28
+    },
+    {
+      "epoch": 0.15691579303347988,
+      "grad_norm": 0.18557779490947723,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.13,
+      "step": 29
+    },
+    {
+      "epoch": 0.16232668244842746,
+      "grad_norm": 0.20400725305080414,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.065,
+      "step": 30
+    },
+    {
+      "epoch": 0.16773757186337504,
+      "grad_norm": 0.20410767197608948,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.1318,
+      "step": 31
+    },
+    {
+      "epoch": 0.17314846127832262,
+      "grad_norm": 0.2068430483341217,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.0403,
+      "step": 32
+    },
+    {
+      "epoch": 0.1785593506932702,
+      "grad_norm": 0.21575738489627838,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.038,
+      "step": 33
+    },
+    {
+      "epoch": 0.18397024010821778,
+      "grad_norm": 0.23572982847690582,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.0261,
+      "step": 34
+    },
+    {
+      "epoch": 0.18938112952316538,
+      "grad_norm": 0.2618209719657898,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.9806,
+      "step": 35
+    },
+    {
+      "epoch": 0.19479201893811296,
+      "grad_norm": 0.307118684053421,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.0235,
+      "step": 36
+    },
+    {
+      "epoch": 0.20020290835306054,
+      "grad_norm": 0.33040422201156616,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.027,
+      "step": 37
+    },
+    {
+      "epoch": 0.20561379776800812,
+      "grad_norm": 0.21346908807754517,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.3273,
+      "step": 38
+    },
+    {
+      "epoch": 0.2110246871829557,
+      "grad_norm": 0.1645258665084839,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.1897,
+      "step": 39
+    },
+    {
+      "epoch": 0.21643557659790327,
+      "grad_norm": 0.1729971021413803,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.1253,
+      "step": 40
+    },
+    {
+      "epoch": 0.22184646601285085,
+      "grad_norm": 0.16712252795696259,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.0615,
+      "step": 41
+    },
+    {
+      "epoch": 0.22725735542779846,
+      "grad_norm": 0.20118552446365356,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.1512,
+      "step": 42
+    },
+    {
+      "epoch": 0.23266824484274604,
+      "grad_norm": 0.19876576960086823,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.1167,
+      "step": 43
+    },
+    {
+      "epoch": 0.23807913425769361,
+      "grad_norm": 0.2086692750453949,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.0548,
+      "step": 44
+    },
+    {
+      "epoch": 0.2434900236726412,
+      "grad_norm": 0.20932449400424957,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.9874,
+      "step": 45
+    },
+    {
+      "epoch": 0.24890091308758877,
+      "grad_norm": 0.21197985112667084,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.0269,
+      "step": 46
+    },
+    {
+      "epoch": 0.2543118025025364,
+      "grad_norm": 0.23848804831504822,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.9747,
+      "step": 47
+    },
+    {
+      "epoch": 0.2597226919174839,
+      "grad_norm": 0.25608116388320923,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.9815,
+      "step": 48
+    },
+    {
+      "epoch": 0.26513358133243153,
+      "grad_norm": 0.3206362724304199,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.0397,
+      "step": 49
+    },
+    {
+      "epoch": 0.2705444707473791,
+      "grad_norm": 0.3978687822818756,
+      "learning_rate": 0.0,
+      "loss": 0.9562,
+      "step": 50
+    },
+    {
+      "epoch": 0.2705444707473791,
+      "eval_loss": 1.0481798648834229,
+      "eval_runtime": 35.423,
+      "eval_samples_per_second": 35.147,
+      "eval_steps_per_second": 4.404,
+      "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": 2.629552387915776e+17,
+  "total_flos": 5.259104775831552e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null