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:c60d44f16dbdc1ce77b7359acc627beb59fcf5353a2141aa677b383519d465be
+oid sha256:19ad2c600f9f229b39fb67dc6dc9c34d71f1b3ad89544a1ca64061d7e5efcade
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2d498c349fcd5821bc4b0c99d7e2b2bcd272864d10a5adb733da55562c147cd
+oid sha256:60562173737c46bf000b691da9d753e6343b9ee6e3f0d00bd56e68a1b2c018a0
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24f89a3282a6b35332ac005f7e29c65dc21c12bfebc2768bbe3d4388000c8944
+oid sha256:b7bf981d6d7bb318627a6649dd0308e1ff8c505104a3882742bb7b4de03e1ac6
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f46ead07a7cc8f24bde67af7158b9ec8794471d2bd8145497c279d6119ccb511
+oid sha256:3fe468bf4d05b63325f0c6634d95eaaa0cee7ed864cd67b15b406ddf7ca83784
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:039bc0be694dccde694f0d5e98a3c5508fbd31ce308f90bf950dd18f51f24afe
+oid sha256:2dbdb7aedb0ee90a0bb6efc0f26aba8ea6014a868ab81b2d91a1f30e000e913e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c9bc607986704587d2f4702db16b9d5eb6787af0f5925675967bb65ce4393ca
+oid sha256:2cd83d49f6dcfbb9ca838bcd0f0f33dcb9898327deb5174ed93ac8ac7e0a9fb7
 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": 1.315967321395874,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.1736111111111111,
+  "best_metric": 1.2535191774368286,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.3472222222222222,
   "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": 32.243,
       "eval_steps_per_second": 4.055,
       "step": 25
+    },
+    {
+      "epoch": 0.18055555555555555,
+      "grad_norm": 4.528706073760986,
+      "learning_rate": 5e-05,
+      "loss": 2.2754,
+      "step": 26
+    },
+    {
+      "epoch": 0.1875,
+      "grad_norm": 1.2604354619979858,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.1671,
+      "step": 27
+    },
+    {
+      "epoch": 0.19444444444444445,
+      "grad_norm": 1.2874277830123901,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.193,
+      "step": 28
+    },
+    {
+      "epoch": 0.2013888888888889,
+      "grad_norm": 0.8460001349449158,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.1593,
+      "step": 29
+    },
+    {
+      "epoch": 0.20833333333333334,
+      "grad_norm": 0.30335867404937744,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.1539,
+      "step": 30
+    },
+    {
+      "epoch": 0.2152777777777778,
+      "grad_norm": 1.150852084159851,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.1991,
+      "step": 31
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 1.0014760494232178,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.2075,
+      "step": 32
+    },
+    {
+      "epoch": 0.22916666666666666,
+      "grad_norm": 1.1253355741500854,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.2038,
+      "step": 33
+    },
+    {
+      "epoch": 0.2361111111111111,
+      "grad_norm": 0.4158329665660858,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.2013,
+      "step": 34
+    },
+    {
+      "epoch": 0.24305555555555555,
+      "grad_norm": 0.3990498483181,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.179,
+      "step": 35
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.34036171436309814,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.1811,
+      "step": 36
+    },
+    {
+      "epoch": 0.2569444444444444,
+      "grad_norm": 0.3939284384250641,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.2234,
+      "step": 37
+    },
+    {
+      "epoch": 0.2638888888888889,
+      "grad_norm": 2.1086604595184326,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.2966,
+      "step": 38
+    },
+    {
+      "epoch": 0.2708333333333333,
+      "grad_norm": 0.648451566696167,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.1439,
+      "step": 39
+    },
+    {
+      "epoch": 0.2777777777777778,
+      "grad_norm": 0.5881859660148621,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.1396,
+      "step": 40
+    },
+    {
+      "epoch": 0.2847222222222222,
+      "grad_norm": 0.5503454208374023,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.1291,
+      "step": 41
+    },
+    {
+      "epoch": 0.2916666666666667,
+      "grad_norm": 0.5237451791763306,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.1538,
+      "step": 42
+    },
+    {
+      "epoch": 0.2986111111111111,
+      "grad_norm": 0.6803749799728394,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.176,
+      "step": 43
+    },
+    {
+      "epoch": 0.3055555555555556,
+      "grad_norm": 0.4073289930820465,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.1751,
+      "step": 44
+    },
+    {
+      "epoch": 0.3125,
+      "grad_norm": 0.397196501493454,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.1962,
+      "step": 45
+    },
+    {
+      "epoch": 0.3194444444444444,
+      "grad_norm": 0.447818398475647,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.1877,
+      "step": 46
+    },
+    {
+      "epoch": 0.3263888888888889,
+      "grad_norm": 0.34394121170043945,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.1707,
+      "step": 47
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.34709423780441284,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.1682,
+      "step": 48
+    },
+    {
+      "epoch": 0.3402777777777778,
+      "grad_norm": 0.2884080410003662,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.1722,
+      "step": 49
+    },
+    {
+      "epoch": 0.3472222222222222,
+      "grad_norm": 0.35996749997138977,
+      "learning_rate": 0.0,
+      "loss": 1.2179,
+      "step": 50
+    },
+    {
+      "epoch": 0.3472222222222222,
+      "eval_loss": 1.2535191774368286,
+      "eval_runtime": 29.8222,
+      "eval_samples_per_second": 32.526,
+      "eval_steps_per_second": 4.091,
+      "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": 2.89638977248428e+17,
+  "total_flos": 5.805082167402824e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null