Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cceef7a1360e4fbb1e9524e793dd450723ce3cff115152dc37667e3ef801e23
+oid sha256:532f27a26bc6eede5f71969e0b697bee8e10092db831230c9e68d394363e3483
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1085816f83a5ebc354a12938771891021f6b1dc74b3dff6a77d08fed616cc600
+oid sha256:25e9953d1b2dce5eca95e544fc7c6a170564a3bc9b9ae1db3ebf2fb299557650
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1fafbced35ef879be7defb4369b1f5c33a7eb9abe310dc17c7295b4838d2a41
+oid sha256:e7bd98062205e91dc602c742bd603a4df67b66a0ef884bf736439f554a4272fb
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1ce1a1ad315f2c919d3b69b955b8cf02003c6f5f2d80d648b38fb746de4cdfa
+oid sha256:59d63d058fb8c7cc3d1a79e5cc74714abaa222c6747ec9ab81414ac5c78768bb
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afdf0751911e8725e22be8f4749b9bf0d7da606a7a18a047d6f3be2fd2cf2029
+oid sha256:77a65e62f7f8ec86f71178a11abe77e20ea310bcba6c35166d7992ec3eea5337
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bb332c75a7a344c385a031e3b299e53177e19332b4f2b735028b800e76ce0fb
+oid sha256:e08280078cbc0724895fea076d2fb9d3682a98171ea98da9823adb89e8b28334
 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": 0.3598560690879822,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.33755274261603374,
+  "best_metric": 0.1645851880311966,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6751054852320675,
   "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": 32.876,
       "eval_steps_per_second": 4.151,
       "step": 25
+    },
+    {
+      "epoch": 0.3510548523206751,
+      "grad_norm": 4.339173316955566,
+      "learning_rate": 5e-05,
+      "loss": 0.6258,
+      "step": 26
+    },
+    {
+      "epoch": 0.36455696202531646,
+      "grad_norm": 3.878525733947754,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.5842,
+      "step": 27
+    },
+    {
+      "epoch": 0.3780590717299578,
+      "grad_norm": 3.5104947090148926,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.512,
+      "step": 28
+    },
+    {
+      "epoch": 0.39156118143459917,
+      "grad_norm": 2.3546969890594482,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.367,
+      "step": 29
+    },
+    {
+      "epoch": 0.4050632911392405,
+      "grad_norm": 1.871620774269104,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.3047,
+      "step": 30
+    },
+    {
+      "epoch": 0.41856540084388183,
+      "grad_norm": 1.3824152946472168,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.2219,
+      "step": 31
+    },
+    {
+      "epoch": 0.4320675105485232,
+      "grad_norm": 1.3422837257385254,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.1512,
+      "step": 32
+    },
+    {
+      "epoch": 0.44556962025316454,
+      "grad_norm": 1.333117961883545,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.1522,
+      "step": 33
+    },
+    {
+      "epoch": 0.45907172995780593,
+      "grad_norm": 2.088132381439209,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.2185,
+      "step": 34
+    },
+    {
+      "epoch": 0.47257383966244726,
+      "grad_norm": 2.526772975921631,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.2609,
+      "step": 35
+    },
+    {
+      "epoch": 0.4860759493670886,
+      "grad_norm": 2.376660108566284,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.2183,
+      "step": 36
+    },
+    {
+      "epoch": 0.49957805907173,
+      "grad_norm": 2.1182215213775635,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.1805,
+      "step": 37
+    },
+    {
+      "epoch": 0.5130801687763713,
+      "grad_norm": 0.9188656806945801,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.236,
+      "step": 38
+    },
+    {
+      "epoch": 0.5265822784810127,
+      "grad_norm": 1.0770657062530518,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.2585,
+      "step": 39
+    },
+    {
+      "epoch": 0.540084388185654,
+      "grad_norm": 0.9798564314842224,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.2234,
+      "step": 40
+    },
+    {
+      "epoch": 0.5535864978902953,
+      "grad_norm": 0.7824795842170715,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.2099,
+      "step": 41
+    },
+    {
+      "epoch": 0.5670886075949367,
+      "grad_norm": 0.8526087403297424,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.1849,
+      "step": 42
+    },
+    {
+      "epoch": 0.580590717299578,
+      "grad_norm": 0.685903012752533,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.1996,
+      "step": 43
+    },
+    {
+      "epoch": 0.5940928270042194,
+      "grad_norm": 0.954988956451416,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.1537,
+      "step": 44
+    },
+    {
+      "epoch": 0.6075949367088608,
+      "grad_norm": 0.699277400970459,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.1394,
+      "step": 45
+    },
+    {
+      "epoch": 0.6210970464135022,
+      "grad_norm": 0.5863059163093567,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.1467,
+      "step": 46
+    },
+    {
+      "epoch": 0.6345991561181434,
+      "grad_norm": 1.0702379941940308,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.1562,
+      "step": 47
+    },
+    {
+      "epoch": 0.6481012658227848,
+      "grad_norm": 1.1115703582763672,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.145,
+      "step": 48
+    },
+    {
+      "epoch": 0.6616033755274262,
+      "grad_norm": 1.0013189315795898,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.1066,
+      "step": 49
+    },
+    {
+      "epoch": 0.6751054852320675,
+      "grad_norm": 1.1740268468856812,
+      "learning_rate": 0.0,
+      "loss": 0.1087,
+      "step": 50
+    },
+    {
+      "epoch": 0.6751054852320675,
+      "eval_loss": 0.1645851880311966,
+      "eval_runtime": 15.1774,
+      "eval_samples_per_second": 32.878,
+      "eval_steps_per_second": 4.151,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null