Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a182a7fbd722bdc3511a798531cea88f769914a5cf1707251cb67abd1087e75
+oid sha256:72cd248766c9a08e857846004bd94be1bff3d6cab63d047cc8bc34b88dad76e1
 size 239536272

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:067aa5b5ef9cccaf39c9c9d008a11c22ae8701c09bf8f343c99367ff461d1c74
+oid sha256:30ba681176927536448d074b7b2a64fc14f5061019086aa6b8fdc825fc1f92ab
 size 479362682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:112a9b8c8c1fb906f75e1fb34e7b1cb864bd51e98e54843f9f4bcfda9828faae
+oid sha256:965bd22ba6eda568cf53b5dc813d85b5d998e6b74b43847b60dcb67e3a5355a0
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b7936fb37c6ebdcea12dae3e1749a03742ba8615a7a9288b5b90123f40e6afa
+oid sha256:34a6efb34c3730a3115153a6435425bb9a456802a63d8c31de63d5e7971e151c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9db736662d41900759d57f9bc86f1292530d71eb6b7304a0b44168cc2945ad7
+oid sha256:6a558089f3a22c33f2ce3fe4b207feb2ca78f066e706c6a71e07ac17dc188b1c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4000deea95dcc303dd2ad642cbc93993ce75d220ad521d4c28e00efb1926b0d
+oid sha256:d9cf0382a380a44ae421ae9a33f34b2806659d4a3c17ff50555daf26fb0b6414
 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": 4.725675582885742,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.3401360544217687,
+  "best_metric": 4.613088607788086,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6802721088435374,
   "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": 54.762,
       "eval_steps_per_second": 6.859,
       "step": 25
+    },
+    {
+      "epoch": 0.35374149659863946,
+      "grad_norm": 2.5993564128875732,
+      "learning_rate": 5e-05,
+      "loss": 3.8505,
+      "step": 26
+    },
+    {
+      "epoch": 0.3673469387755102,
+      "grad_norm": 2.5245633125305176,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 4.1639,
+      "step": 27
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": 2.204711675643921,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 4.1353,
+      "step": 28
+    },
+    {
+      "epoch": 0.3945578231292517,
+      "grad_norm": 1.923013687133789,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 4.4266,
+      "step": 29
+    },
+    {
+      "epoch": 0.40816326530612246,
+      "grad_norm": 2.102698564529419,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 4.3867,
+      "step": 30
+    },
+    {
+      "epoch": 0.4217687074829932,
+      "grad_norm": 1.8343956470489502,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 4.4635,
+      "step": 31
+    },
+    {
+      "epoch": 0.43537414965986393,
+      "grad_norm": 1.8821370601654053,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 4.4229,
+      "step": 32
+    },
+    {
+      "epoch": 0.4489795918367347,
+      "grad_norm": 2.1628355979919434,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 4.9361,
+      "step": 33
+    },
+    {
+      "epoch": 0.46258503401360546,
+      "grad_norm": 2.0924601554870605,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 4.9282,
+      "step": 34
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "grad_norm": 2.0800721645355225,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 4.8883,
+      "step": 35
+    },
+    {
+      "epoch": 0.4897959183673469,
+      "grad_norm": 2.4742178916931152,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 5.0422,
+      "step": 36
+    },
+    {
+      "epoch": 0.5034013605442177,
+      "grad_norm": 3.6025562286376953,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 5.6058,
+      "step": 37
+    },
+    {
+      "epoch": 0.5170068027210885,
+      "grad_norm": 1.8626090288162231,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 4.4827,
+      "step": 38
+    },
+    {
+      "epoch": 0.5306122448979592,
+      "grad_norm": 1.6383427381515503,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 3.8985,
+      "step": 39
+    },
+    {
+      "epoch": 0.54421768707483,
+      "grad_norm": 1.6859347820281982,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 4.021,
+      "step": 40
+    },
+    {
+      "epoch": 0.5578231292517006,
+      "grad_norm": 1.714751124382019,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 4.2328,
+      "step": 41
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 1.5772175788879395,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 4.3372,
+      "step": 42
+    },
+    {
+      "epoch": 0.5850340136054422,
+      "grad_norm": 1.8678478002548218,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 4.3201,
+      "step": 43
+    },
+    {
+      "epoch": 0.5986394557823129,
+      "grad_norm": 1.673134446144104,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 4.3886,
+      "step": 44
+    },
+    {
+      "epoch": 0.6122448979591837,
+      "grad_norm": 2.0004281997680664,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 4.8627,
+      "step": 45
+    },
+    {
+      "epoch": 0.6258503401360545,
+      "grad_norm": 2.623873472213745,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 4.8831,
+      "step": 46
+    },
+    {
+      "epoch": 0.6394557823129252,
+      "grad_norm": 1.9565924406051636,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 4.9377,
+      "step": 47
+    },
+    {
+      "epoch": 0.6530612244897959,
+      "grad_norm": 2.1026477813720703,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 4.9891,
+      "step": 48
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 2.7066915035247803,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 5.4155,
+      "step": 49
+    },
+    {
+      "epoch": 0.6802721088435374,
+      "grad_norm": 4.02397346496582,
+      "learning_rate": 0.0,
+      "loss": 5.9606,
+      "step": 50
+    },
+    {
+      "epoch": 0.6802721088435374,
+      "eval_loss": 4.613088607788086,
+      "eval_runtime": 9.0406,
+      "eval_samples_per_second": 54.753,
+      "eval_steps_per_second": 6.858,
+      "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": 1.114626154561536e+17,
+  "total_flos": 2.229252309123072e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null