Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d13c0d921595fa914305d1f37624dc2a9e53cf1fb6f69a230c54666eb35a075
+oid sha256:4d34d755190754c20f1b650d9ae3dac63ea091d496b28e19dd29567518bc0bf4
 size 524363632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd1ebe956e4b54dda9a74a738ca25201f0bf9361958a15d96cff684e5ea54108
+oid sha256:8fb4af6259f66593b873e6f1a1c9f485c89c03e0107d0edc9f097c99b456e60a
 size 1049049122

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f3f7a6cf58cb791d9262fa72c2c8676c15a09b626243fa5812fd48398db0eb3
+oid sha256:236765ab337dbbfc2510a4de6b4b6a49c3cd88c8e60aa299b8740a74d1ddc8cb
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22c709fa148ce9020135525eddddde15f4a03ecd96e9e7b8b73418d8b0bf590b
+oid sha256:e98fe7a32b920850980683e04af976090ff94266ea7ccebc72f21de318130dc9
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3217a7d977cf2a4e33c165648c0778a80b8172f0c97766fc8c7fc3fe1c4bbba7
+oid sha256:173b74ab0fd8e486cacfeea01e0bd6c6d74f6245c31c781754e3c47dffa4cf1a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:011e37e3be9b22cc585a53456f0ae0e3bee8342656e683e227e5442688c1c261
+oid sha256:9ad31bac153808a9be5cc3379c64ed526dba136b4fb4de6da64d12fadbf27a02
 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": 1.6321067810058594,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.038834951456310676,
+  "best_metric": 1.5666643381118774,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.07766990291262135,
   "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": 20.631,
       "eval_steps_per_second": 2.583,
       "step": 25
+    },
+    {
+      "epoch": 0.040388349514563104,
+      "grad_norm": 13.166337966918945,
+      "learning_rate": 5e-05,
+      "loss": 1.9865,
+      "step": 26
+    },
+    {
+      "epoch": 0.04194174757281553,
+      "grad_norm": 10.11324405670166,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.951,
+      "step": 27
+    },
+    {
+      "epoch": 0.04349514563106796,
+      "grad_norm": 8.36307430267334,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.8482,
+      "step": 28
+    },
+    {
+      "epoch": 0.04504854368932039,
+      "grad_norm": 17.972200393676758,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.7202,
+      "step": 29
+    },
+    {
+      "epoch": 0.04660194174757282,
+      "grad_norm": 7.58774471282959,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.5568,
+      "step": 30
+    },
+    {
+      "epoch": 0.048155339805825245,
+      "grad_norm": 8.460081100463867,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.6775,
+      "step": 31
+    },
+    {
+      "epoch": 0.04970873786407767,
+      "grad_norm": 8.742280960083008,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.4752,
+      "step": 32
+    },
+    {
+      "epoch": 0.051262135922330095,
+      "grad_norm": 8.674991607666016,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.5046,
+      "step": 33
+    },
+    {
+      "epoch": 0.05281553398058252,
+      "grad_norm": 9.43136215209961,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.4211,
+      "step": 34
+    },
+    {
+      "epoch": 0.05436893203883495,
+      "grad_norm": 11.62206745147705,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.3159,
+      "step": 35
+    },
+    {
+      "epoch": 0.05592233009708738,
+      "grad_norm": 12.839760780334473,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.3253,
+      "step": 36
+    },
+    {
+      "epoch": 0.05747572815533981,
+      "grad_norm": 17.61329460144043,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.5886,
+      "step": 37
+    },
+    {
+      "epoch": 0.059029126213592235,
+      "grad_norm": 14.410882949829102,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.8647,
+      "step": 38
+    },
+    {
+      "epoch": 0.060582524271844664,
+      "grad_norm": 7.580593585968018,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.8426,
+      "step": 39
+    },
+    {
+      "epoch": 0.062135922330097085,
+      "grad_norm": 8.240480422973633,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.7878,
+      "step": 40
+    },
+    {
+      "epoch": 0.06368932038834951,
+      "grad_norm": 6.518659591674805,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.5998,
+      "step": 41
+    },
+    {
+      "epoch": 0.06524271844660194,
+      "grad_norm": 7.034609317779541,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.6894,
+      "step": 42
+    },
+    {
+      "epoch": 0.06679611650485437,
+      "grad_norm": 8.43715763092041,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.6934,
+      "step": 43
+    },
+    {
+      "epoch": 0.0683495145631068,
+      "grad_norm": 7.128195285797119,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.4095,
+      "step": 44
+    },
+    {
+      "epoch": 0.06990291262135923,
+      "grad_norm": 7.772005558013916,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.3048,
+      "step": 45
+    },
+    {
+      "epoch": 0.07145631067961165,
+      "grad_norm": 11.243234634399414,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.3976,
+      "step": 46
+    },
+    {
+      "epoch": 0.07300970873786408,
+      "grad_norm": 11.831357955932617,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.2958,
+      "step": 47
+    },
+    {
+      "epoch": 0.07456310679611651,
+      "grad_norm": 8.776447296142578,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.1538,
+      "step": 48
+    },
+    {
+      "epoch": 0.07611650485436894,
+      "grad_norm": 12.493200302124023,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.2776,
+      "step": 49
+    },
+    {
+      "epoch": 0.07766990291262135,
+      "grad_norm": 29.81696891784668,
+      "learning_rate": 0.0,
+      "loss": 1.7919,
+      "step": 50
+    },
+    {
+      "epoch": 0.07766990291262135,
+      "eval_loss": 1.5666643381118774,
+      "eval_runtime": 210.218,
+      "eval_samples_per_second": 20.631,
+      "eval_steps_per_second": 2.583,
+      "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": 5.476375360176128e+17,
+  "total_flos": 1.0952750720352256e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null