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:a28bc7f4d9cebfad13f5882f5e3ec4dd07ca684ee920fa24b42f486bf6702b02
+oid sha256:4b1d570c707988b9000400ae6a405019bf23575f6a3e052f11efad8249d6a70a
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32013c9c0bc88d60e65154f97b02da929a084ca166f4b8be79fda12ba7e2570c
+oid sha256:aa87a474b59fcc4311def47b659fa17b4a69b47d18097d06a5df4bdb860d3328
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e2d90156216baf60fb915383a24cc0bba54711b7a1b4d299f8284f1ee4bbff1
+oid sha256:685472f680ec906e9a6de913c27bbadd0f115ff33d02d726c6b87a06427aae18
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c083b8158d023a6ea01ca4dc29691362044c704c25372c93714db91cfb476f8d
+oid sha256:e81f312cbbd84c013c82e5bdb5a11170ea9518bfb652edb2bba2f9801e3572d6
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4214368bc5b1e7030614f5ec2d127505d2af76cee739def210a2152e28c6b714
+oid sha256:44d55033c4fca5050c114d1ac9a63cb5483b2464ceec245883b2a308782c40db
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb1eca72b5f669bf0c687b78fc12ad88ca9c61367d9ed973ede829abf3d3904f
+oid sha256:474c9fc782e8e564bea9183ba963eeb11b70adcbee689526ea8f834961afd21c
 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": 11.753792762756348,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.24096385542168675,
+  "best_metric": 11.733083724975586,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.4819277108433735,
   "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": 289.403,
       "eval_steps_per_second": 36.434,
       "step": 25
+    },
+    {
+      "epoch": 0.25060240963855424,
+      "grad_norm": 0.4973628520965576,
+      "learning_rate": 5e-05,
+      "loss": 11.7594,
+      "step": 26
+    },
+    {
+      "epoch": 0.26024096385542167,
+      "grad_norm": 0.6137694120407104,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 11.7547,
+      "step": 27
+    },
+    {
+      "epoch": 0.26987951807228916,
+      "grad_norm": 0.6217210292816162,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 11.7535,
+      "step": 28
+    },
+    {
+      "epoch": 0.27951807228915665,
+      "grad_norm": 0.6200572848320007,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 11.7515,
+      "step": 29
+    },
+    {
+      "epoch": 0.2891566265060241,
+      "grad_norm": 0.6112415194511414,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 11.7454,
+      "step": 30
+    },
+    {
+      "epoch": 0.2987951807228916,
+      "grad_norm": 0.59600430727005,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 11.7427,
+      "step": 31
+    },
+    {
+      "epoch": 0.30843373493975906,
+      "grad_norm": 0.7312055826187134,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 11.7438,
+      "step": 32
+    },
+    {
+      "epoch": 0.3180722891566265,
+      "grad_norm": 0.7176217436790466,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 11.734,
+      "step": 33
+    },
+    {
+      "epoch": 0.327710843373494,
+      "grad_norm": 0.7809088826179504,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 11.7259,
+      "step": 34
+    },
+    {
+      "epoch": 0.3373493975903614,
+      "grad_norm": 0.7829328775405884,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 11.7296,
+      "step": 35
+    },
+    {
+      "epoch": 0.3469879518072289,
+      "grad_norm": 0.7592332363128662,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 11.7332,
+      "step": 36
+    },
+    {
+      "epoch": 0.3566265060240964,
+      "grad_norm": 0.8703128695487976,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 11.7266,
+      "step": 37
+    },
+    {
+      "epoch": 0.36626506024096384,
+      "grad_norm": 0.7841212749481201,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.7338,
+      "step": 38
+    },
+    {
+      "epoch": 0.3759036144578313,
+      "grad_norm": 0.6084020733833313,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 11.7476,
+      "step": 39
+    },
+    {
+      "epoch": 0.3855421686746988,
+      "grad_norm": 0.7725892663002014,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 11.7369,
+      "step": 40
+    },
+    {
+      "epoch": 0.39518072289156625,
+      "grad_norm": 0.6861575841903687,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 11.7437,
+      "step": 41
+    },
+    {
+      "epoch": 0.40481927710843374,
+      "grad_norm": 0.7572954297065735,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 11.7375,
+      "step": 42
+    },
+    {
+      "epoch": 0.41445783132530123,
+      "grad_norm": 0.6916650533676147,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 11.7284,
+      "step": 43
+    },
+    {
+      "epoch": 0.42409638554216866,
+      "grad_norm": 0.6975832581520081,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 11.7311,
+      "step": 44
+    },
+    {
+      "epoch": 0.43373493975903615,
+      "grad_norm": 0.6840330362319946,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 11.7331,
+      "step": 45
+    },
+    {
+      "epoch": 0.4433734939759036,
+      "grad_norm": 0.7329042553901672,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 11.7307,
+      "step": 46
+    },
+    {
+      "epoch": 0.4530120481927711,
+      "grad_norm": 0.7996618151664734,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 11.7201,
+      "step": 47
+    },
+    {
+      "epoch": 0.46265060240963857,
+      "grad_norm": 0.8392429947853088,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 11.7235,
+      "step": 48
+    },
+    {
+      "epoch": 0.472289156626506,
+      "grad_norm": 0.847804069519043,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 11.7244,
+      "step": 49
+    },
+    {
+      "epoch": 0.4819277108433735,
+      "grad_norm": 0.9711650609970093,
+      "learning_rate": 0.0,
+      "loss": 11.7187,
+      "step": 50
+    },
+    {
+      "epoch": 0.4819277108433735,
+      "eval_loss": 11.733083724975586,
+      "eval_runtime": 2.4719,
+      "eval_samples_per_second": 282.779,
+      "eval_steps_per_second": 35.6,
+      "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": 81943068672000.0,
+  "total_flos": 163886137344000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null