Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:215b567951fa564e83a067a9bb0629bbbcc73f7bc19bf2dd017b43bc785859a4
+oid sha256:7097d109660720aa5cee965fe23dd6ae9d6b3a231d4775d7109903f5c55aa447
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91f79909a27a93b34aefcd0631570566da361c20300a9b9fd52a1215e4751610
+oid sha256:480e518df0375debf26c47f0340d754efe46df431fe7bb069a0a65892e59b197
 size 113994

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42b1c438952374e9998f5a2d36f3ac410bfcddca63ff6db23249e0c076bbb4d0
+oid sha256:b539fa5b0bccdf4b05a6d43118df02a5b8d4ca2672eaa1d4550a5a39c893cc90
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7bd295bb9eb2b4447feb8e88034e07dec714797cb0c938948724e55ce978154
+oid sha256:5bf979eb34032480c1694be2dd61219a9a8c1213fcec198ecf671580a91b7dd8
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4cbd9a4f3c2ffff8ab81ca8194a07a4515433be3cf91c11ff795c788e91e80b
+oid sha256:8ecf1cd84eca1c5cf716bdedbc75b082bfe1e3293d02e6edaa7e836c98f4de2b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:776f157b9782b4dcf5d918131ef5313c31323c3735df0e9390d199135423c0bc
+oid sha256:6dce7b4ffbc54485b37f3d6968e739c4a4668585da5bf3d1862f61e568f8c490
 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": 11.915081977844238,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.1145475372279496,
+  "best_metric": 11.912494659423828,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.2290950744558992,
   "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": 509.229,
       "eval_steps_per_second": 63.74,
       "step": 25
+    },
+    {
+      "epoch": 0.11912943871706758,
+      "grad_norm": 0.12901845574378967,
+      "learning_rate": 5e-05,
+      "loss": 11.9201,
+      "step": 26
+    },
+    {
+      "epoch": 0.12371134020618557,
+      "grad_norm": 0.13046033680438995,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 11.9141,
+      "step": 27
+    },
+    {
+      "epoch": 0.12829324169530354,
+      "grad_norm": 0.1262538731098175,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 11.9201,
+      "step": 28
+    },
+    {
+      "epoch": 0.13287514318442153,
+      "grad_norm": 0.1264946609735489,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 11.9192,
+      "step": 29
+    },
+    {
+      "epoch": 0.13745704467353953,
+      "grad_norm": 0.12444325536489487,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 11.9203,
+      "step": 30
+    },
+    {
+      "epoch": 0.1420389461626575,
+      "grad_norm": 0.13133777678012848,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 11.9202,
+      "step": 31
+    },
+    {
+      "epoch": 0.1466208476517755,
+      "grad_norm": 0.12449181079864502,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 11.9175,
+      "step": 32
+    },
+    {
+      "epoch": 0.15120274914089346,
+      "grad_norm": 0.13398633897304535,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 11.9129,
+      "step": 33
+    },
+    {
+      "epoch": 0.15578465063001146,
+      "grad_norm": 0.12955492734909058,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 11.9181,
+      "step": 34
+    },
+    {
+      "epoch": 0.16036655211912945,
+      "grad_norm": 0.13738389313220978,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 11.9117,
+      "step": 35
+    },
+    {
+      "epoch": 0.16494845360824742,
+      "grad_norm": 0.14591968059539795,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 11.9209,
+      "step": 36
+    },
+    {
+      "epoch": 0.16953035509736541,
+      "grad_norm": 0.17198042571544647,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 11.9157,
+      "step": 37
+    },
+    {
+      "epoch": 0.17411225658648338,
+      "grad_norm": 0.16452500224113464,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.9104,
+      "step": 38
+    },
+    {
+      "epoch": 0.17869415807560138,
+      "grad_norm": 0.1382473111152649,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 11.9129,
+      "step": 39
+    },
+    {
+      "epoch": 0.18327605956471935,
+      "grad_norm": 0.14481095969676971,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 11.9148,
+      "step": 40
+    },
+    {
+      "epoch": 0.18785796105383734,
+      "grad_norm": 0.13745011389255524,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 11.9214,
+      "step": 41
+    },
+    {
+      "epoch": 0.19243986254295534,
+      "grad_norm": 0.14128021895885468,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 11.9173,
+      "step": 42
+    },
+    {
+      "epoch": 0.1970217640320733,
+      "grad_norm": 0.12983211874961853,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 11.917,
+      "step": 43
+    },
+    {
+      "epoch": 0.2016036655211913,
+      "grad_norm": 0.1443158984184265,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 11.9146,
+      "step": 44
+    },
+    {
+      "epoch": 0.20618556701030927,
+      "grad_norm": 0.1407080441713333,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 11.9105,
+      "step": 45
+    },
+    {
+      "epoch": 0.21076746849942726,
+      "grad_norm": 0.13506297767162323,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 11.9123,
+      "step": 46
+    },
+    {
+      "epoch": 0.21534936998854526,
+      "grad_norm": 0.1397785097360611,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 11.9091,
+      "step": 47
+    },
+    {
+      "epoch": 0.21993127147766323,
+      "grad_norm": 0.1519603431224823,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 11.9153,
+      "step": 48
+    },
+    {
+      "epoch": 0.22451317296678122,
+      "grad_norm": 0.15966291725635529,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 11.9142,
+      "step": 49
+    },
+    {
+      "epoch": 0.2290950744558992,
+      "grad_norm": 0.20552374422550201,
+      "learning_rate": 0.0,
+      "loss": 11.9106,
+      "step": 50
+    },
+    {
+      "epoch": 0.2290950744558992,
+      "eval_loss": 11.912494659423828,
+      "eval_runtime": 2.8969,
+      "eval_samples_per_second": 507.442,
+      "eval_steps_per_second": 63.517,
+      "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": 521247129600.0,
+  "total_flos": 1042494259200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null