Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11b07cb5fce3265e744b690087bb8910f17e7c85bc916f38f427367493983033
+oid sha256:3be8c835d90ef6a0e5be353b98569d168ca6ca36f1a29ffce5a22464f044852d
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a10a0bb19074b46ef7c2f3ef163f90ba1bca0f55055084b6078892226eb3af61
+oid sha256:bfaaaf38d45bae3d70de866ff183e3a4359c58acf627b11d07f24845a7e427f1
 size 313998650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:779e97e8ea7cb127409cbb724efbebd167605f0a190e1036b5903a084a92e655
+oid sha256:97cec626985927ebf5f926ef8db14111273baf09d11734b9764f6b920bb7ded1
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3a53dddb2fb642bdb032ebaa463b6b4e474bec37af360b04fdb99dc58ec2a2a
+oid sha256:21b8ebd07f99f4b9febf514224d316c5373a34ff4ad237c86f42e9212750f04a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afd59f255cf47b03bae4462289eb19484151becbe4554c41e06e11f5a4bb1002
+oid sha256:f3ab4bc2ab73c53f960cd00d8fa71e61ca98b331cd1d1d9fd5ca4ada15400168
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a52f9ad0a74ffe421a11e307ffb467999cdc9fbeb2982b45bd492bbc12fa9f5
+oid sha256:4186250a1aca3322d717a26f3a6e78fedf802a8b67a62364cc6fb604a2aea6cc
 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": 1.6246213912963867,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.1225114854517611,
+  "best_metric": 1.5265823602676392,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.2450229709035222,
   "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": 74.409,
       "eval_steps_per_second": 9.308,
       "step": 25
+    },
+    {
+      "epoch": 0.12741194486983154,
+      "grad_norm": 1.912805199623108,
+      "learning_rate": 5e-05,
+      "loss": 1.3076,
+      "step": 26
+    },
+    {
+      "epoch": 0.132312404287902,
+      "grad_norm": 1.7271080017089844,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.5167,
+      "step": 27
+    },
+    {
+      "epoch": 0.13721286370597244,
+      "grad_norm": 1.879220724105835,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.1116,
+      "step": 28
+    },
+    {
+      "epoch": 0.14211332312404287,
+      "grad_norm": 1.5653444528579712,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.0531,
+      "step": 29
+    },
+    {
+      "epoch": 0.14701378254211334,
+      "grad_norm": 1.661484718322754,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.345,
+      "step": 30
+    },
+    {
+      "epoch": 0.15191424196018377,
+      "grad_norm": 1.8263542652130127,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.4316,
+      "step": 31
+    },
+    {
+      "epoch": 0.1568147013782542,
+      "grad_norm": 2.0890257358551025,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.6723,
+      "step": 32
+    },
+    {
+      "epoch": 0.16171516079632464,
+      "grad_norm": 2.0878026485443115,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.8243,
+      "step": 33
+    },
+    {
+      "epoch": 0.1666156202143951,
+      "grad_norm": 2.1519672870635986,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.8026,
+      "step": 34
+    },
+    {
+      "epoch": 0.17151607963246554,
+      "grad_norm": 2.1100552082061768,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.6778,
+      "step": 35
+    },
+    {
+      "epoch": 0.17641653905053598,
+      "grad_norm": 2.2416326999664307,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.9641,
+      "step": 36
+    },
+    {
+      "epoch": 0.18131699846860644,
+      "grad_norm": 2.2929885387420654,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.9768,
+      "step": 37
+    },
+    {
+      "epoch": 0.18621745788667687,
+      "grad_norm": 1.919622778892517,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.6375,
+      "step": 38
+    },
+    {
+      "epoch": 0.1911179173047473,
+      "grad_norm": 1.6996771097183228,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.3368,
+      "step": 39
+    },
+    {
+      "epoch": 0.19601837672281777,
+      "grad_norm": 1.4825369119644165,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.0644,
+      "step": 40
+    },
+    {
+      "epoch": 0.2009188361408882,
+      "grad_norm": 1.6856578588485718,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.179,
+      "step": 41
+    },
+    {
+      "epoch": 0.20581929555895864,
+      "grad_norm": 1.5633989572525024,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.188,
+      "step": 42
+    },
+    {
+      "epoch": 0.2107197549770291,
+      "grad_norm": 1.8037993907928467,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.2002,
+      "step": 43
+    },
+    {
+      "epoch": 0.21562021439509954,
+      "grad_norm": 1.8860701322555542,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.4013,
+      "step": 44
+    },
+    {
+      "epoch": 0.22052067381316998,
+      "grad_norm": 1.9994962215423584,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.532,
+      "step": 45
+    },
+    {
+      "epoch": 0.22542113323124044,
+      "grad_norm": 2.0619125366210938,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.5686,
+      "step": 46
+    },
+    {
+      "epoch": 0.23032159264931087,
+      "grad_norm": 1.921753168106079,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.712,
+      "step": 47
+    },
+    {
+      "epoch": 0.2352220520673813,
+      "grad_norm": 2.2192230224609375,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.7398,
+      "step": 48
+    },
+    {
+      "epoch": 0.24012251148545177,
+      "grad_norm": 1.9620671272277832,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.9291,
+      "step": 49
+    },
+    {
+      "epoch": 0.2450229709035222,
+      "grad_norm": 2.0268142223358154,
+      "learning_rate": 0.0,
+      "loss": 1.8767,
+      "step": 50
+    },
+    {
+      "epoch": 0.2450229709035222,
+      "eval_loss": 1.5265823602676392,
+      "eval_runtime": 18.5545,
+      "eval_samples_per_second": 74.106,
+      "eval_steps_per_second": 9.27,
+      "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": 7.957253052799386e+16,
+  "total_flos": 1.5904571953617306e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null