Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39491b639ad18c7b0f401324356e241e922a8377417b4b6fc0a87e304039883a
+oid sha256:e551ed1743fe8e3e6e03638908fe04546b66c6a9a36e5f909bde598be1f260a8
 size 166182480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:533b72c07db2edc6d07507a85ab715f0ffee58615407da3c5b4e3ef660153d3f
+oid sha256:fdf7bad96b87a70674c226e1ff3cd94e8bb30bc818d9b8f75e68e25ed902841d
 size 332574358

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7176eb57e63e60f1f3883f83440949e1e57eb8ebb36123d19a29745c3036cd64
+oid sha256:df9a7922a47242d484c9f1be90cefb3c08bee5fd3ce161187f3f317f39271466
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4d23cef74532bc53c197645e0c4ce63d61c895e5cf75b42ea4d3f1fe2392c26
+oid sha256:c3a503548c05a08efedaa5899b82c35e2cc327017de9edfbb59d1f0318fca585
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d908870ad7e82ee540b83f27e5f2249831e97118ba9f64f79a42c818b715cd79
+oid sha256:8d9a6caaefc5dfab364be6afee628b1e215964d7a20d395c1c4f0029268c4f5c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c29aed889f1506959b0a9ccde56cb7d19a3925222927f87e273ed8a14d53e7a8
+oid sha256:d6c01ad44b955ed96d87496e784dc43aaacd44ec2520d14eb9d5d1848faa3038
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.0004642109270207584,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.031773770752244024,
+  "best_metric": 0.00031724729342386127,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.06354754150448805,
   "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": 39.953,
       "eval_steps_per_second": 10.388,
       "step": 25
+    },
+    {
+      "epoch": 0.033044721582333784,
+      "grad_norm": 0.06591206043958664,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0024,
+      "step": 26
+    },
+    {
+      "epoch": 0.034315672412423545,
+      "grad_norm": 0.08313017338514328,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.003,
+      "step": 27
+    },
+    {
+      "epoch": 0.035586623242513306,
+      "grad_norm": 0.08835230022668839,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0011,
+      "step": 28
+    },
+    {
+      "epoch": 0.036857574072603067,
+      "grad_norm": 0.04048483073711395,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.0013,
+      "step": 29
+    },
+    {
+      "epoch": 0.03812852490269283,
+      "grad_norm": 0.06910810619592667,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0013,
+      "step": 30
+    },
+    {
+      "epoch": 0.03939947573278259,
+      "grad_norm": 0.08303745836019516,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.0037,
+      "step": 31
+    },
+    {
+      "epoch": 0.04067042656287235,
+      "grad_norm": 0.05123548209667206,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0009,
+      "step": 32
+    },
+    {
+      "epoch": 0.04194137739296211,
+      "grad_norm": 0.041676923632621765,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.0004,
+      "step": 33
+    },
+    {
+      "epoch": 0.04321232822305187,
+      "grad_norm": 0.036259882152080536,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0007,
+      "step": 34
+    },
+    {
+      "epoch": 0.04448327905314163,
+      "grad_norm": 0.2851651906967163,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.0013,
+      "step": 35
+    },
+    {
+      "epoch": 0.04575422988323139,
+      "grad_norm": 0.08879315108060837,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.003,
+      "step": 36
+    },
+    {
+      "epoch": 0.04702518071332115,
+      "grad_norm": 0.008346485905349255,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.0002,
+      "step": 37
+    },
+    {
+      "epoch": 0.04829613154341091,
+      "grad_norm": 0.14562931656837463,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.004,
+      "step": 38
+    },
+    {
+      "epoch": 0.04956708237350067,
+      "grad_norm": 0.1382046937942505,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0014,
+      "step": 39
+    },
+    {
+      "epoch": 0.050838033203590434,
+      "grad_norm": 0.022914864122867584,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0006,
+      "step": 40
+    },
+    {
+      "epoch": 0.052108984033680195,
+      "grad_norm": 0.020301444455981255,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0002,
+      "step": 41
+    },
+    {
+      "epoch": 0.053379934863769955,
+      "grad_norm": 0.052298810333013535,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.001,
+      "step": 42
+    },
+    {
+      "epoch": 0.054650885693859716,
+      "grad_norm": 0.06274766474962234,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0007,
+      "step": 43
+    },
+    {
+      "epoch": 0.05592183652394948,
+      "grad_norm": 0.034948330372571945,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0005,
+      "step": 44
+    },
+    {
+      "epoch": 0.05719278735403924,
+      "grad_norm": 0.01532821450382471,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0005,
+      "step": 45
+    },
+    {
+      "epoch": 0.058463738184129005,
+      "grad_norm": 0.013808445073664188,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0003,
+      "step": 46
+    },
+    {
+      "epoch": 0.059734689014218766,
+      "grad_norm": 0.13328535854816437,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0036,
+      "step": 47
+    },
+    {
+      "epoch": 0.061005639844308526,
+      "grad_norm": 0.341700941324234,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.013,
+      "step": 48
+    },
+    {
+      "epoch": 0.06227659067439829,
+      "grad_norm": 0.010579594410955906,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0003,
+      "step": 49
+    },
+    {
+      "epoch": 0.06354754150448805,
+      "grad_norm": 0.281735897064209,
+      "learning_rate": 1e-05,
+      "loss": 0.0029,
+      "step": 50
+    },
+    {
+      "epoch": 0.06354754150448805,
+      "eval_loss": 0.00031724729342386127,
+      "eval_runtime": 1.2607,
+      "eval_samples_per_second": 39.659,
+      "eval_steps_per_second": 10.311,
+      "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": 8.1240447254528e+16,
+  "total_flos": 1.62480894509056e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null