Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3608114920b4ac7b42e31151af8e5770d39195330670408be400958f1015ac98
+oid sha256:551954999fe31ace2ee4957eff001348ea20462da4405c76d9c66ce5f33cb0c3
 size 550593184

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a8a52bad9cb5cc05a9a21bce7524c6e1286b0f49e6dc71f7d9685d2d85def1a
+oid sha256:10e164ac136a39fbc19cbe26ab32efe48e7f2114d027cc15239016255f815937
 size 1101572914

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b63c3e907184c0d5484b3224300b42b61a6c9440a5a94b24400fb63ab05da27c
+oid sha256:c63f2bd6159d222a1368eb00941862696055207e0f11bed8a56cca37da4a657a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0b9420152133a50b6a9d2ea128ce22e09513d4b7e065656d36d60ebece9711c
+oid sha256:a8b4c4da4686e2db85fa9751cf19d3a8bf19c4cf1f5bafef0c977f879cd3201c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b461a5bece7d2ff1d5c0ed0c0666be163db65350f144c80e6ea5ab4a18c56e1f
+oid sha256:c3429046e328e8266a9e71b2ee4597e9d02d6a16300c9fd11152dc28f34caf38
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2754e9b056786ed908241171559591965d39696ae8b9f4dff8db515fcc68f7ae
+oid sha256:0a90618c560f9a4de07e765fb854df1fc39742ee2adb3d1521489b2e423ac15f
 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": 0.0024142141919583082,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.029750836742283376,
+  "best_metric": 0.0017845286056399345,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.05950167348456675,
   "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": 18.77,
       "eval_steps_per_second": 2.347,
       "step": 25
+    },
+    {
+      "epoch": 0.03094087021197471,
+      "grad_norm": 0.11670713126659393,
+      "learning_rate": 5e-05,
+      "loss": 0.0092,
+      "step": 26
+    },
+    {
+      "epoch": 0.032130903681666045,
+      "grad_norm": 0.025358397513628006,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0006,
+      "step": 27
+    },
+    {
+      "epoch": 0.03332093715135738,
+      "grad_norm": 0.019817519932985306,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0024,
+      "step": 28
+    },
+    {
+      "epoch": 0.034510970621048714,
+      "grad_norm": 0.10703627020120621,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0031,
+      "step": 29
+    },
+    {
+      "epoch": 0.03570100409074005,
+      "grad_norm": 0.002817679662257433,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0001,
+      "step": 30
+    },
+    {
+      "epoch": 0.03689103756043139,
+      "grad_norm": 0.01130523532629013,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0002,
+      "step": 31
+    },
+    {
+      "epoch": 0.038081071030122725,
+      "grad_norm": 0.020346427336335182,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0003,
+      "step": 32
+    },
+    {
+      "epoch": 0.03927110449981406,
+      "grad_norm": 0.001904260367155075,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0001,
+      "step": 33
+    },
+    {
+      "epoch": 0.040461137969505394,
+      "grad_norm": 0.007746758870780468,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0002,
+      "step": 34
+    },
+    {
+      "epoch": 0.04165117143919673,
+      "grad_norm": 0.004477960988879204,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0001,
+      "step": 35
+    },
+    {
+      "epoch": 0.04284120490888806,
+      "grad_norm": 0.06279127299785614,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0049,
+      "step": 36
+    },
+    {
+      "epoch": 0.0440312383785794,
+      "grad_norm": 0.007732586935162544,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0002,
+      "step": 37
+    },
+    {
+      "epoch": 0.04522127184827073,
+      "grad_norm": 0.09072456508874893,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0066,
+      "step": 38
+    },
+    {
+      "epoch": 0.046411305317962066,
+      "grad_norm": 0.04076767712831497,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0017,
+      "step": 39
+    },
+    {
+      "epoch": 0.0476013387876534,
+      "grad_norm": 0.004594309721142054,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0001,
+      "step": 40
+    },
+    {
+      "epoch": 0.048791372257344735,
+      "grad_norm": 0.022521473467350006,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0023,
+      "step": 41
+    },
+    {
+      "epoch": 0.04998140572703607,
+      "grad_norm": 0.03882487118244171,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0002,
+      "step": 42
+    },
+    {
+      "epoch": 0.05117143919672741,
+      "grad_norm": 0.023141443729400635,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0003,
+      "step": 43
+    },
+    {
+      "epoch": 0.052361472666418746,
+      "grad_norm": 0.034502483904361725,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0056,
+      "step": 44
+    },
+    {
+      "epoch": 0.05355150613611008,
+      "grad_norm": 0.0009720915113575757,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.054741539605801415,
+      "grad_norm": 0.002274035941809416,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0001,
+      "step": 46
+    },
+    {
+      "epoch": 0.05593157307549275,
+      "grad_norm": 0.05807733163237572,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0067,
+      "step": 47
+    },
+    {
+      "epoch": 0.057121606545184084,
+      "grad_norm": 0.009669804945588112,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0003,
+      "step": 48
+    },
+    {
+      "epoch": 0.05831164001487542,
+      "grad_norm": 0.0655217170715332,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0009,
+      "step": 49
+    },
+    {
+      "epoch": 0.05950167348456675,
+      "grad_norm": 0.08589838445186615,
+      "learning_rate": 0.0,
+      "loss": 0.0107,
+      "step": 50
+    },
+    {
+      "epoch": 0.05950167348456675,
+      "eval_loss": 0.0017845286056399345,
+      "eval_runtime": 301.5784,
+      "eval_samples_per_second": 18.771,
+      "eval_steps_per_second": 2.348,
+      "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": 5.555785010511872e+17,
+  "total_flos": 1.1111570021023744e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null