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:ec50516f3874d6d1115516439724ff3f2704b4657dac93f94afc07f7f6cb0d6b
+oid sha256:e832d6a0b290cf7ba34bd10b442d840ca151e156448f792822fb4c7e98363ead
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8893ed449be3c6e7e7db449955c8bfbdfc72bbc678b8d2bc4c2f53aa9960d77c
+oid sha256:725268fec9f41c1c6193f897d1ad8e6639b70476ea978a8e970def2e607f5798
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b288c08ffb356da813aea4d51330c2bdf7a1c71a5d03ad34e7b40ab9f1c10152
+oid sha256:b3da4b3aa724e139f12e62827de654305e68dd97ff17e8805a960b0a0d40762e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf437d54592839a1a1f0d1fdaa565a15e2d9ad663d3b3733b9a5450a971c8cf1
+oid sha256:b8a9aece79bc3a6459209878b19432b412c580814697e063ebc7fc02dd2d1686
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cb7746e248ba9ff875d0dcc7257ef651c1f23d3b5c8227b91638182a297ec13
+oid sha256:bd2aa693d85fa2567dc4bad8cb5446656f947ece017a2ea1d7177da7f6b60e6f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ac609f247543cee40407f295f6b86fd8d234522bdbf61b17cb18f2deb141580
+oid sha256:bf0a378687e9be116f603c0e10199415b4295449f309b39822fa4dbec325389a
 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": 0.003844380145892501,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.018443378827001106,
+  "best_metric": 0.0013253026409074664,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.03688675765400221,
   "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": 14.798,
       "eval_steps_per_second": 1.851,
       "step": 25
+    },
+    {
+      "epoch": 0.01918111398008115,
+      "grad_norm": 0.17327414453029633,
+      "learning_rate": 5e-05,
+      "loss": 0.0063,
+      "step": 26
+    },
+    {
+      "epoch": 0.019918849133161196,
+      "grad_norm": 0.27742308378219604,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0054,
+      "step": 27
+    },
+    {
+      "epoch": 0.020656584286241238,
+      "grad_norm": 0.519931972026825,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0059,
+      "step": 28
+    },
+    {
+      "epoch": 0.021394319439321283,
+      "grad_norm": 0.061371006071567535,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0011,
+      "step": 29
+    },
+    {
+      "epoch": 0.022132054592401328,
+      "grad_norm": 0.030833333730697632,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0005,
+      "step": 30
+    },
+    {
+      "epoch": 0.022869789745481373,
+      "grad_norm": 0.030925383791327477,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0006,
+      "step": 31
+    },
+    {
+      "epoch": 0.023607524898561418,
+      "grad_norm": 0.25980839133262634,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0181,
+      "step": 32
+    },
+    {
+      "epoch": 0.02434526005164146,
+      "grad_norm": 0.2763437330722809,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0069,
+      "step": 33
+    },
+    {
+      "epoch": 0.025082995204721504,
+      "grad_norm": 0.21243636310100555,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.004,
+      "step": 34
+    },
+    {
+      "epoch": 0.02582073035780155,
+      "grad_norm": 0.16072770953178406,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.006,
+      "step": 35
+    },
+    {
+      "epoch": 0.026558465510881594,
+      "grad_norm": 0.09806128591299057,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0006,
+      "step": 36
+    },
+    {
+      "epoch": 0.02729620066396164,
+      "grad_norm": 0.2226666510105133,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0097,
+      "step": 37
+    },
+    {
+      "epoch": 0.028033935817041684,
+      "grad_norm": 0.038759976625442505,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0005,
+      "step": 38
+    },
+    {
+      "epoch": 0.028771670970121725,
+      "grad_norm": 0.027910703793168068,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0005,
+      "step": 39
+    },
+    {
+      "epoch": 0.02950940612320177,
+      "grad_norm": 0.02285999432206154,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0004,
+      "step": 40
+    },
+    {
+      "epoch": 0.030247141276281815,
+      "grad_norm": 0.03520093858242035,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0009,
+      "step": 41
+    },
+    {
+      "epoch": 0.03098487642936186,
+      "grad_norm": 0.0282539501786232,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0004,
+      "step": 42
+    },
+    {
+      "epoch": 0.031722611582441905,
+      "grad_norm": 0.017113978043198586,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0004,
+      "step": 43
+    },
+    {
+      "epoch": 0.03246034673552195,
+      "grad_norm": 0.028783045709133148,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0005,
+      "step": 44
+    },
+    {
+      "epoch": 0.033198081888601995,
+      "grad_norm": 0.007767962757498026,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0002,
+      "step": 45
+    },
+    {
+      "epoch": 0.03393581704168203,
+      "grad_norm": 0.07338442653417587,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0006,
+      "step": 46
+    },
+    {
+      "epoch": 0.03467355219476208,
+      "grad_norm": 0.022086704149842262,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0006,
+      "step": 47
+    },
+    {
+      "epoch": 0.03541128734784212,
+      "grad_norm": 0.002825175179168582,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0001,
+      "step": 48
+    },
+    {
+      "epoch": 0.03614902250092217,
+      "grad_norm": 0.06952456384897232,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0006,
+      "step": 49
+    },
+    {
+      "epoch": 0.03688675765400221,
+      "grad_norm": 0.06509310752153397,
+      "learning_rate": 0.0,
+      "loss": 0.0008,
+      "step": 50
+    },
+    {
+      "epoch": 0.03688675765400221,
+      "eval_loss": 0.0013253026409074664,
+      "eval_runtime": 618.4418,
+      "eval_samples_per_second": 14.766,
+      "eval_steps_per_second": 1.847,
+      "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": 2.9859068337822106e+17,
+  "total_flos": 5.969948642440643e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null