Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ec97a68d2ece69db8aa3ffc90aec7a03d6b7c391136419d732dae3f31486aa1
+oid sha256:6298d70e5f62448bef45884babd62f897586b8cedbe3046b972d2d117e27d450
 size 194563400

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03cdcd21f1c849019efe8c767e4a36488dbbc2fb975db3aaac32af991840fe56
+oid sha256:e04a13b949c73fd52a6e010e54fced1a108a166be51abea41ad0c93417a183f5
 size 389352298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80b276b82cb55b418e982a7ad79b12742a0c2e31029d5aa295da0e623d42b41a
+oid sha256:85416e5c5863bee702450311e32712b63107e40d6ece354d4a1ef4bd1a26ca83
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0def89e4ccd0851d694a32a226bd57c980d9abe745e8f5b8381a6865a27e0689
+oid sha256:1045d70e90564a39c503f7fba4ebcd1e7b9d686d0aeda0657682bc88c90b9314
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14192d10db628ee6052442e6e798b167002ae7ea6bbd702d659add2450a5f15d
+oid sha256:45c60b0646fd39dc0b82b4f3b7def365559e10c7a2c329c70883399c840970d4
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aafe325953d9cdda4a77be2ad76420891e30c5911150737da330cd73bb02e0e9
+oid sha256:a6fba47f89e0b7af37aa52353314fc4b5c994e33bc5c580098311aad2d960c35
 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": 1.9494298696517944,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.16161616161616163,
+  "best_metric": 1.9395381212234497,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.32323232323232326,
   "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": 55.164,
       "eval_steps_per_second": 6.929,
       "step": 25
+    },
+    {
+      "epoch": 0.16808080808080808,
+      "grad_norm": 0.10119690001010895,
+      "learning_rate": 5e-05,
+      "loss": 2.0909,
+      "step": 26
+    },
+    {
+      "epoch": 0.17454545454545456,
+      "grad_norm": 0.1081235408782959,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 2.0909,
+      "step": 27
+    },
+    {
+      "epoch": 0.181010101010101,
+      "grad_norm": 0.12175089120864868,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.0908,
+      "step": 28
+    },
+    {
+      "epoch": 0.1874747474747475,
+      "grad_norm": 0.13839766383171082,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 2.0257,
+      "step": 29
+    },
+    {
+      "epoch": 0.19393939393939394,
+      "grad_norm": 0.1502249538898468,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 2.0209,
+      "step": 30
+    },
+    {
+      "epoch": 0.20040404040404042,
+      "grad_norm": 0.16542190313339233,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.9956,
+      "step": 31
+    },
+    {
+      "epoch": 0.20686868686868687,
+      "grad_norm": 0.1611490398645401,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.9543,
+      "step": 32
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 0.1697140336036682,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.9624,
+      "step": 33
+    },
+    {
+      "epoch": 0.2197979797979798,
+      "grad_norm": 0.18247292935848236,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.8987,
+      "step": 34
+    },
+    {
+      "epoch": 0.22626262626262628,
+      "grad_norm": 0.2177690714597702,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.8438,
+      "step": 35
+    },
+    {
+      "epoch": 0.23272727272727273,
+      "grad_norm": 0.2801283895969391,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.8015,
+      "step": 36
+    },
+    {
+      "epoch": 0.2391919191919192,
+      "grad_norm": 0.3550100028514862,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.7079,
+      "step": 37
+    },
+    {
+      "epoch": 0.24565656565656566,
+      "grad_norm": 0.10651691257953644,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.0448,
+      "step": 38
+    },
+    {
+      "epoch": 0.25212121212121213,
+      "grad_norm": 0.10382003337144852,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.0345,
+      "step": 39
+    },
+    {
+      "epoch": 0.2585858585858586,
+      "grad_norm": 0.10816065967082977,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.0477,
+      "step": 40
+    },
+    {
+      "epoch": 0.26505050505050504,
+      "grad_norm": 0.13777312636375427,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 2.0325,
+      "step": 41
+    },
+    {
+      "epoch": 0.27151515151515154,
+      "grad_norm": 0.12429886311292648,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.9577,
+      "step": 42
+    },
+    {
+      "epoch": 0.277979797979798,
+      "grad_norm": 0.13117745518684387,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.0359,
+      "step": 43
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "grad_norm": 0.13389986753463745,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.9874,
+      "step": 44
+    },
+    {
+      "epoch": 0.2909090909090909,
+      "grad_norm": 0.14647652208805084,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.9679,
+      "step": 45
+    },
+    {
+      "epoch": 0.2973737373737374,
+      "grad_norm": 0.1532333493232727,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.9175,
+      "step": 46
+    },
+    {
+      "epoch": 0.30383838383838385,
+      "grad_norm": 0.1804121434688568,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.8934,
+      "step": 47
+    },
+    {
+      "epoch": 0.3103030303030303,
+      "grad_norm": 0.23982085287570953,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.7789,
+      "step": 48
+    },
+    {
+      "epoch": 0.31676767676767675,
+      "grad_norm": 0.3199950158596039,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.7638,
+      "step": 49
+    },
+    {
+      "epoch": 0.32323232323232326,
+      "grad_norm": 0.4603963792324066,
+      "learning_rate": 0.0,
+      "loss": 1.7108,
+      "step": 50
+    },
+    {
+      "epoch": 0.32323232323232326,
+      "eval_loss": 1.9395381212234497,
+      "eval_runtime": 18.9224,
+      "eval_samples_per_second": 55.12,
+      "eval_steps_per_second": 6.923,
+      "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": 1.127497768894464e+17,
+  "total_flos": 2.254995537788928e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null