Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33c379a385f135f2e95660ccda3cf361b3a5672d258f65378e0a7eb01a1294b6
+oid sha256:9aaff10e159ba194ae6518274d71d77aa366a78c40664615f413eb0f63af3a69
 size 432223744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a09a4a7f8a3414a3a44d3df42f56d71934af861b901acaa65bef07a2c35724f
+oid sha256:0d920bdf0070a7b953b5df0e2b81779e3ad41dc26877cb4ff98054f439588691
 size 864785974

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04fd424bfddedd71ebab065e85e5179f9fffa58178f47d3c89c772f56f17fd21
+oid sha256:e9fee207f1d6976751fc9439bdc1bdba92686a87c9980e44dc73c3871cde11cb
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea0f1915f27864d9a28c74467f533dbcece4565487e2ae9e4be257ea22c26505
+oid sha256:acbf5d96eb4e590e5900d4a0fd05f97a018c1c842da925ef924e7b9da84c452f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dc6c71ab8f7cc04543f2c1fcf87a6ad9ba4ece7efb17a6e9c4f8af4d27f88cd
+oid sha256:cc3753f7c5fe63d5991a5d38439c4e8ecb12c17bd8047b081ee396c2c66ab6ec
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca0def8fce7d42ae025cfdd30f23266f2ce76ab4e04efd524e394b438a441dca
+oid sha256:ea697d00c686d3edb31c0fdf6ad89e8a1f2c82e5418b5a2e5a05bf435ddd7334
 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": 0.29774895310401917,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.7194244604316546,
+  "best_metric": 0.21533425152301788,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.4406474820143884,
   "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": 25.222,
       "eval_steps_per_second": 3.234,
       "step": 25
+    },
+    {
+      "epoch": 0.7482014388489209,
+      "grad_norm": 1.5737944841384888,
+      "learning_rate": 5e-05,
+      "loss": 0.2944,
+      "step": 26
+    },
+    {
+      "epoch": 0.7769784172661871,
+      "grad_norm": 1.186069130897522,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.3601,
+      "step": 27
+    },
+    {
+      "epoch": 0.8057553956834532,
+      "grad_norm": 1.3156697750091553,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.4084,
+      "step": 28
+    },
+    {
+      "epoch": 0.8345323741007195,
+      "grad_norm": 0.8197304010391235,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.3833,
+      "step": 29
+    },
+    {
+      "epoch": 0.8633093525179856,
+      "grad_norm": 0.7455169558525085,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.3442,
+      "step": 30
+    },
+    {
+      "epoch": 0.8920863309352518,
+      "grad_norm": 0.647731363773346,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.2965,
+      "step": 31
+    },
+    {
+      "epoch": 0.920863309352518,
+      "grad_norm": 0.9201293587684631,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.182,
+      "step": 32
+    },
+    {
+      "epoch": 0.9496402877697842,
+      "grad_norm": 0.8363877534866333,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.1878,
+      "step": 33
+    },
+    {
+      "epoch": 0.9784172661870504,
+      "grad_norm": 0.5325927734375,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.1111,
+      "step": 34
+    },
+    {
+      "epoch": 1.0089928057553956,
+      "grad_norm": 1.7002311944961548,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.3383,
+      "step": 35
+    },
+    {
+      "epoch": 1.0377697841726619,
+      "grad_norm": 4.443037509918213,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.5528,
+      "step": 36
+    },
+    {
+      "epoch": 1.066546762589928,
+      "grad_norm": 2.736210346221924,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.4109,
+      "step": 37
+    },
+    {
+      "epoch": 1.0953237410071943,
+      "grad_norm": 1.8709927797317505,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.3634,
+      "step": 38
+    },
+    {
+      "epoch": 1.1241007194244603,
+      "grad_norm": 1.336185097694397,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.3063,
+      "step": 39
+    },
+    {
+      "epoch": 1.1528776978417266,
+      "grad_norm": 0.8743398189544678,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.2986,
+      "step": 40
+    },
+    {
+      "epoch": 1.1816546762589928,
+      "grad_norm": 1.1188706159591675,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.2025,
+      "step": 41
+    },
+    {
+      "epoch": 1.210431654676259,
+      "grad_norm": 0.7593362331390381,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.1725,
+      "step": 42
+    },
+    {
+      "epoch": 1.2392086330935252,
+      "grad_norm": 0.6174198985099792,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.1326,
+      "step": 43
+    },
+    {
+      "epoch": 1.2679856115107913,
+      "grad_norm": 0.37820106744766235,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.261,
+      "step": 44
+    },
+    {
+      "epoch": 1.2967625899280575,
+      "grad_norm": 0.6265496015548706,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.3512,
+      "step": 45
+    },
+    {
+      "epoch": 1.3255395683453237,
+      "grad_norm": 0.5311719179153442,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.3005,
+      "step": 46
+    },
+    {
+      "epoch": 1.35431654676259,
+      "grad_norm": 0.6251354217529297,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.3055,
+      "step": 47
+    },
+    {
+      "epoch": 1.3830935251798562,
+      "grad_norm": 0.7828004956245422,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.2657,
+      "step": 48
+    },
+    {
+      "epoch": 1.4118705035971222,
+      "grad_norm": 0.9686384201049805,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.2564,
+      "step": 49
+    },
+    {
+      "epoch": 1.4406474820143884,
+      "grad_norm": 0.9383431077003479,
+      "learning_rate": 0.0,
+      "loss": 0.2077,
+      "step": 50
+    },
+    {
+      "epoch": 1.4406474820143884,
+      "eval_loss": 0.21533425152301788,
+      "eval_runtime": 9.3202,
+      "eval_samples_per_second": 25.107,
+      "eval_steps_per_second": 3.219,
+      "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": 3.317763172739318e+17,
+  "total_flos": 6.635526345478636e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null