Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88a3eb617f459bdde4193857324a00f2eb85c0691af0c53435eaf2e8470dbf06
+oid sha256:9c5dd85d07aab78e647be6019ed8915087e58f709be2492d82f8c91b730fd0bf
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fc59b2ff247472bb1c976171060565a6e436a95400f68b6ae04c019cace8b2b
+oid sha256:56fb2c3b77042cf21e6a283bf6f922e0c82525a637bf8b8157fa2b8068604c7e
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a363c334654f1c68aad6807d6def25a18a36cdac3a1c6377b01ddb6524c5bc8
+oid sha256:aed583d19938bb1b45ad2e20567d2c61f29d4ebf7136af97835c06893b20e053
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:737c1874f128f7c5ce3db82472c9de5364ecd60e69e7cc03e50ab0a621ed8f9b
+oid sha256:1e9b97506b04bbea295b22169fad21a0acf92a464ed8318520911280bf25b6ed
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3e272f33531d07593cf8756fcdc1760d05de791a77e1aa446a0c43d73523823
+oid sha256:25ca9600684503fe69e7d6faa80f557ed1d7e36c7d7a1fbb19b8adf2ad7560c5
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc8e7f4e0a3b832a6238dbc5560ab0b11a20958e7310357cd10af03eb04c320e
+oid sha256:98dcc66433ab01b3189cb6208fa86d7527c2cebf59453b4b3ad80fe13c2276fb
 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": 0.22943511605262756,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.28198801550934083,
+  "best_metric": 0.18903478980064392,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.5639760310186817,
   "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": 9.714,
       "eval_steps_per_second": 2.526,
       "step": 25
+    },
+    {
+      "epoch": 0.2932675361297145,
+      "grad_norm": 2.8830854892730713,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.5776,
+      "step": 26
+    },
+    {
+      "epoch": 0.30454705675008814,
+      "grad_norm": 0.001804250292479992,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.31582657737046177,
+      "grad_norm": 0.018968435004353523,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0001,
+      "step": 28
+    },
+    {
+      "epoch": 0.3271060979908354,
+      "grad_norm": 0.08772213757038116,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.0002,
+      "step": 29
+    },
+    {
+      "epoch": 0.338385618611209,
+      "grad_norm": 0.06046594679355621,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0005,
+      "step": 30
+    },
+    {
+      "epoch": 0.34966513923158266,
+      "grad_norm": 0.09872586280107498,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.0001,
+      "step": 31
+    },
+    {
+      "epoch": 0.3609446598519563,
+      "grad_norm": 0.0029770503751933575,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.3722241804723299,
+      "grad_norm": 0.3427497148513794,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.0011,
+      "step": 33
+    },
+    {
+      "epoch": 0.38350370109270354,
+      "grad_norm": 0.006538857705891132,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0001,
+      "step": 34
+    },
+    {
+      "epoch": 0.39478322171307717,
+      "grad_norm": 0.0016080508939921856,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.40606274233345085,
+      "grad_norm": 0.00036259597982279956,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.4173422629538245,
+      "grad_norm": 0.00044910263386555016,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.4286217835741981,
+      "grad_norm": 3.9493634700775146,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.4749,
+      "step": 38
+    },
+    {
+      "epoch": 0.43990130419457174,
+      "grad_norm": 0.0019561927765607834,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.45118082481494537,
+      "grad_norm": 0.003831230802461505,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.462460345435319,
+      "grad_norm": 0.0014211925445124507,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.4737398660556926,
+      "grad_norm": 0.0003359741240274161,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.48501938667606626,
+      "grad_norm": 0.00035142392152920365,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.4962989072964399,
+      "grad_norm": 0.0010094629833474755,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.5075784279168135,
+      "grad_norm": 0.029661918058991432,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0003,
+      "step": 45
+    },
+    {
+      "epoch": 0.5188579485371871,
+      "grad_norm": 0.00044001490459777415,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.5301374691575608,
+      "grad_norm": 0.005407867021858692,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.5414169897779344,
+      "grad_norm": 0.0023250116501003504,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.552696510398308,
+      "grad_norm": 0.0011205272749066353,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.5639760310186817,
+      "grad_norm": 0.0002717706374824047,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.5639760310186817,
+      "eval_loss": 0.18903478980064392,
+      "eval_runtime": 5.157,
+      "eval_samples_per_second": 9.696,
+      "eval_steps_per_second": 2.521,
+      "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": 3.00828715674239e+17,
+  "total_flos": 6.019371851170447e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null