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:abe3172d893d4b05b0cf861879099e73cf62149527c45a506f1de0bb2ca0cd14
+oid sha256:72a227222e615cd0e4b72a1d83977cc335afe794adfc7213783d9e1723f34d88
 size 400084608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b05dbb965181e0f72bb2052a8026dbb70c920819443d405584d3b5f444afceba
+oid sha256:ab74105eba143459122956ad28dadb484b55e2d8997cb75d75038ee30f65ca15
 size 800394282

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbb2792eb3d45dcd70ce13b0d300e85f158c19c1d8c1951ba5eaeeccc5a5ee49
+oid sha256:a3eb5d44ee7d9e387a83f2ef09e5c7b959b49f49780dbce1d845610dff6dae94
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14245c420859b5408b046981499c9754688a73d7d1e07aaee96997ca8883e5cf
+oid sha256:c1e611a2e89d7029f8381cd7d8b030018ad25b7d733e411acdbe993cb36201c1
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3938e6c00d6501a53a59c0c2b78e9eec79bc9c3a1e48108da23f7c006a6907a4
+oid sha256:8a62e237303af5c0a4263f774f623e93bed0768951ddb1ab4c115a7e784c78c8
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:667e0e681b7727ca0a431ce23b4907cf4981f19d48c467648b508f8dc7ffe3de
+oid sha256:bac7b9321d2275ad35b4eb635d8c0cd4518b80f07cb1e8fbd74c0b9187a2d916
 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": 0.31171107292175293,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.07108583614714768,
+  "best_metric": 0.26503002643585205,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.14217167229429536,
   "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": 12.476,
       "eval_steps_per_second": 3.244,
       "step": 25
+    },
+    {
+      "epoch": 0.07392926959303359,
+      "grad_norm": 1.1360609531402588,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.3498,
+      "step": 26
+    },
+    {
+      "epoch": 0.07677270303891949,
+      "grad_norm": 1.0913562774658203,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.3328,
+      "step": 27
+    },
+    {
+      "epoch": 0.07961613648480541,
+      "grad_norm": 2.2489614486694336,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.3531,
+      "step": 28
+    },
+    {
+      "epoch": 0.08245956993069131,
+      "grad_norm": 1.245743751525879,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.3458,
+      "step": 29
+    },
+    {
+      "epoch": 0.08530300337657722,
+      "grad_norm": 0.9143818616867065,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.3279,
+      "step": 30
+    },
+    {
+      "epoch": 0.08814643682246312,
+      "grad_norm": 0.9616953134536743,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.3483,
+      "step": 31
+    },
+    {
+      "epoch": 0.09098987026834904,
+      "grad_norm": 1.3551769256591797,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.3119,
+      "step": 32
+    },
+    {
+      "epoch": 0.09383330371423494,
+      "grad_norm": 0.7638424038887024,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.2966,
+      "step": 33
+    },
+    {
+      "epoch": 0.09667673716012085,
+      "grad_norm": 0.7949358820915222,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.3511,
+      "step": 34
+    },
+    {
+      "epoch": 0.09952017060600675,
+      "grad_norm": 0.8913821578025818,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.3015,
+      "step": 35
+    },
+    {
+      "epoch": 0.10236360405189265,
+      "grad_norm": 1.1559334993362427,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.3538,
+      "step": 36
+    },
+    {
+      "epoch": 0.10520703749777857,
+      "grad_norm": 1.223947286605835,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.3099,
+      "step": 37
+    },
+    {
+      "epoch": 0.10805047094366448,
+      "grad_norm": 0.9780659675598145,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.306,
+      "step": 38
+    },
+    {
+      "epoch": 0.11089390438955038,
+      "grad_norm": 1.0553867816925049,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.318,
+      "step": 39
+    },
+    {
+      "epoch": 0.11373733783543628,
+      "grad_norm": 1.149210810661316,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.2961,
+      "step": 40
+    },
+    {
+      "epoch": 0.1165807712813222,
+      "grad_norm": 1.1460851430892944,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.2907,
+      "step": 41
+    },
+    {
+      "epoch": 0.1194242047272081,
+      "grad_norm": 1.234253168106079,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.3047,
+      "step": 42
+    },
+    {
+      "epoch": 0.12226763817309401,
+      "grad_norm": 1.5525425672531128,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.3576,
+      "step": 43
+    },
+    {
+      "epoch": 0.1251110716189799,
+      "grad_norm": 1.1359039545059204,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.3114,
+      "step": 44
+    },
+    {
+      "epoch": 0.12795450506486583,
+      "grad_norm": 1.2153254747390747,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.3103,
+      "step": 45
+    },
+    {
+      "epoch": 0.13079793851075172,
+      "grad_norm": 1.3485732078552246,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.3211,
+      "step": 46
+    },
+    {
+      "epoch": 0.13364137195663764,
+      "grad_norm": 0.954004168510437,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.2795,
+      "step": 47
+    },
+    {
+      "epoch": 0.13648480540252356,
+      "grad_norm": 0.9658924341201782,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.3035,
+      "step": 48
+    },
+    {
+      "epoch": 0.13932823884840945,
+      "grad_norm": 0.9231831431388855,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.2799,
+      "step": 49
+    },
+    {
+      "epoch": 0.14217167229429536,
+      "grad_norm": 0.8936429619789124,
+      "learning_rate": 1e-05,
+      "loss": 0.2711,
+      "step": 50
+    },
+    {
+      "epoch": 0.14217167229429536,
+      "eval_loss": 0.26503002643585205,
+      "eval_runtime": 4.0026,
+      "eval_samples_per_second": 12.492,
+      "eval_steps_per_second": 3.248,
+      "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": 3.087239672233984e+17,
+  "total_flos": 6.174479344467968e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null