Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c81b5cbf5b844a37dbdf46da3618fa29caafd960ba4021511ed57e434edd2f2
+oid sha256:d18f12996ed344742e64ef863e98b30887c81bcd1733b056c15cc7568bc34b16
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e162d196773e7676dc0ab4db0bf5efc0769b4b980b1d1cd88818c1eabf712151
+oid sha256:f58e9bc235de0ed403dfdf56d98a23d2452c7c837a67710dfdf6f695d9526695
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa1253fbf8924a77310098537d960e243e39b335ad4591938ce4bd8f3a62bcf2
+oid sha256:5aff0c00f40fcdaf87b184777dd7595f5d1f867e4e8861d40fab2b59f3ae3015
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69c487e316ef3a6c7f6fa80d35fdcba8bd5f775fd840e7416a21a51860ce96d5
+oid sha256:83b9e4e2147a219379f578426becaa1e81c06a61463d38ac740b314536c7107f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28af93cbb409f0c87c6f7b5dc5f1ee7f66af4608a43b8206d349b16624affb7f
+oid sha256:631e5f54ba5c42fbdf360f6fc7f631b487150def6a21807bde3abfa6357743af
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddfcfa9692920a3290b401f4697bfa642bea6452cbbbbdd87cf606077b015f8a
+oid sha256:a570771cecf4fd1931d6a87a3f91cb983c682154ae47a759c6d7aa7df158cc05
 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": 1.6187020540237427,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.16999575010624735,
+  "best_metric": 1.5225000381469727,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.3399915002124947,
   "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": 10.185,
       "eval_steps_per_second": 2.648,
       "step": 25
+    },
+    {
+      "epoch": 0.17679558011049723,
+      "grad_norm": 0.41425418853759766,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.5504,
+      "step": 26
+    },
+    {
+      "epoch": 0.18359541011474714,
+      "grad_norm": 0.39358168840408325,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.5128,
+      "step": 27
+    },
+    {
+      "epoch": 0.19039524011899703,
+      "grad_norm": 0.3743652105331421,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.5086,
+      "step": 28
+    },
+    {
+      "epoch": 0.1971950701232469,
+      "grad_norm": 0.29533228278160095,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.4098,
+      "step": 29
+    },
+    {
+      "epoch": 0.20399490012749683,
+      "grad_norm": 0.3027362525463104,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.3184,
+      "step": 30
+    },
+    {
+      "epoch": 0.2107947301317467,
+      "grad_norm": 0.3000122606754303,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.234,
+      "step": 31
+    },
+    {
+      "epoch": 0.2175945601359966,
+      "grad_norm": 0.29423949122428894,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.3064,
+      "step": 32
+    },
+    {
+      "epoch": 0.22439439014024648,
+      "grad_norm": 0.3147090673446655,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.3182,
+      "step": 33
+    },
+    {
+      "epoch": 0.2311942201444964,
+      "grad_norm": 0.3395575284957886,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.4098,
+      "step": 34
+    },
+    {
+      "epoch": 0.23799405014874628,
+      "grad_norm": 0.41077926754951477,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.3439,
+      "step": 35
+    },
+    {
+      "epoch": 0.24479388015299616,
+      "grad_norm": 0.46304410696029663,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.5453,
+      "step": 36
+    },
+    {
+      "epoch": 0.2515937101572461,
+      "grad_norm": 0.6503234505653381,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.5968,
+      "step": 37
+    },
+    {
+      "epoch": 0.25839354016149596,
+      "grad_norm": 0.3714839816093445,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.523,
+      "step": 38
+    },
+    {
+      "epoch": 0.26519337016574585,
+      "grad_norm": 0.2543235719203949,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.5445,
+      "step": 39
+    },
+    {
+      "epoch": 0.27199320016999573,
+      "grad_norm": 0.2596566081047058,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.5307,
+      "step": 40
+    },
+    {
+      "epoch": 0.27879303017424567,
+      "grad_norm": 0.2656037509441376,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.4163,
+      "step": 41
+    },
+    {
+      "epoch": 0.28559286017849556,
+      "grad_norm": 0.24982349574565887,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.3385,
+      "step": 42
+    },
+    {
+      "epoch": 0.29239269018274544,
+      "grad_norm": 0.24610008299350739,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.2552,
+      "step": 43
+    },
+    {
+      "epoch": 0.2991925201869953,
+      "grad_norm": 0.2621634602546692,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.2534,
+      "step": 44
+    },
+    {
+      "epoch": 0.3059923501912452,
+      "grad_norm": 0.2883884012699127,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.2217,
+      "step": 45
+    },
+    {
+      "epoch": 0.3127921801954951,
+      "grad_norm": 0.31969720125198364,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.2927,
+      "step": 46
+    },
+    {
+      "epoch": 0.319592010199745,
+      "grad_norm": 0.3438730239868164,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.4063,
+      "step": 47
+    },
+    {
+      "epoch": 0.3263918402039949,
+      "grad_norm": 0.420473575592041,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.4759,
+      "step": 48
+    },
+    {
+      "epoch": 0.3331916702082448,
+      "grad_norm": 0.5387545824050903,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.5752,
+      "step": 49
+    },
+    {
+      "epoch": 0.3399915002124947,
+      "grad_norm": 0.875813901424408,
+      "learning_rate": 1e-05,
+      "loss": 1.7165,
+      "step": 50
+    },
+    {
+      "epoch": 0.3399915002124947,
+      "eval_loss": 1.5225000381469727,
+      "eval_runtime": 4.9,
+      "eval_samples_per_second": 10.204,
+      "eval_steps_per_second": 2.653,
+      "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": 2.7698250104858214e+17,
+  "total_flos": 5.513049055124521e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null