Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25b1f94eaf6d39551a78ad778692a7d42f8ff5c178880051219ea14aeb94cdf2
+oid sha256:11e350d2759276c2f728c85e79854887ad9c1c944be09ff93135a5dd0be7899a
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b29ebc56513c0dba57f09b3e0433e759241e786c657aaf5e284a0f7e4efcf0c9
+oid sha256:26c5a921db4fc5f79cdbaddf76c4b44fb8f21b35e3babd2bdcd71701b8d0fe8d
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:801d7d83c24c40916f58076e00c4f26fea64e52541ba92058ab844df3c09d4d6
+oid sha256:5d4bc7bd355a3ddeda1b0d0c83f49b30fb3a31890641ae70f7ebf862afe3fd92
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05d983889f868d5371022e69eaef589aee748a9dbe66ba73c77df8dd836e299c
+oid sha256:ae91023a435252b323366bd5c1a9210da3d37d0abed5518699297bbd167a2ea6
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4d97584e062f4742bfc7f75f541ca4dee1675e2a1e19a646f806031bbb56085
+oid sha256:228191e181c69e263b04f93740d502c760e8ee44a9a2a3be15cfef6781d4cce3
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:249d461cf3b5745c3c53b789a803f560f925013a6b22f7b4940b1b6926de54e6
+oid sha256:5d226d8b101d1c380fc8dff8b7d458949a74c1584eb730496e1977723528db09
 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": 3.5550496249925345e-05,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.08131734092295181,
+  "best_metric": 2.4327282517333515e-05,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.16263468184590363,
   "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": 28.561,
       "eval_steps_per_second": 7.426,
       "step": 25
+    },
+    {
+      "epoch": 0.08457003455986989,
+      "grad_norm": 0.1755603402853012,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0015,
+      "step": 26
+    },
+    {
+      "epoch": 0.08782272819678796,
+      "grad_norm": 1.3422788381576538,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.0087,
+      "step": 27
+    },
+    {
+      "epoch": 0.09107542183370604,
+      "grad_norm": 3.2834012508392334,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0199,
+      "step": 28
+    },
+    {
+      "epoch": 0.09432811547062411,
+      "grad_norm": 1.0278654098510742,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.0039,
+      "step": 29
+    },
+    {
+      "epoch": 0.09758080910754219,
+      "grad_norm": 0.008438934572041035,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0006,
+      "step": 30
+    },
+    {
+      "epoch": 0.10083350274446026,
+      "grad_norm": 0.0395902544260025,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.0009,
+      "step": 31
+    },
+    {
+      "epoch": 0.10408619638137832,
+      "grad_norm": 0.2128855437040329,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0025,
+      "step": 32
+    },
+    {
+      "epoch": 0.1073388900182964,
+      "grad_norm": 0.010209944099187851,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.0009,
+      "step": 33
+    },
+    {
+      "epoch": 0.11059158365521447,
+      "grad_norm": 0.040100499987602234,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0011,
+      "step": 34
+    },
+    {
+      "epoch": 0.11384427729213255,
+      "grad_norm": 0.012900767847895622,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.0008,
+      "step": 35
+    },
+    {
+      "epoch": 0.11709697092905062,
+      "grad_norm": 0.06265828758478165,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.0021,
+      "step": 36
+    },
+    {
+      "epoch": 0.1203496645659687,
+      "grad_norm": 0.05355784669518471,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.0017,
+      "step": 37
+    },
+    {
+      "epoch": 0.12360235820288677,
+      "grad_norm": 2.6918680667877197,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.101,
+      "step": 38
+    },
+    {
+      "epoch": 0.12685505183980483,
+      "grad_norm": 1.0052647590637207,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0202,
+      "step": 39
+    },
+    {
+      "epoch": 0.1301077454767229,
+      "grad_norm": 0.16937710344791412,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0014,
+      "step": 40
+    },
+    {
+      "epoch": 0.13336043911364098,
+      "grad_norm": 0.006115274969488382,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0006,
+      "step": 41
+    },
+    {
+      "epoch": 0.13661313275055906,
+      "grad_norm": 0.027183569967746735,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0008,
+      "step": 42
+    },
+    {
+      "epoch": 0.13986582638747713,
+      "grad_norm": 0.036184392869472504,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0013,
+      "step": 43
+    },
+    {
+      "epoch": 0.1431185200243952,
+      "grad_norm": 0.00422509852796793,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0004,
+      "step": 44
+    },
+    {
+      "epoch": 0.14637121366131328,
+      "grad_norm": 0.01154299546033144,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0007,
+      "step": 45
+    },
+    {
+      "epoch": 0.14962390729823136,
+      "grad_norm": 0.010334019549190998,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0008,
+      "step": 46
+    },
+    {
+      "epoch": 0.15287660093514943,
+      "grad_norm": 1.308108925819397,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0027,
+      "step": 47
+    },
+    {
+      "epoch": 0.1561292945720675,
+      "grad_norm": 0.007694561965763569,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0005,
+      "step": 48
+    },
+    {
+      "epoch": 0.15938198820898555,
+      "grad_norm": 0.006533082574605942,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0006,
+      "step": 49
+    },
+    {
+      "epoch": 0.16263468184590363,
+      "grad_norm": 0.011260352097451687,
+      "learning_rate": 1e-05,
+      "loss": 0.0007,
+      "step": 50
+    },
+    {
+      "epoch": 0.16263468184590363,
+      "eval_loss": 2.4327282517333515e-05,
+      "eval_runtime": 1.7631,
+      "eval_samples_per_second": 28.36,
+      "eval_steps_per_second": 7.374,
+      "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": 2.629578157719552e+17,
+  "total_flos": 5.259156315439104e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null