Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61f8a1378e26e298ddec5eac34f623c88e1da766981dd5c45e9803bfe1282436
+oid sha256:43151d966acc6737265dcfc6c3e30154ed7457db0d34585219a1705ff61042a6
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e023a6b42d67d299aba9655288f0ab5a774e7bdbef189a0112d22d8cdde1b57
+oid sha256:32a1df358459900687a7e01a2f62ec860c2a901361c0c34e1c2e93287ba982e8
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d51a55cca1578ced079e5de73c2df24e13df4a5009ec7bb7bf851f3c69f463e
+oid sha256:4c1072de1c69fa8179f10ec11b48cba14a12ec61ff205c44282656151a9477a2
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1197fd7ea210546eb0c76e01d350e26b376eff015b69dd29f7e70ed0046be036
+oid sha256:e33373ab18f12c507d326e8ff8e7196760c6858ad5449b0499b1f0c7e62485b7
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3ad2023324bef5425c01d25fff2aa0f0793c30294b1d46113fe8e097f754d85
+oid sha256:2d887527c3715a0667cceddbc10cb71725e69b7ee46050037ea038c078088212
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f793b40b3b40e8212724fec5ea453e25a90e23cfed37bf9f6fc3a2e00a5b905
+oid sha256:fad95af9ccc870168cf4c79c6c8b3ffde0476970b617db29ac9b0896e6088c54
 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": 0.2647845447063446,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.032435939020434644,
+  "best_metric": 0.15865732729434967,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.06487187804086929,
   "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": 7.163,
       "eval_steps_per_second": 0.897,
       "step": 25
+    },
+    {
+      "epoch": 0.03373337658125203,
+      "grad_norm": 1.2551417350769043,
+      "learning_rate": 5e-05,
+      "loss": 0.3919,
+      "step": 26
+    },
+    {
+      "epoch": 0.03503081414206941,
+      "grad_norm": 0.8644043803215027,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.2815,
+      "step": 27
+    },
+    {
+      "epoch": 0.036328251702886796,
+      "grad_norm": 1.071536898612976,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.3794,
+      "step": 28
+    },
+    {
+      "epoch": 0.03762568926370419,
+      "grad_norm": 0.9373099207878113,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.2419,
+      "step": 29
+    },
+    {
+      "epoch": 0.03892312682452157,
+      "grad_norm": 0.7272729873657227,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.2656,
+      "step": 30
+    },
+    {
+      "epoch": 0.040220564385338956,
+      "grad_norm": 0.6365888714790344,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.2369,
+      "step": 31
+    },
+    {
+      "epoch": 0.04151800194615634,
+      "grad_norm": 0.5733128786087036,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.2344,
+      "step": 32
+    },
+    {
+      "epoch": 0.042815439506973724,
+      "grad_norm": 0.8147559762001038,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.1945,
+      "step": 33
+    },
+    {
+      "epoch": 0.044112877067791115,
+      "grad_norm": 0.6627955436706543,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.1499,
+      "step": 34
+    },
+    {
+      "epoch": 0.0454103146286085,
+      "grad_norm": 0.686931848526001,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.2258,
+      "step": 35
+    },
+    {
+      "epoch": 0.04670775218942588,
+      "grad_norm": 0.6705523729324341,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.1502,
+      "step": 36
+    },
+    {
+      "epoch": 0.04800518975024327,
+      "grad_norm": 0.689427375793457,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.1622,
+      "step": 37
+    },
+    {
+      "epoch": 0.04930262731106066,
+      "grad_norm": 1.0235787630081177,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.2471,
+      "step": 38
+    },
+    {
+      "epoch": 0.05060006487187804,
+      "grad_norm": 1.1735961437225342,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.3028,
+      "step": 39
+    },
+    {
+      "epoch": 0.051897502432695426,
+      "grad_norm": 0.9888461232185364,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.2619,
+      "step": 40
+    },
+    {
+      "epoch": 0.05319493999351281,
+      "grad_norm": 0.5311381816864014,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.1487,
+      "step": 41
+    },
+    {
+      "epoch": 0.054492377554330194,
+      "grad_norm": 0.5367828011512756,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.1823,
+      "step": 42
+    },
+    {
+      "epoch": 0.055789815115147585,
+      "grad_norm": 0.4981409013271332,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.1559,
+      "step": 43
+    },
+    {
+      "epoch": 0.05708725267596497,
+      "grad_norm": 0.6254920959472656,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.1662,
+      "step": 44
+    },
+    {
+      "epoch": 0.058384690236782354,
+      "grad_norm": 0.5365238785743713,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.1845,
+      "step": 45
+    },
+    {
+      "epoch": 0.05968212779759974,
+      "grad_norm": 0.463119238615036,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.1534,
+      "step": 46
+    },
+    {
+      "epoch": 0.06097956535841713,
+      "grad_norm": 0.5386232733726501,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.1316,
+      "step": 47
+    },
+    {
+      "epoch": 0.06227700291923451,
+      "grad_norm": 0.4464093744754791,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0845,
+      "step": 48
+    },
+    {
+      "epoch": 0.0635744404800519,
+      "grad_norm": 0.5563793778419495,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.1266,
+      "step": 49
+    },
+    {
+      "epoch": 0.06487187804086929,
+      "grad_norm": 0.7688611149787903,
+      "learning_rate": 0.0,
+      "loss": 0.1718,
+      "step": 50
+    },
+    {
+      "epoch": 0.06487187804086929,
+      "eval_loss": 0.15865732729434967,
+      "eval_runtime": 719.7011,
+      "eval_samples_per_second": 7.215,
+      "eval_steps_per_second": 0.903,
+      "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