Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:210c43450ee534ff4b1b45252f486feeba835d7bb3951e35a3d61925cfd991e3
+oid sha256:1fceef7f91ae2767b349c55ff5371567037b0dabc0f320302e305c8ef0e438bb
 size 500770656

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c586c69fa7c05f27d62f5f2558c71c72f8c9a592638b4e1d5a2bc532b7352de
+oid sha256:7efda1a11e4d8bc602abdcd2a65adc62afc75d90796c3c30ecc8292caeae81eb
 size 1001863522

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64b619e76c9e56b51826f937e756455869085bc8b9b510d1c1d8ae453e3fca16
+oid sha256:b674abe9436e9b97b8d92c5ba7e6754b21ae06f49bdc63e64e5ea8361ca77e95
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02498c5f2877d044eca2357d48b9614c461ea4e137cf5d0958754d866fb2e6b7
+oid sha256:898c5c1ef4ac43fae65e200839a6ad6ad755feb201a4277ab787a5a668115049
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcefda907d41a05cd0d84a22e164ae93625e74c61eef79a6df2ce12fab3036f7
+oid sha256:32e27d910b8f252abb4b844a4bf77c8592eb87ed29059df47bfe567fbdc786c1
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:582a3c1e24f2e46b687332536e8124ac7e87bbf825eac5752f157d1c24bdbdb0
+oid sha256:d749e288e3f994418e09fc5698f709f549d1261d19cbeb213f2f8b2c15f71111
 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": 0.3183044195175171,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.023789699060306885,
+  "best_metric": 0.3009062111377716,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.04757939812061377,
   "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": 22.341,
       "eval_steps_per_second": 2.793,
       "step": 25
+    },
+    {
+      "epoch": 0.024741287022719164,
+      "grad_norm": 0.4331679046154022,
+      "learning_rate": 5e-05,
+      "loss": 0.3114,
+      "step": 26
+    },
+    {
+      "epoch": 0.02569287498513144,
+      "grad_norm": 0.37552371621131897,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.3306,
+      "step": 27
+    },
+    {
+      "epoch": 0.026644462947543714,
+      "grad_norm": 0.3065773844718933,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.3101,
+      "step": 28
+    },
+    {
+      "epoch": 0.02759605090995599,
+      "grad_norm": 0.3482958972454071,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.3635,
+      "step": 29
+    },
+    {
+      "epoch": 0.028547638872368265,
+      "grad_norm": 0.28071439266204834,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.3249,
+      "step": 30
+    },
+    {
+      "epoch": 0.02949922683478054,
+      "grad_norm": 0.29683056473731995,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.3202,
+      "step": 31
+    },
+    {
+      "epoch": 0.030450814797192815,
+      "grad_norm": 0.3477626442909241,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.3242,
+      "step": 32
+    },
+    {
+      "epoch": 0.03140240275960509,
+      "grad_norm": 0.45291534066200256,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.2807,
+      "step": 33
+    },
+    {
+      "epoch": 0.03235399072201737,
+      "grad_norm": 0.4736618995666504,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.3729,
+      "step": 34
+    },
+    {
+      "epoch": 0.03330557868442964,
+      "grad_norm": 0.3130555748939514,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.3032,
+      "step": 35
+    },
+    {
+      "epoch": 0.03425716664684192,
+      "grad_norm": 0.4449267089366913,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.3466,
+      "step": 36
+    },
+    {
+      "epoch": 0.03520875460925419,
+      "grad_norm": 0.31513071060180664,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.3688,
+      "step": 37
+    },
+    {
+      "epoch": 0.03616034257166647,
+      "grad_norm": 0.3374822437763214,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.3219,
+      "step": 38
+    },
+    {
+      "epoch": 0.03711193053407874,
+      "grad_norm": 0.2929448187351227,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.3866,
+      "step": 39
+    },
+    {
+      "epoch": 0.03806351849649102,
+      "grad_norm": 0.26822617650032043,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.2781,
+      "step": 40
+    },
+    {
+      "epoch": 0.0390151064589033,
+      "grad_norm": 0.23648488521575928,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.2547,
+      "step": 41
+    },
+    {
+      "epoch": 0.03996669442131557,
+      "grad_norm": 0.2830832004547119,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.3341,
+      "step": 42
+    },
+    {
+      "epoch": 0.04091828238372785,
+      "grad_norm": 0.30678245425224304,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.3192,
+      "step": 43
+    },
+    {
+      "epoch": 0.04186987034614012,
+      "grad_norm": 0.2609436511993408,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.2764,
+      "step": 44
+    },
+    {
+      "epoch": 0.0428214583085524,
+      "grad_norm": 0.2292177975177765,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.2895,
+      "step": 45
+    },
+    {
+      "epoch": 0.04377304627096467,
+      "grad_norm": 0.29264628887176514,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.3456,
+      "step": 46
+    },
+    {
+      "epoch": 0.04472463423337695,
+      "grad_norm": 0.29742947220802307,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.2929,
+      "step": 47
+    },
+    {
+      "epoch": 0.04567622219578922,
+      "grad_norm": 0.3194923996925354,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.4462,
+      "step": 48
+    },
+    {
+      "epoch": 0.0466278101582015,
+      "grad_norm": 0.3254033327102661,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.2784,
+      "step": 49
+    },
+    {
+      "epoch": 0.04757939812061377,
+      "grad_norm": 0.30053213238716125,
+      "learning_rate": 0.0,
+      "loss": 0.3422,
+      "step": 50
+    },
+    {
+      "epoch": 0.04757939812061377,
+      "eval_loss": 0.3009062111377716,
+      "eval_runtime": 317.1922,
+      "eval_samples_per_second": 22.321,
+      "eval_steps_per_second": 2.79,
+      "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": 5.102842054443008e+17,
+  "total_flos": 1.0205684108886016e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null