Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27f7de58975ac58e8798fe0273f13453b94fdcb2e55fec197e0cf1c0ac6ef89e
+oid sha256:ee0e30140d009c2629d749fbab764f327b53070ba63f4ba766ee1be58f2671b4
 size 456206152

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6345e30900b7b03eb46baa0bb06490e92ce370189591a65aab53dc078d12ba73
+oid sha256:6fafc3c6089f45546ac46f86ced20de168ded642002daa60a3e765f23261f8ba
 size 912734242

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:762044f895db498d826a198ea352c03db8d3c8b1b9a88dbc34526b00701c66f0
+oid sha256:ff95b514febeac1a4524cf9d651f3b56b5e3470671a0c03845d5ef9dc900ffc0
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0d5125b99785623c7a3f73e28a2096d689febda5885b2c79e0e04ee73ae6127
+oid sha256:e502bec1102a63c2e35e273ed07c245cac690bb1b6bbf1d9024b683ddd2f89a8
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:819108c1637f3bfbdd9ed9fe61ebc4a945c98a589c0c071c97ac7eb61e340d8d
+oid sha256:c02e90af799c7735f86e9399088dd9688ad56acdc62846719611b950fdbc8dcd
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:128ccaac07f22508fb7733249fa237b0f162df5d0c7d62b344f8fce0890aa0bf
+oid sha256:dbf468c38bb08cc8df83c18f0185bcd3c00fe68dedbe1383df8ad6b8ddb43b4a
 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": 1.122847557067871,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.39564787339268054,
+  "best_metric": 1.0894900560379028,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.7912957467853611,
   "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": 23.225,
       "eval_steps_per_second": 2.944,
       "step": 25
+    },
+    {
+      "epoch": 0.4114737883283877,
+      "grad_norm": 9.869994163513184,
+      "learning_rate": 5e-05,
+      "loss": 1.0232,
+      "step": 26
+    },
+    {
+      "epoch": 0.42729970326409494,
+      "grad_norm": 9.686948776245117,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.0263,
+      "step": 27
+    },
+    {
+      "epoch": 0.4431256181998022,
+      "grad_norm": 10.00652027130127,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.002,
+      "step": 28
+    },
+    {
+      "epoch": 0.4589515331355094,
+      "grad_norm": 9.696783065795898,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.0132,
+      "step": 29
+    },
+    {
+      "epoch": 0.47477744807121663,
+      "grad_norm": 11.705400466918945,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.092,
+      "step": 30
+    },
+    {
+      "epoch": 0.49060336300692386,
+      "grad_norm": 10.257039070129395,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.0313,
+      "step": 31
+    },
+    {
+      "epoch": 0.506429277942631,
+      "grad_norm": 10.613300323486328,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.0224,
+      "step": 32
+    },
+    {
+      "epoch": 0.5222551928783383,
+      "grad_norm": 11.017250061035156,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.0769,
+      "step": 33
+    },
+    {
+      "epoch": 0.5380811078140455,
+      "grad_norm": 16.603017807006836,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.0977,
+      "step": 34
+    },
+    {
+      "epoch": 0.5539070227497527,
+      "grad_norm": 13.133756637573242,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.1007,
+      "step": 35
+    },
+    {
+      "epoch": 0.56973293768546,
+      "grad_norm": 15.047310829162598,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.1513,
+      "step": 36
+    },
+    {
+      "epoch": 0.5855588526211671,
+      "grad_norm": 17.72347640991211,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.1953,
+      "step": 37
+    },
+    {
+      "epoch": 0.6013847675568744,
+      "grad_norm": 12.774372100830078,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.0298,
+      "step": 38
+    },
+    {
+      "epoch": 0.6172106824925816,
+      "grad_norm": 8.430004119873047,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.9786,
+      "step": 39
+    },
+    {
+      "epoch": 0.6330365974282888,
+      "grad_norm": 8.151567459106445,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.9518,
+      "step": 40
+    },
+    {
+      "epoch": 0.6488625123639961,
+      "grad_norm": 10.981574058532715,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.0174,
+      "step": 41
+    },
+    {
+      "epoch": 0.6646884272997032,
+      "grad_norm": 10.649538040161133,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.0235,
+      "step": 42
+    },
+    {
+      "epoch": 0.6805143422354105,
+      "grad_norm": 10.363326072692871,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.0967,
+      "step": 43
+    },
+    {
+      "epoch": 0.6963402571711177,
+      "grad_norm": 11.041847229003906,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.0079,
+      "step": 44
+    },
+    {
+      "epoch": 0.712166172106825,
+      "grad_norm": 10.589798927307129,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.0251,
+      "step": 45
+    },
+    {
+      "epoch": 0.7279920870425322,
+      "grad_norm": 12.95122241973877,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.0545,
+      "step": 46
+    },
+    {
+      "epoch": 0.7438180019782393,
+      "grad_norm": 19.719316482543945,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.0717,
+      "step": 47
+    },
+    {
+      "epoch": 0.7596439169139466,
+      "grad_norm": 13.02059555053711,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.0867,
+      "step": 48
+    },
+    {
+      "epoch": 0.7754698318496538,
+      "grad_norm": 14.491941452026367,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.0927,
+      "step": 49
+    },
+    {
+      "epoch": 0.7912957467853611,
+      "grad_norm": 20.872737884521484,
+      "learning_rate": 0.0,
+      "loss": 1.1306,
+      "step": 50
+    },
+    {
+      "epoch": 0.7912957467853611,
+      "eval_loss": 1.0894900560379028,
+      "eval_runtime": 18.3462,
+      "eval_samples_per_second": 23.22,
+      "eval_steps_per_second": 2.943,
+      "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": 4.596980806320128e+17,
+  "total_flos": 9.193961612640256e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null