Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4238ccb438801f9fc4c6600ab6454b39ad5a9a938a2a8a29b60d631e7b9580ad
+oid sha256:ad86049362070a296243b86a5db27e0f00f9d321c15bb7af836421316904e283
 size 524363632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f753dbbdf4ebd97aed3b6cd28ce3cf56ebaf9f4e23463ba294d96a810629aff
+oid sha256:64c57e4822e526bbedd59fe8125cae23ea6c32aff16db2c9d1edba795b4ae656
 size 1049049122

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95e1494687d47199e5e72f11c1b2b5b7ec74efcc1cdd56c2ce15c5bfb8e70fbb
+oid sha256:aac3505fab4c989c0d8859e7b7238bf35c42a9cadaed4fbcf35fda3adc7a58e0
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a184b85962db9c711c9c3d5b9e6296a03d15fe3cbe1bcb33e724ca22073eb88
+oid sha256:7f97f60482ca5b00847cdd8645ed0e3a562fa8332173f687f215ce84e83ade16
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f41f32fbca667c9fafba72d1fa978df785969e2b891d23f3074b9f569f4d5ed
+oid sha256:6fc43548f20349fc0a838b9914fe21152692c2a6be0995130d1647b2cc3b7608
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99e76dcca0e50804084ee9e55e84800de7784b2860d4782f31175312f10c9659
+oid sha256:97547d3b2d165aabf9ae5eb0e0a0dd357d3d79cc701a3408f66d555cd0bec250
 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": 0.9688600897789001,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.06591957811470006,
+  "best_metric": 0.9440848231315613,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.13183915622940012,
   "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": 20.421,
       "eval_steps_per_second": 2.558,
       "step": 25
+    },
+    {
+      "epoch": 0.06855636123928807,
+      "grad_norm": 1.7932987213134766,
+      "learning_rate": 5e-05,
+      "loss": 0.9886,
+      "step": 26
+    },
+    {
+      "epoch": 0.07119314436387607,
+      "grad_norm": 2.4545319080352783,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.1235,
+      "step": 27
+    },
+    {
+      "epoch": 0.07382992748846408,
+      "grad_norm": 2.206700325012207,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.088,
+      "step": 28
+    },
+    {
+      "epoch": 0.07646671061305207,
+      "grad_norm": 2.3057193756103516,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.0664,
+      "step": 29
+    },
+    {
+      "epoch": 0.07910349373764008,
+      "grad_norm": 2.116140842437744,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.0877,
+      "step": 30
+    },
+    {
+      "epoch": 0.08174027686222808,
+      "grad_norm": 1.8481568098068237,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.0048,
+      "step": 31
+    },
+    {
+      "epoch": 0.08437705998681608,
+      "grad_norm": 2.556462287902832,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.0342,
+      "step": 32
+    },
+    {
+      "epoch": 0.08701384311140409,
+      "grad_norm": 2.689141035079956,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.929,
+      "step": 33
+    },
+    {
+      "epoch": 0.08965062623599208,
+      "grad_norm": 3.946350336074829,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.8648,
+      "step": 34
+    },
+    {
+      "epoch": 0.0922874093605801,
+      "grad_norm": 3.916400671005249,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.7134,
+      "step": 35
+    },
+    {
+      "epoch": 0.09492419248516809,
+      "grad_norm": 5.732182502746582,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.7544,
+      "step": 36
+    },
+    {
+      "epoch": 0.0975609756097561,
+      "grad_norm": 8.657495498657227,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.8536,
+      "step": 37
+    },
+    {
+      "epoch": 0.1001977587343441,
+      "grad_norm": 9.490399360656738,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.0348,
+      "step": 38
+    },
+    {
+      "epoch": 0.10283454185893211,
+      "grad_norm": 1.175460934638977,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.0276,
+      "step": 39
+    },
+    {
+      "epoch": 0.1054713249835201,
+      "grad_norm": 1.179926872253418,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.0622,
+      "step": 40
+    },
+    {
+      "epoch": 0.10810810810810811,
+      "grad_norm": 1.2721707820892334,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.0583,
+      "step": 41
+    },
+    {
+      "epoch": 0.11074489123269611,
+      "grad_norm": 1.4001848697662354,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.0218,
+      "step": 42
+    },
+    {
+      "epoch": 0.1133816743572841,
+      "grad_norm": 1.6390767097473145,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.0694,
+      "step": 43
+    },
+    {
+      "epoch": 0.11601845748187212,
+      "grad_norm": 2.0891051292419434,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.02,
+      "step": 44
+    },
+    {
+      "epoch": 0.11865524060646011,
+      "grad_norm": 2.4620070457458496,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.9383,
+      "step": 45
+    },
+    {
+      "epoch": 0.12129202373104812,
+      "grad_norm": 2.9754490852355957,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.9056,
+      "step": 46
+    },
+    {
+      "epoch": 0.12392880685563612,
+      "grad_norm": 4.956353664398193,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.8469,
+      "step": 47
+    },
+    {
+      "epoch": 0.12656558998022413,
+      "grad_norm": 4.547539234161377,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.8408,
+      "step": 48
+    },
+    {
+      "epoch": 0.12920237310481214,
+      "grad_norm": 6.952060222625732,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.7187,
+      "step": 49
+    },
+    {
+      "epoch": 0.13183915622940012,
+      "grad_norm": 14.889754295349121,
+      "learning_rate": 0.0,
+      "loss": 0.9862,
+      "step": 50
+    },
+    {
+      "epoch": 0.13183915622940012,
+      "eval_loss": 0.9440848231315613,
+      "eval_runtime": 125.0915,
+      "eval_samples_per_second": 20.425,
+      "eval_steps_per_second": 2.558,
+      "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": 5.476375360176128e+17,
+  "total_flos": 1.0952750720352256e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null