Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47abcd15db3fad77036d3b80fd97cba1df32e91d23fe66c81fe45ccbd72cce3a
+oid sha256:14432f33fb6c9bf4a7cdfc52f9baa452259dfc0380749673594a67c778e062bf
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aded3b91ad383c2070d579bbbf84ecbb76223406ed0c647e6c2438dd0e4c74e7
+oid sha256:9332005f05c8d9f87d03913517971ec0c4b86b318c5543c0fff8f2a9b9e7b9be
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:769aecb7765c7bfc8b1e5f9b8c8b350d99e3e66352ec4df63882f791f0105c92
+oid sha256:d7db8f4c040c768012c59b1888f3fcd75fe7b72eddb11d4cae32263d723cc414
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c91c84085a9d4d3d513e14f19f1f85b52949468ac57abcc1c72a0b0b41699b0
+oid sha256:47cba121b4c81b08c1ba2abc78fdd5aa7c9bb1778fdb067923485f887a0ed3a1
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17a1ce19b19ca527e3380a641673dfb5aff9fb5bce91c96bf6ac78709a5efe72
+oid sha256:9483a47174e5ba0eeb725399ebde36b560deec63888a6457c358aba73cbbca78
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0966bd9479508653360c9f7e5e003e4a9f5d4442ac56843c136661894df89311
+oid sha256:b92c5b678903e3456502d645cc73cc12bf7d31de76aca9aab51ad7618c6c51e9
 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": 0.6997354626655579,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.23894862604540024,
+  "best_metric": 0.6973173022270203,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.4778972520908005,
   "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": 24.604,
       "eval_steps_per_second": 6.397,
       "step": 25
+    },
+    {
+      "epoch": 0.24850657108721624,
+      "grad_norm": 0.7586610913276672,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.7004,
+      "step": 26
+    },
+    {
+      "epoch": 0.25806451612903225,
+      "grad_norm": 1.076542854309082,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.6972,
+      "step": 27
+    },
+    {
+      "epoch": 0.26762246117084826,
+      "grad_norm": 1.4424303770065308,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.6967,
+      "step": 28
+    },
+    {
+      "epoch": 0.27718040621266427,
+      "grad_norm": 1.472855806350708,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.7022,
+      "step": 29
+    },
+    {
+      "epoch": 0.2867383512544803,
+      "grad_norm": 0.6519089341163635,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.6861,
+      "step": 30
+    },
+    {
+      "epoch": 0.2962962962962963,
+      "grad_norm": 1.0849039554595947,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.7029,
+      "step": 31
+    },
+    {
+      "epoch": 0.3058542413381123,
+      "grad_norm": 0.612296462059021,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.6895,
+      "step": 32
+    },
+    {
+      "epoch": 0.3154121863799283,
+      "grad_norm": 0.9275369048118591,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.7005,
+      "step": 33
+    },
+    {
+      "epoch": 0.3249701314217443,
+      "grad_norm": 0.8235135674476624,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.697,
+      "step": 34
+    },
+    {
+      "epoch": 0.3345280764635603,
+      "grad_norm": 0.6381819248199463,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.6879,
+      "step": 35
+    },
+    {
+      "epoch": 0.34408602150537637,
+      "grad_norm": 1.0177886486053467,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.7004,
+      "step": 36
+    },
+    {
+      "epoch": 0.3536439665471924,
+      "grad_norm": 0.8794744610786438,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.7023,
+      "step": 37
+    },
+    {
+      "epoch": 0.3632019115890084,
+      "grad_norm": 0.8776364922523499,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.6876,
+      "step": 38
+    },
+    {
+      "epoch": 0.3727598566308244,
+      "grad_norm": 0.612334132194519,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.6956,
+      "step": 39
+    },
+    {
+      "epoch": 0.3823178016726404,
+      "grad_norm": 1.2593517303466797,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.6988,
+      "step": 40
+    },
+    {
+      "epoch": 0.3918757467144564,
+      "grad_norm": 1.0815540552139282,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.7007,
+      "step": 41
+    },
+    {
+      "epoch": 0.4014336917562724,
+      "grad_norm": 0.7590096592903137,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.6985,
+      "step": 42
+    },
+    {
+      "epoch": 0.4109916367980884,
+      "grad_norm": 0.6991857290267944,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.6941,
+      "step": 43
+    },
+    {
+      "epoch": 0.42054958183990443,
+      "grad_norm": 1.1214922666549683,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.7013,
+      "step": 44
+    },
+    {
+      "epoch": 0.43010752688172044,
+      "grad_norm": 1.3420926332473755,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.6983,
+      "step": 45
+    },
+    {
+      "epoch": 0.43966547192353644,
+      "grad_norm": 0.8333279490470886,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.6937,
+      "step": 46
+    },
+    {
+      "epoch": 0.44922341696535245,
+      "grad_norm": 0.8321746587753296,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.6935,
+      "step": 47
+    },
+    {
+      "epoch": 0.45878136200716846,
+      "grad_norm": 0.8994906544685364,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.6884,
+      "step": 48
+    },
+    {
+      "epoch": 0.46833930704898447,
+      "grad_norm": 0.8762169480323792,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.6981,
+      "step": 49
+    },
+    {
+      "epoch": 0.4778972520908005,
+      "grad_norm": 1.2555692195892334,
+      "learning_rate": 1e-05,
+      "loss": 0.7074,
+      "step": 50
+    },
+    {
+      "epoch": 0.4778972520908005,
+      "eval_loss": 0.6973173022270203,
+      "eval_runtime": 2.0327,
+      "eval_samples_per_second": 24.598,
+      "eval_steps_per_second": 6.395,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null