Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d2d619d782675790a8525c6c0936942546a85f4f98b42ee1a2d1d8416f1d655
+oid sha256:05faec3d7bbc42f0f5161d82d3819260257761738a1f5fee16874f5727988503
 size 27153960

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7f49bdbd21d5f30087d114a91cdbb1c6c3b7b4d41dcc331671f7951ca594467
+oid sha256:72a6435459bf2fccd10b8e93eb9258116e4a9b26ecce14d686162cab3237510b
 size 54405050

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c8704d8214b9a3d8392b10a391daff32a8ae7d9fdfd1e12db945879bb6d58bc
+oid sha256:94ef3215132a5f3c1f93d81566eeae92f5e0882f53f40a32a9e99be35f4c3b2e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c411b4faa4d3dfb7c87072a4bf63fc5a3bca3833a197c0a48b08f2bc2c21feac
+oid sha256:ac661d5329df3e395978e635b839ff1c0323f6cb6248743ad3541186209cbf8e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f13241ac57a9dab0b4d949f7bc47ebc2f670740fa2e70b770d85282d2dd6c139
+oid sha256:a877704db41849ca884be4db1ba5b6dda9e6950af49efece590396fe20118ef2
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f29fc7ccff5f27a89a82c58717dd007238897e1bcdedf826b13272e112b4ddb
+oid sha256:62dca64f131d915a0e7d1d20b0472c79a7edcdc5a7852250a8c5fe6309391d5d
 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": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.010243015543776088,
+  "epoch": 0.020486031087552176,
   "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": 171.602,
       "eval_steps_per_second": 44.617,
       "step": 25
+    },
+    {
+      "epoch": 0.010652736165527131,
+      "grad_norm": 0.0,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.011062456787278175,
+      "grad_norm": 0.0,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.011472177409029219,
+      "grad_norm": 0.0,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.011881898030780262,
+      "grad_norm": 0.0,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.012291618652531306,
+      "grad_norm": 0.0,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.01270133927428235,
+      "grad_norm": 0.0,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.013111059896033393,
+      "grad_norm": 0.0,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.013520780517784436,
+      "grad_norm": 0.0,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.01393050113953548,
+      "grad_norm": 0.0,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.014340221761286522,
+      "grad_norm": 0.0,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.014749942383037565,
+      "grad_norm": 0.0,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.015159663004788609,
+      "grad_norm": 0.0,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.015569383626539653,
+      "grad_norm": 0.0,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.015979104248290698,
+      "grad_norm": 0.0,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.01638882487004174,
+      "grad_norm": 0.0,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.016798545491792785,
+      "grad_norm": 0.0,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.017208266113543827,
+      "grad_norm": 0.0,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.017617986735294872,
+      "grad_norm": 0.0,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.018027707357045914,
+      "grad_norm": 0.0,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.01843742797879696,
+      "grad_norm": 0.0,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.018847148600548,
+      "grad_norm": 0.0,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.019256869222299043,
+      "grad_norm": 0.0,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.01966658984405009,
+      "grad_norm": 0.0,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.02007631046580113,
+      "grad_norm": 0.0,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.020486031087552176,
+      "grad_norm": 0.0,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.020486031087552176,
+      "eval_loss": NaN,
+      "eval_runtime": 0.2806,
+      "eval_samples_per_second": 178.21,
+      "eval_steps_per_second": 46.335,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,7 +395,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5686862177894400.0,
+  "total_flos": 1.13737243557888e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null