Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8854906e5e59c76288b22aa4e4f6575c6e022cb1fdf279fe1807f7749be65ed2
+oid sha256:0a621d07d2aa8193eeff244f70a2621016fc5de7e3868e2e0795ca202408bfb6
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39bfae6a7c61109aca1f9220199e16b505718a24381145c0a1cca22bb20793cb
+oid sha256:c005b4c7025380f723a57b94cab7b1ee8d7c29443cd6a1486b60f9c11d7dc199
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6922407163a7d1eeb7ca384df5f6e655e645ef560fc87a0fb7c4cd8dc598b44d
+oid sha256:aef53990127b00e294511afc7687904976de980016376a08f21a936c2dd1add6
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db93277afa3860a92388703478cde248aa5f0f5770aaa212c8bb66bdbf51aee1
+oid sha256:6918316e339d961da43fb486fd694ad7ef6eb8b5dbcb9d74d46fcb0199631ba5
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1eee9a7b06dadd6e9b8bd239752f93f1d4e1eaa964012ec086fd223e0e3f2f9
+oid sha256:8b73e271758141478a11cc9a677665dbe43205d00d6e40dcd1317979c2b0489a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83bb650cbb58398a4f8fec78823af27087242f34d83ce078b9c589159fac66d6
+oid sha256:fb88f34760a741f46b951a6b828fae375e7d58d90df6aa749e659fa748608b38
 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": 1.6385608911514282,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.5988023952095808,
+  "best_metric": 1.2797590494155884,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.1991017964071857,
   "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": 27.176,
       "eval_steps_per_second": 7.066,
       "step": 25
+    },
+    {
+      "epoch": 0.6227544910179641,
+      "grad_norm": 3.454927444458008,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 2.4419,
+      "step": 26
+    },
+    {
+      "epoch": 0.6467065868263473,
+      "grad_norm": 15.82660961151123,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.979,
+      "step": 27
+    },
+    {
+      "epoch": 0.6706586826347305,
+      "grad_norm": 2.704850673675537,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.5964,
+      "step": 28
+    },
+    {
+      "epoch": 0.6946107784431138,
+      "grad_norm": 0.9731075763702393,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.3988,
+      "step": 29
+    },
+    {
+      "epoch": 0.718562874251497,
+      "grad_norm": 0.9410566091537476,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.1846,
+      "step": 30
+    },
+    {
+      "epoch": 0.7425149700598802,
+      "grad_norm": 0.6559235453605652,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.2623,
+      "step": 31
+    },
+    {
+      "epoch": 0.7664670658682635,
+      "grad_norm": 0.8387520909309387,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.289,
+      "step": 32
+    },
+    {
+      "epoch": 0.7904191616766467,
+      "grad_norm": 0.8098101615905762,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.3178,
+      "step": 33
+    },
+    {
+      "epoch": 0.8143712574850299,
+      "grad_norm": 0.6314873099327087,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.302,
+      "step": 34
+    },
+    {
+      "epoch": 0.8383233532934131,
+      "grad_norm": 0.613024115562439,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.1753,
+      "step": 35
+    },
+    {
+      "epoch": 0.8622754491017964,
+      "grad_norm": 0.9052037596702576,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.7577,
+      "step": 36
+    },
+    {
+      "epoch": 0.8862275449101796,
+      "grad_norm": 0.9839400053024292,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.6996,
+      "step": 37
+    },
+    {
+      "epoch": 0.9101796407185628,
+      "grad_norm": 0.8733965158462524,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.5614,
+      "step": 38
+    },
+    {
+      "epoch": 0.9341317365269461,
+      "grad_norm": 0.7196979522705078,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.3533,
+      "step": 39
+    },
+    {
+      "epoch": 0.9580838323353293,
+      "grad_norm": 0.7690499424934387,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.241,
+      "step": 40
+    },
+    {
+      "epoch": 0.9820359281437125,
+      "grad_norm": 1.088390827178955,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.0753,
+      "step": 41
+    },
+    {
+      "epoch": 1.0074850299401197,
+      "grad_norm": 0.6395664811134338,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.8832,
+      "step": 42
+    },
+    {
+      "epoch": 1.031437125748503,
+      "grad_norm": 0.5951088070869446,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.1295,
+      "step": 43
+    },
+    {
+      "epoch": 1.0553892215568863,
+      "grad_norm": 0.5507844686508179,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.3376,
+      "step": 44
+    },
+    {
+      "epoch": 1.0793413173652695,
+      "grad_norm": 0.5301908850669861,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.2178,
+      "step": 45
+    },
+    {
+      "epoch": 1.1032934131736527,
+      "grad_norm": 0.6889688372612,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.2051,
+      "step": 46
+    },
+    {
+      "epoch": 1.127245508982036,
+      "grad_norm": 0.6885656714439392,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.5593,
+      "step": 47
+    },
+    {
+      "epoch": 1.151197604790419,
+      "grad_norm": 0.7920830845832825,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.6038,
+      "step": 48
+    },
+    {
+      "epoch": 1.1751497005988023,
+      "grad_norm": 0.7186149954795837,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.4422,
+      "step": 49
+    },
+    {
+      "epoch": 1.1991017964071857,
+      "grad_norm": 0.717149555683136,
+      "learning_rate": 1e-05,
+      "loss": 1.2962,
+      "step": 50
+    },
+    {
+      "epoch": 1.1991017964071857,
+      "eval_loss": 1.2797590494155884,
+      "eval_runtime": 1.8277,
+      "eval_samples_per_second": 27.356,
+      "eval_steps_per_second": 7.113,
+      "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": 2.812028905324544e+17,
+  "total_flos": 5.624057810649088e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null