Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a7b5687d3d29a54f5fa041699d4a2ef389a161ed95737d098386c7788c909d0
+oid sha256:ee459256b4fdc00f77717d64b54e5ab31636cdd7e7f15e43a51f6dd66191e5be
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b4e563a14ee083ae67ab22a032771c05f3a704a378fee4d8edde32448c61e07
+oid sha256:8c50fa19938d2716972f3a5428f0551b1de85cb8e05ef5ae37b338c7c9ed9e8e
 size 113994

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a98cd8d2de968dbd9d113d4cceb61e4a67853efbf782dd1fd73e54e446660233
+oid sha256:ec534dd103c36b7ed649ea4db5b1570c2ab760e0b93691bb8ebcf6be937b1021
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ff3a8aa4e2e1ca342efa2e2c9da4f60e1288da338040cc3d2d3b762777eb54e
+oid sha256:3ce5e96e88f10de19f89bedbd5cacb17e8b0269ce65df7ed905b6c25db6c1095
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e44aee6f92c0ad5389ce6fd81345d0954cefef479ad5041e93dfa01d1e5c105f
+oid sha256:651c4a9a347eb69f28598214a263f302fe3b0313ac88d018663d14dc0c905d84
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e1dbb7786585ed256d333d5b6be601f1bfffa30d4936e668a3d0471f7b3765e
+oid sha256:99adb6b3161224be6a23bb69ffc044e3ae667659b82779fc94e685a7a0fa9c7f
 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": 11.933411598205566,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.08213552361396304,
+  "best_metric": 11.930052757263184,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.16427104722792607,
   "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": 295.171,
       "eval_steps_per_second": 76.744,
       "step": 25
+    },
+    {
+      "epoch": 0.08542094455852156,
+      "grad_norm": 0.0746845081448555,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 11.9349,
+      "step": 26
+    },
+    {
+      "epoch": 0.08870636550308009,
+      "grad_norm": 0.08587120473384857,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 11.9355,
+      "step": 27
+    },
+    {
+      "epoch": 0.0919917864476386,
+      "grad_norm": 0.09801056236028671,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 11.9345,
+      "step": 28
+    },
+    {
+      "epoch": 0.09527720739219712,
+      "grad_norm": 0.10124927014112473,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 11.9342,
+      "step": 29
+    },
+    {
+      "epoch": 0.09856262833675565,
+      "grad_norm": 0.1071905717253685,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 11.9341,
+      "step": 30
+    },
+    {
+      "epoch": 0.10184804928131416,
+      "grad_norm": 0.13783201575279236,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 11.9321,
+      "step": 31
+    },
+    {
+      "epoch": 0.10513347022587269,
+      "grad_norm": 0.12671908736228943,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 11.9357,
+      "step": 32
+    },
+    {
+      "epoch": 0.10841889117043121,
+      "grad_norm": 0.1352739781141281,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 11.9353,
+      "step": 33
+    },
+    {
+      "epoch": 0.11170431211498973,
+      "grad_norm": 0.13712292909622192,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 11.9337,
+      "step": 34
+    },
+    {
+      "epoch": 0.11498973305954825,
+      "grad_norm": 0.1451713740825653,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 11.9328,
+      "step": 35
+    },
+    {
+      "epoch": 0.11827515400410678,
+      "grad_norm": 0.13962270319461823,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 11.9299,
+      "step": 36
+    },
+    {
+      "epoch": 0.1215605749486653,
+      "grad_norm": 0.1617678552865982,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 11.9311,
+      "step": 37
+    },
+    {
+      "epoch": 0.12484599589322382,
+      "grad_norm": 0.1094789206981659,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 11.9343,
+      "step": 38
+    },
+    {
+      "epoch": 0.12813141683778234,
+      "grad_norm": 0.09994740039110184,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 11.9339,
+      "step": 39
+    },
+    {
+      "epoch": 0.13141683778234087,
+      "grad_norm": 0.1053725853562355,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 11.9345,
+      "step": 40
+    },
+    {
+      "epoch": 0.1347022587268994,
+      "grad_norm": 0.1118607148528099,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 11.9358,
+      "step": 41
+    },
+    {
+      "epoch": 0.13798767967145792,
+      "grad_norm": 0.11891821771860123,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 11.9318,
+      "step": 42
+    },
+    {
+      "epoch": 0.14127310061601642,
+      "grad_norm": 0.14357700943946838,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 11.9331,
+      "step": 43
+    },
+    {
+      "epoch": 0.14455852156057494,
+      "grad_norm": 0.14908310770988464,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 11.9308,
+      "step": 44
+    },
+    {
+      "epoch": 0.14784394250513347,
+      "grad_norm": 0.13474707305431366,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 11.9332,
+      "step": 45
+    },
+    {
+      "epoch": 0.151129363449692,
+      "grad_norm": 0.14854881167411804,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 11.9322,
+      "step": 46
+    },
+    {
+      "epoch": 0.15441478439425052,
+      "grad_norm": 0.1468830704689026,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 11.9309,
+      "step": 47
+    },
+    {
+      "epoch": 0.15770020533880905,
+      "grad_norm": 0.14374658465385437,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 11.9291,
+      "step": 48
+    },
+    {
+      "epoch": 0.16098562628336754,
+      "grad_norm": 0.15578904747962952,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 11.9302,
+      "step": 49
+    },
+    {
+      "epoch": 0.16427104722792607,
+      "grad_norm": 0.16485072672367096,
+      "learning_rate": 1e-05,
+      "loss": 11.9277,
+      "step": 50
+    },
+    {
+      "epoch": 0.16427104722792607,
+      "eval_loss": 11.930052757263184,
+      "eval_runtime": 0.1707,
+      "eval_samples_per_second": 292.919,
+      "eval_steps_per_second": 76.159,
+      "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": 521247129600.0,
+  "total_flos": 1042494259200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null