Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97e769f4cff3b02e7b11d21a374cd088dfb62b54e3cee16e0fb99376b36af577
+oid sha256:12454d18514d9443757656ffec24e7c1f6903b89902a2f8c017b8c74a649bc16
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27de57caeea5b53400f4aa69ae8f401d26b5aedef74079d73c49384fc79ea1a2
+oid sha256:c86bc9377f0704b3eed662c8f89a218263ff03225045549f8290efd87298c15b
 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": 11.93404769897461,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.08213552361396304,
+  "best_metric": 11.931068420410156,
+  "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": 289.278,
       "eval_steps_per_second": 75.212,
       "step": 25
+    },
+    {
+      "epoch": 0.08542094455852156,
+      "grad_norm": 0.061159469187259674,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 11.9353,
+      "step": 26
+    },
+    {
+      "epoch": 0.08870636550308009,
+      "grad_norm": 0.0698854923248291,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 11.936,
+      "step": 27
+    },
+    {
+      "epoch": 0.0919917864476386,
+      "grad_norm": 0.07924137264490128,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 11.935,
+      "step": 28
+    },
+    {
+      "epoch": 0.09527720739219712,
+      "grad_norm": 0.08310386538505554,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 11.9348,
+      "step": 29
+    },
+    {
+      "epoch": 0.09856262833675565,
+      "grad_norm": 0.08692660182714462,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 11.9347,
+      "step": 30
+    },
+    {
+      "epoch": 0.10184804928131416,
+      "grad_norm": 0.1117107942700386,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 11.9329,
+      "step": 31
+    },
+    {
+      "epoch": 0.10513347022587269,
+      "grad_norm": 0.10682588070631027,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 11.9364,
+      "step": 32
+    },
+    {
+      "epoch": 0.10841889117043121,
+      "grad_norm": 0.11467161029577255,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 11.936,
+      "step": 33
+    },
+    {
+      "epoch": 0.11170431211498973,
+      "grad_norm": 0.11791813373565674,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 11.9345,
+      "step": 34
+    },
+    {
+      "epoch": 0.11498973305954825,
+      "grad_norm": 0.12620225548744202,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 11.9336,
+      "step": 35
+    },
+    {
+      "epoch": 0.11827515400410678,
+      "grad_norm": 0.12209944427013397,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 11.9307,
+      "step": 36
+    },
+    {
+      "epoch": 0.1215605749486653,
+      "grad_norm": 0.14005905389785767,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 11.932,
+      "step": 37
+    },
+    {
+      "epoch": 0.12484599589322382,
+      "grad_norm": 0.0928557962179184,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 11.935,
+      "step": 38
+    },
+    {
+      "epoch": 0.12813141683778234,
+      "grad_norm": 0.08085311949253082,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 11.9346,
+      "step": 39
+    },
+    {
+      "epoch": 0.13141683778234087,
+      "grad_norm": 0.08359197527170181,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 11.9352,
+      "step": 40
+    },
+    {
+      "epoch": 0.1347022587268994,
+      "grad_norm": 0.08855370432138443,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 11.9366,
+      "step": 41
+    },
+    {
+      "epoch": 0.13798767967145792,
+      "grad_norm": 0.09516077488660812,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 11.9326,
+      "step": 42
+    },
+    {
+      "epoch": 0.14127310061601642,
+      "grad_norm": 0.11417657136917114,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 11.9341,
+      "step": 43
+    },
+    {
+      "epoch": 0.14455852156057494,
+      "grad_norm": 0.12174195796251297,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 11.9319,
+      "step": 44
+    },
+    {
+      "epoch": 0.14784394250513347,
+      "grad_norm": 0.1158878356218338,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 11.934,
+      "step": 45
+    },
+    {
+      "epoch": 0.151129363449692,
+      "grad_norm": 0.12922489643096924,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 11.933,
+      "step": 46
+    },
+    {
+      "epoch": 0.15441478439425052,
+      "grad_norm": 0.13009999692440033,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 11.9317,
+      "step": 47
+    },
+    {
+      "epoch": 0.15770020533880905,
+      "grad_norm": 0.12648075819015503,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 11.9299,
+      "step": 48
+    },
+    {
+      "epoch": 0.16098562628336754,
+      "grad_norm": 0.1377834528684616,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 11.9311,
+      "step": 49
+    },
+    {
+      "epoch": 0.16427104722792607,
+      "grad_norm": 0.14867839217185974,
+      "learning_rate": 1e-05,
+      "loss": 11.9286,
+      "step": 50
+    },
+    {
+      "epoch": 0.16427104722792607,
+      "eval_loss": 11.931068420410156,
+      "eval_runtime": 0.1711,
+      "eval_samples_per_second": 292.261,
+      "eval_steps_per_second": 75.988,
+      "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