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:cb419d9c9c6597685c3da85794a776ec677c83d4a9caa63b80317db8ff3b8138
+oid sha256:ebde25d0b61fab9473ddb2daffc25157bd46edc7dfc1de5ef61b34eb8bad4ffd
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18f05a03e4e948e1680be67e87e5b2bb0281b62714f8c00829e5613887821b0c
+oid sha256:1432bd7d4afdaffb7191f3a93987bf614091c3dfbe0b79c044319797540a13f3
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4d939fa8a73339b0eacb4f942155a1f5c173559681c320f81ebb7026b684963
+oid sha256:3f6b28ddceffcfbb0eba88c1253d9911a71087a0094e0bfdf46af8eb09c71e1e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdebbaef04f27a5f7646687f30112a2fffa2f707ab07d50b31476eb5c8ff2721
+oid sha256:2d309aaef3b1e5898ac57d64657b760ac77a2c95a5d95f8529614ca1aed1aaaa
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96e3be404530e347355eb700f11b1e80c9b7f3eaaeb3af279418c0d19f662e55
+oid sha256:97c53f4da5420488101ec3275bdfc923e394ed7e19e556423cd25a0dedcbfc47
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:260783626fa52d0ac8d89469df9c10b55a57bc69e952cc53fe47a8672f810dbc
+oid sha256:17433ce56533032b14ee12a4eaa80b1ba94e3f84b10da2de1e7b768ebdb2efb1
 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": 0.33393481373786926,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.01778845084828675,
+  "best_metric": 0.1434822976589203,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.0355769016965735,
   "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": 14.297,
       "eval_steps_per_second": 3.717,
       "step": 25
+    },
+    {
+      "epoch": 0.01849998888221822,
+      "grad_norm": 2.969831943511963,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.5724,
+      "step": 26
+    },
+    {
+      "epoch": 0.01921152691614969,
+      "grad_norm": 2.821878433227539,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.4745,
+      "step": 27
+    },
+    {
+      "epoch": 0.01992306495008116,
+      "grad_norm": 2.2078421115875244,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.2994,
+      "step": 28
+    },
+    {
+      "epoch": 0.02063460298401263,
+      "grad_norm": 1.3875349760055542,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.2495,
+      "step": 29
+    },
+    {
+      "epoch": 0.0213461410179441,
+      "grad_norm": 0.6588164567947388,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.1957,
+      "step": 30
+    },
+    {
+      "epoch": 0.02205767905187557,
+      "grad_norm": 0.9994838237762451,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.1777,
+      "step": 31
+    },
+    {
+      "epoch": 0.02276921708580704,
+      "grad_norm": 1.3160651922225952,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.1387,
+      "step": 32
+    },
+    {
+      "epoch": 0.02348075511973851,
+      "grad_norm": 1.2686349153518677,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.1326,
+      "step": 33
+    },
+    {
+      "epoch": 0.02419229315366998,
+      "grad_norm": 1.0544302463531494,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.1315,
+      "step": 34
+    },
+    {
+      "epoch": 0.02490383118760145,
+      "grad_norm": 0.8117554187774658,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.1057,
+      "step": 35
+    },
+    {
+      "epoch": 0.02561536922153292,
+      "grad_norm": 0.8301512002944946,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.1408,
+      "step": 36
+    },
+    {
+      "epoch": 0.02632690725546439,
+      "grad_norm": 0.698844313621521,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.108,
+      "step": 37
+    },
+    {
+      "epoch": 0.02703844528939586,
+      "grad_norm": 1.0740541219711304,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.336,
+      "step": 38
+    },
+    {
+      "epoch": 0.02774998332332733,
+      "grad_norm": 1.0991758108139038,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.2901,
+      "step": 39
+    },
+    {
+      "epoch": 0.0284615213572588,
+      "grad_norm": 0.9590191841125488,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.2117,
+      "step": 40
+    },
+    {
+      "epoch": 0.02917305939119027,
+      "grad_norm": 0.9291145205497742,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.1994,
+      "step": 41
+    },
+    {
+      "epoch": 0.02988459742512174,
+      "grad_norm": 0.9364894032478333,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.1825,
+      "step": 42
+    },
+    {
+      "epoch": 0.03059613545905321,
+      "grad_norm": 0.8379543423652649,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.1323,
+      "step": 43
+    },
+    {
+      "epoch": 0.03130767349298468,
+      "grad_norm": 0.8360366821289062,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.1075,
+      "step": 44
+    },
+    {
+      "epoch": 0.03201921152691615,
+      "grad_norm": 0.6033630967140198,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.1072,
+      "step": 45
+    },
+    {
+      "epoch": 0.03273074956084762,
+      "grad_norm": 0.4806281328201294,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0838,
+      "step": 46
+    },
+    {
+      "epoch": 0.03344228759477909,
+      "grad_norm": 0.53305584192276,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0922,
+      "step": 47
+    },
+    {
+      "epoch": 0.03415382562871056,
+      "grad_norm": 0.4884934723377228,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.115,
+      "step": 48
+    },
+    {
+      "epoch": 0.03486536366264203,
+      "grad_norm": 0.723628044128418,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.1015,
+      "step": 49
+    },
+    {
+      "epoch": 0.0355769016965735,
+      "grad_norm": 1.2043287754058838,
+      "learning_rate": 1e-05,
+      "loss": 0.1129,
+      "step": 50
+    },
+    {
+      "epoch": 0.0355769016965735,
+      "eval_loss": 0.1434822976589203,
+      "eval_runtime": 3.4781,
+      "eval_samples_per_second": 14.375,
+      "eval_steps_per_second": 3.738,
+      "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": 1,
   "trial_name": null,
   "trial_params": null