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:feceadf45f9bc2eed7695ffc4ed6297e572758925e463ffedd9b5c4a63034517
+oid sha256:f454e0e386db9c20532b3ef16fcfc1959b9de36a9d0b4c780e401d628fc13ec3
 size 1521616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2dcc6999bf8b339ea6113e5efa72b9495567b10b6d6d59eb181405eb1d6b1c5
+oid sha256:e094eed46b3e419e29c6216f76f239cba7deb1c2cb5847f02b68114357f92e80
 size 3108666

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e90cffc37525db80276db8c6089af714ed88e204a289b16b49476cbda95812e5
+oid sha256:4c54cb6fb3fde091155721291098edc0eb2a8088af63d633d50436c49749f64e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:481e7e63c94e0d25bbef40e058d8d6c7111400a0a25f7454aaa11f2f8c9217c4
+oid sha256:c5e4e94fee887418018a813ed9f327599cbc02abb0bbc77099df27a6b8ab766e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86e94b165e57113fa61e445a1092b0d4b35a25c8d6854c2250eaa04a9e8924dc
+oid sha256:cd40681bd3f334543de0825f28561023738b3f0f3cf3e7c2db4eceb21ad97391
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b51998645c2db9d2875e9e06cd46b4b9817f6fbb2b67a663b9321d5de119b57e
+oid sha256:3a0795396b0cd724821b804b1d1d5cd7b95a815c3ec344f4ea19700e46d4a2f9
 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": 9.23811149597168,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.11782032400589101,
+  "best_metric": 8.977178573608398,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.23564064801178203,
   "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": 101.876,
       "eval_steps_per_second": 26.488,
       "step": 25
+    },
+    {
+      "epoch": 0.12253313696612665,
+      "grad_norm": 3.067300319671631,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 9.3613,
+      "step": 26
+    },
+    {
+      "epoch": 0.1272459499263623,
+      "grad_norm": 2.990858554840088,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 9.3185,
+      "step": 27
+    },
+    {
+      "epoch": 0.13195876288659794,
+      "grad_norm": 2.6319973468780518,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 9.2747,
+      "step": 28
+    },
+    {
+      "epoch": 0.13667157584683357,
+      "grad_norm": 2.567063331604004,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 9.2475,
+      "step": 29
+    },
+    {
+      "epoch": 0.14138438880706922,
+      "grad_norm": 2.5072484016418457,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 9.2569,
+      "step": 30
+    },
+    {
+      "epoch": 0.14609720176730487,
+      "grad_norm": 2.1724252700805664,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 9.211,
+      "step": 31
+    },
+    {
+      "epoch": 0.1508100147275405,
+      "grad_norm": 2.120619297027588,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 9.1952,
+      "step": 32
+    },
+    {
+      "epoch": 0.15552282768777614,
+      "grad_norm": 2.0732386112213135,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 9.1858,
+      "step": 33
+    },
+    {
+      "epoch": 0.1602356406480118,
+      "grad_norm": 2.1644465923309326,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 9.1393,
+      "step": 34
+    },
+    {
+      "epoch": 0.16494845360824742,
+      "grad_norm": 2.295318365097046,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 9.1125,
+      "step": 35
+    },
+    {
+      "epoch": 0.16966126656848307,
+      "grad_norm": 2.5284130573272705,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 9.1036,
+      "step": 36
+    },
+    {
+      "epoch": 0.1743740795287187,
+      "grad_norm": 2.977668285369873,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 9.069,
+      "step": 37
+    },
+    {
+      "epoch": 0.17908689248895435,
+      "grad_norm": 2.8644096851348877,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 9.1527,
+      "step": 38
+    },
+    {
+      "epoch": 0.18379970544919,
+      "grad_norm": 2.555832862854004,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 9.1339,
+      "step": 39
+    },
+    {
+      "epoch": 0.18851251840942562,
+      "grad_norm": 2.2942168712615967,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 9.1262,
+      "step": 40
+    },
+    {
+      "epoch": 0.19322533136966127,
+      "grad_norm": 2.1787540912628174,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 9.1232,
+      "step": 41
+    },
+    {
+      "epoch": 0.1979381443298969,
+      "grad_norm": 2.0844101905822754,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 9.0999,
+      "step": 42
+    },
+    {
+      "epoch": 0.20265095729013255,
+      "grad_norm": 1.9640425443649292,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 9.1021,
+      "step": 43
+    },
+    {
+      "epoch": 0.2073637702503682,
+      "grad_norm": 1.822178840637207,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 9.0733,
+      "step": 44
+    },
+    {
+      "epoch": 0.21207658321060383,
+      "grad_norm": 1.7947851419448853,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 9.0681,
+      "step": 45
+    },
+    {
+      "epoch": 0.21678939617083948,
+      "grad_norm": 1.8649380207061768,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 9.0623,
+      "step": 46
+    },
+    {
+      "epoch": 0.2215022091310751,
+      "grad_norm": 2.00160813331604,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 9.0516,
+      "step": 47
+    },
+    {
+      "epoch": 0.22621502209131075,
+      "grad_norm": 2.279819965362549,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 9.0429,
+      "step": 48
+    },
+    {
+      "epoch": 0.2309278350515464,
+      "grad_norm": 2.5081207752227783,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 8.9909,
+      "step": 49
+    },
+    {
+      "epoch": 0.23564064801178203,
+      "grad_norm": 4.336541652679443,
+      "learning_rate": 1e-05,
+      "loss": 8.9784,
+      "step": 50
+    },
+    {
+      "epoch": 0.23564064801178203,
+      "eval_loss": 8.977178573608398,
+      "eval_runtime": 0.4786,
+      "eval_samples_per_second": 104.474,
+      "eval_steps_per_second": 27.163,
+      "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": 116224411828224.0,
+  "total_flos": 232376319344640.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null