Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:110f0218ee3d57a2bc381e17dcf9c4856e3d231df7166eb6fa0ace36aec07a02
+oid sha256:aaa881ede47b4abcb17067182a6d1483ca3b91076a815001bb071c2f91b29643
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3145d7e97f9a3203eadf54cbfec371440b07ed9d48b3d5c0788e6d63b371fcc
+oid sha256:6f42be0b106e081e3a4f07be258eb0066c66062535a1c38b5ac21f0afff9e4f8
 size 313998650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed3932c88d7e11f4d0af8d0d5f6de07ceb1d5a4d4ecae0b2ee6c7918a33330e0
+oid sha256:d706eaa3c5760c677592560c0dce31bbfdb6bc2a5bc8bd045fff880b18dbabd2
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d5d34beb0bba589db4c1a50399c5c93189656d1fd1e17d14dbf40e7dfd9a89d
+oid sha256:9070abbe0de00d3bff2562c0f3095b8df2959010499e9b5eeed78890cffcd6e9
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcc6cc4394fc733fc5540f45985638f0fdc2cda7ed7ec950680defd101f9df82
+oid sha256:8a8d1135bbaf180b404013c6833376ded19c302895501641f4a56867b51a475e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:670debcb6cd7aea4247215522ac231826c93316dc90e6f677ad4398ff766cf40
+oid sha256:fe2503d968696a138f44954fa63899a291fbfb12e2ef7e7b0baca5ee4318f980
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.661895751953125,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.10219724067450178,
+  "best_metric": 2.4978737831115723,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.20439448134900357,
   "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": 75.593,
       "eval_steps_per_second": 9.449,
       "step": 25
+    },
+    {
+      "epoch": 0.10628513030148186,
+      "grad_norm": 5.8317461013793945,
+      "learning_rate": 5e-05,
+      "loss": 2.0647,
+      "step": 26
+    },
+    {
+      "epoch": 0.11037301992846194,
+      "grad_norm": 4.961366176605225,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 2.1673,
+      "step": 27
+    },
+    {
+      "epoch": 0.114460909555442,
+      "grad_norm": 4.830630779266357,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.1166,
+      "step": 28
+    },
+    {
+      "epoch": 0.11854879918242207,
+      "grad_norm": 4.64272403717041,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 2.2113,
+      "step": 29
+    },
+    {
+      "epoch": 0.12263668880940215,
+      "grad_norm": 4.4510979652404785,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 2.2713,
+      "step": 30
+    },
+    {
+      "epoch": 0.1267245784363822,
+      "grad_norm": 4.489824295043945,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 2.595,
+      "step": 31
+    },
+    {
+      "epoch": 0.1308124680633623,
+      "grad_norm": 5.059741973876953,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 3.0219,
+      "step": 32
+    },
+    {
+      "epoch": 0.13490035769034237,
+      "grad_norm": 5.121081352233887,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 2.9382,
+      "step": 33
+    },
+    {
+      "epoch": 0.13898824731732243,
+      "grad_norm": 4.78178071975708,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.9814,
+      "step": 34
+    },
+    {
+      "epoch": 0.1430761369443025,
+      "grad_norm": 4.80839204788208,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 2.99,
+      "step": 35
+    },
+    {
+      "epoch": 0.14716402657128258,
+      "grad_norm": 5.164693832397461,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 3.1595,
+      "step": 36
+    },
+    {
+      "epoch": 0.15125191619826264,
+      "grad_norm": 4.842580318450928,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 3.0705,
+      "step": 37
+    },
+    {
+      "epoch": 0.1553398058252427,
+      "grad_norm": 4.596642971038818,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.7793,
+      "step": 38
+    },
+    {
+      "epoch": 0.1594276954522228,
+      "grad_norm": 4.785800933837891,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.1162,
+      "step": 39
+    },
+    {
+      "epoch": 0.16351558507920286,
+      "grad_norm": 4.623363494873047,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.9282,
+      "step": 40
+    },
+    {
+      "epoch": 0.16760347470618292,
+      "grad_norm": 4.208681583404541,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 2.1205,
+      "step": 41
+    },
+    {
+      "epoch": 0.171691364333163,
+      "grad_norm": 4.413357257843018,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.261,
+      "step": 42
+    },
+    {
+      "epoch": 0.17577925396014307,
+      "grad_norm": 4.360232830047607,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.4546,
+      "step": 43
+    },
+    {
+      "epoch": 0.17986714358712313,
+      "grad_norm": 4.461257457733154,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.757,
+      "step": 44
+    },
+    {
+      "epoch": 0.18395503321410323,
+      "grad_norm": 4.640006065368652,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 2.8297,
+      "step": 45
+    },
+    {
+      "epoch": 0.1880429228410833,
+      "grad_norm": 4.686505317687988,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 2.8533,
+      "step": 46
+    },
+    {
+      "epoch": 0.19213081246806335,
+      "grad_norm": 4.463410377502441,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 2.9272,
+      "step": 47
+    },
+    {
+      "epoch": 0.19621870209504344,
+      "grad_norm": 4.573821544647217,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 2.9632,
+      "step": 48
+    },
+    {
+      "epoch": 0.2003065917220235,
+      "grad_norm": 4.821043014526367,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 3.0597,
+      "step": 49
+    },
+    {
+      "epoch": 0.20439448134900357,
+      "grad_norm": 4.921551704406738,
+      "learning_rate": 0.0,
+      "loss": 3.1556,
+      "step": 50
+    },
+    {
+      "epoch": 0.20439448134900357,
+      "eval_loss": 2.4978737831115723,
+      "eval_runtime": 21.8171,
+      "eval_samples_per_second": 75.537,
+      "eval_steps_per_second": 9.442,
+      "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": 7.962220128790118e+16,
+  "total_flos": 1.5939341485552435e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null