Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ed454ad7f07c9e5c92e75b1ed6386613a2c5d6f6e6cad6a718c07a69a4f943b
+oid sha256:2ca21f3b6802876310f4b193ab5d2619c55c35feb62bf80082b7b711e8d78b25
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08a890771f95e891be8e72fcdd1ea23a6b01361059317f4fb697a428c342096a
+oid sha256:655a0d8b51aff256b7c2aea3ef2ad648814b5c411fed447c0cf40f7cd06225d5
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fd638d30eb26e9dd69ab1bc4949b760535e43b21abf63770f44327208be34f5
+oid sha256:899d44fe9c3b5e49b8991a779f388e99445165a21336c9bb3aaaefe8e631dabb
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37ce8d55234572dbc5080ad2581aa577fe82b87d59a3ed1d9ae2e96907db6ab2
+oid sha256:f493f5a4982f9a5c3ee33730e9e1054b78c14d7a76575bd4ece3212af1273674
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b2c0c72498f77abed1ae73275436478b749aa94f0f9abbeddd80a6fc7e12151
+oid sha256:3fcc9d38ceb4c45eab3eaaaf687827df8c94c0e1b29098dcd39d4ee5076c80cc
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90f742b1d48cadbbf5abaac1f1d1a4a155f1566db8847d43d152d6019903317f
+oid sha256:af0c02464aad0ea470bc8b1671c814035c53288f9c72176aec599f207b3df2ff
 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": 1.2883262634277344,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.461361014994233,
+  "best_metric": 1.2369416952133179,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.922722029988466,
   "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": 45.433,
       "eval_steps_per_second": 5.726,
       "step": 25
+    },
+    {
+      "epoch": 0.4798154555940023,
+      "grad_norm": 1.2016305923461914,
+      "learning_rate": 5e-05,
+      "loss": 1.3585,
+      "step": 26
+    },
+    {
+      "epoch": 0.4982698961937716,
+      "grad_norm": 1.0293444395065308,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.2216,
+      "step": 27
+    },
+    {
+      "epoch": 0.5167243367935409,
+      "grad_norm": 1.0681506395339966,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.2636,
+      "step": 28
+    },
+    {
+      "epoch": 0.5351787773933102,
+      "grad_norm": 0.8969022631645203,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.22,
+      "step": 29
+    },
+    {
+      "epoch": 0.5536332179930796,
+      "grad_norm": 1.0133044719696045,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.2688,
+      "step": 30
+    },
+    {
+      "epoch": 0.5720876585928489,
+      "grad_norm": 1.0388270616531372,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.232,
+      "step": 31
+    },
+    {
+      "epoch": 0.5905420991926182,
+      "grad_norm": 1.102528691291809,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.1384,
+      "step": 32
+    },
+    {
+      "epoch": 0.6089965397923875,
+      "grad_norm": 1.4005072116851807,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.1417,
+      "step": 33
+    },
+    {
+      "epoch": 0.6274509803921569,
+      "grad_norm": 1.2080509662628174,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.162,
+      "step": 34
+    },
+    {
+      "epoch": 0.6459054209919262,
+      "grad_norm": 1.075602650642395,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.2626,
+      "step": 35
+    },
+    {
+      "epoch": 0.6643598615916955,
+      "grad_norm": 0.9468011856079102,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.2333,
+      "step": 36
+    },
+    {
+      "epoch": 0.6828143021914648,
+      "grad_norm": 0.9746062755584717,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.1295,
+      "step": 37
+    },
+    {
+      "epoch": 0.7012687427912342,
+      "grad_norm": 1.348818302154541,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.3782,
+      "step": 38
+    },
+    {
+      "epoch": 0.7197231833910035,
+      "grad_norm": 1.452208399772644,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.2207,
+      "step": 39
+    },
+    {
+      "epoch": 0.7381776239907728,
+      "grad_norm": 1.3578698635101318,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.1844,
+      "step": 40
+    },
+    {
+      "epoch": 0.7566320645905421,
+      "grad_norm": 1.213419795036316,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.1902,
+      "step": 41
+    },
+    {
+      "epoch": 0.7750865051903114,
+      "grad_norm": 0.8172274231910706,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.1263,
+      "step": 42
+    },
+    {
+      "epoch": 0.7935409457900807,
+      "grad_norm": 1.0537660121917725,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.2337,
+      "step": 43
+    },
+    {
+      "epoch": 0.81199538638985,
+      "grad_norm": 1.0971416234970093,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.2341,
+      "step": 44
+    },
+    {
+      "epoch": 0.8304498269896193,
+      "grad_norm": 0.8870224356651306,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.1304,
+      "step": 45
+    },
+    {
+      "epoch": 0.8489042675893888,
+      "grad_norm": 1.0595213174819946,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.1634,
+      "step": 46
+    },
+    {
+      "epoch": 0.8673587081891581,
+      "grad_norm": 1.0634539127349854,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.1305,
+      "step": 47
+    },
+    {
+      "epoch": 0.8858131487889274,
+      "grad_norm": 1.1929792165756226,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.2521,
+      "step": 48
+    },
+    {
+      "epoch": 0.9042675893886967,
+      "grad_norm": 1.0194319486618042,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.2551,
+      "step": 49
+    },
+    {
+      "epoch": 0.922722029988466,
+      "grad_norm": 1.1550265550613403,
+      "learning_rate": 0.0,
+      "loss": 1.1364,
+      "step": 50
+    },
+    {
+      "epoch": 0.922722029988466,
+      "eval_loss": 1.2369416952133179,
+      "eval_runtime": 8.0436,
+      "eval_samples_per_second": 45.378,
+      "eval_steps_per_second": 5.719,
+      "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": 4.203543924205158e+16,
+  "total_flos": 8.391461307836006e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null