Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19b5dfc10500f58f7681ed24f81f65a0264423b0a05980d367a129c4a9fa2796
+oid sha256:5a8fc155401317c99b97749d2c9001309cbf81305dc0403722e7594c6437363f
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27b1856b6aaebc9355af480857c4fa471b75a3154d28f2b703e42e7185ed2786
+oid sha256:490ce1996a3246e2ce315ac5f08ac34ae7f5c1331f71a3a575f13f1a1bc9e41c
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a60bf658be651e5f8150902b9421ae164231588f622e25dc43fbbe7baab08cca
+oid sha256:e836ae14451311d31b89a68ef77e682d7e144aa51abd3f43e7e527a13dc89582
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fa582cf08472e454bca7af225935aac744ec1b28cadcea9efb066ef78ee2e9d
+oid sha256:34e6ee2ded7a2640db83fe4cc31253391e72cfbcf7b2f98ed5b7dea748f7be54
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72ca0d75a3653eb0caf13102680e97453ffeaf37a4aca92db1040ee31317d849
+oid sha256:579617f87ed45993aa37d853811a04adc20a52a5bafd56989ac53d37e949c0fb
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8462edaf55ec6ed445bf9a1fd1e9e65447eab660d5f3e404d1f18314e74d0ce1
+oid sha256:41a073b012fd359493aacf67c7847d5b6bd74ac853e9074a58db2a96a950d9fd
 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": 0.21981914341449738,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.3656307129798903,
+  "best_metric": 0.17505227029323578,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.7312614259597806,
   "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": 36.257,
       "eval_steps_per_second": 4.562,
       "step": 25
+    },
+    {
+      "epoch": 0.3802559414990859,
+      "grad_norm": 2.550391912460327,
+      "learning_rate": 5e-05,
+      "loss": 0.2178,
+      "step": 26
+    },
+    {
+      "epoch": 0.39488117001828155,
+      "grad_norm": 2.0261378288269043,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.2351,
+      "step": 27
+    },
+    {
+      "epoch": 0.40950639853747717,
+      "grad_norm": 2.101436138153076,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.2448,
+      "step": 28
+    },
+    {
+      "epoch": 0.42413162705667273,
+      "grad_norm": 1.7612956762313843,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.1681,
+      "step": 29
+    },
+    {
+      "epoch": 0.43875685557586835,
+      "grad_norm": 1.6624386310577393,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.2175,
+      "step": 30
+    },
+    {
+      "epoch": 0.453382084095064,
+      "grad_norm": 1.192665457725525,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.2132,
+      "step": 31
+    },
+    {
+      "epoch": 0.4680073126142596,
+      "grad_norm": 1.0501598119735718,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.1571,
+      "step": 32
+    },
+    {
+      "epoch": 0.4826325411334552,
+      "grad_norm": 1.083679437637329,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.1835,
+      "step": 33
+    },
+    {
+      "epoch": 0.49725776965265084,
+      "grad_norm": 1.7676903009414673,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.2053,
+      "step": 34
+    },
+    {
+      "epoch": 0.5118829981718465,
+      "grad_norm": 1.9303137063980103,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.2096,
+      "step": 35
+    },
+    {
+      "epoch": 0.526508226691042,
+      "grad_norm": 0.9747893810272217,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.1409,
+      "step": 36
+    },
+    {
+      "epoch": 0.5411334552102377,
+      "grad_norm": 1.0830137729644775,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.1667,
+      "step": 37
+    },
+    {
+      "epoch": 0.5557586837294333,
+      "grad_norm": 1.4457792043685913,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.1385,
+      "step": 38
+    },
+    {
+      "epoch": 0.5703839122486288,
+      "grad_norm": 0.4956473708152771,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.105,
+      "step": 39
+    },
+    {
+      "epoch": 0.5850091407678245,
+      "grad_norm": 1.1572775840759277,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.1632,
+      "step": 40
+    },
+    {
+      "epoch": 0.5996343692870201,
+      "grad_norm": 1.2062376737594604,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.2027,
+      "step": 41
+    },
+    {
+      "epoch": 0.6142595978062158,
+      "grad_norm": 0.7177852988243103,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.226,
+      "step": 42
+    },
+    {
+      "epoch": 0.6288848263254113,
+      "grad_norm": 0.8510001301765442,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.1587,
+      "step": 43
+    },
+    {
+      "epoch": 0.643510054844607,
+      "grad_norm": 1.0772465467453003,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.1439,
+      "step": 44
+    },
+    {
+      "epoch": 0.6581352833638026,
+      "grad_norm": 1.2371275424957275,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.1064,
+      "step": 45
+    },
+    {
+      "epoch": 0.6727605118829981,
+      "grad_norm": 0.785141110420227,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.156,
+      "step": 46
+    },
+    {
+      "epoch": 0.6873857404021938,
+      "grad_norm": 1.2632596492767334,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.1088,
+      "step": 47
+    },
+    {
+      "epoch": 0.7020109689213894,
+      "grad_norm": 1.0525493621826172,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.1652,
+      "step": 48
+    },
+    {
+      "epoch": 0.716636197440585,
+      "grad_norm": 0.9449817538261414,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.1478,
+      "step": 49
+    },
+    {
+      "epoch": 0.7312614259597806,
+      "grad_norm": 1.407353401184082,
+      "learning_rate": 0.0,
+      "loss": 0.1391,
+      "step": 50
+    },
+    {
+      "epoch": 0.7312614259597806,
+      "eval_loss": 0.17505227029323578,
+      "eval_runtime": 12.7323,
+      "eval_samples_per_second": 36.207,
+      "eval_steps_per_second": 4.555,
+      "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": 2.812028905324544e+17,
+  "total_flos": 5.624057810649088e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null