Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39c82a96c74fd7835cffd1cbfc5f21a4499092499c92bcced125ab3658883543
+oid sha256:af2bc1db6cac408d9be019586767faf1625f21d6b21119595b2a676132bc7da0
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c1ff71ac6425f16f92f0325f7b0dba1f70833443f3ebff666780bed666c8c32
+oid sha256:049c91ffc6d500d0f2cbf33f8b926523341eb2d9da9d9a693897ddf718f3b921
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd4b651b3422eb7a41e48f58df8017c8b21dafb88a1f9f17aa75a78b0f7ed84a
+oid sha256:230b400bcd2f0ff597f4cd370393978641ee914ec57e8cbd8886e378714818c8
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b72e365def9770f1f0c8c912ed99d04008e46a619ca9586c3c40db065eacc0f
+oid sha256:1bd410f2d22a533d0458982b964cf48789ba37db49782e2c058dbf799e290673
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb6ffac95f0fcaa3ad339a18582aa64f8d6b66cac786e6901ccb266a816db16e
+oid sha256:93309c16c884872e474e0a1303b8d5491c501b933cc2d6d77798d17df9a202d4
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:327c413d95de96ebbbf8b74e29cc75a48e675b91f909ba70be881926ffa68c15
+oid sha256:b03f2b32b894cb036222a7a8970949ed0697f200a1db5f3ceb3c5b519808a91a
 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": 10.348902702331543,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.1263823064770932,
+  "best_metric": 10.3431978225708,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.2527646129541864,
   "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": 1023.965,
       "eval_steps_per_second": 128.284,
       "step": 25
+    },
+    {
+      "epoch": 0.13143759873617694,
+      "grad_norm": 0.16551639139652252,
+      "learning_rate": 5e-05,
+      "loss": 10.3903,
+      "step": 26
+    },
+    {
+      "epoch": 0.13649289099526066,
+      "grad_norm": 0.25612032413482666,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 10.3751,
+      "step": 27
+    },
+    {
+      "epoch": 0.1415481832543444,
+      "grad_norm": 0.6713676452636719,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 10.3534,
+      "step": 28
+    },
+    {
+      "epoch": 0.14660347551342812,
+      "grad_norm": 0.6692630052566528,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 10.3532,
+      "step": 29
+    },
+    {
+      "epoch": 0.15165876777251186,
+      "grad_norm": 0.6770070195198059,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 10.3525,
+      "step": 30
+    },
+    {
+      "epoch": 0.15671406003159558,
+      "grad_norm": 0.7069156169891357,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 10.3531,
+      "step": 31
+    },
+    {
+      "epoch": 0.1617693522906793,
+      "grad_norm": 0.6632951498031616,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 10.3502,
+      "step": 32
+    },
+    {
+      "epoch": 0.16682464454976303,
+      "grad_norm": 0.588923990726471,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 10.3497,
+      "step": 33
+    },
+    {
+      "epoch": 0.17187993680884675,
+      "grad_norm": 0.9730269908905029,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.3237,
+      "step": 34
+    },
+    {
+      "epoch": 0.1769352290679305,
+      "grad_norm": 1.1822327375411987,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 10.3171,
+      "step": 35
+    },
+    {
+      "epoch": 0.1819905213270142,
+      "grad_norm": 0.8201085329055786,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 10.3087,
+      "step": 36
+    },
+    {
+      "epoch": 0.18704581358609795,
+      "grad_norm": 1.3781483173370361,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 10.318,
+      "step": 37
+    },
+    {
+      "epoch": 0.19210110584518167,
+      "grad_norm": 0.40582355856895447,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 10.3761,
+      "step": 38
+    },
+    {
+      "epoch": 0.1971563981042654,
+      "grad_norm": 0.17469125986099243,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 10.38,
+      "step": 39
+    },
+    {
+      "epoch": 0.20221169036334913,
+      "grad_norm": 0.47525304555892944,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 10.3601,
+      "step": 40
+    },
+    {
+      "epoch": 0.20726698262243287,
+      "grad_norm": 0.6610441207885742,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 10.3537,
+      "step": 41
+    },
+    {
+      "epoch": 0.2123222748815166,
+      "grad_norm": 0.652646541595459,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.3501,
+      "step": 42
+    },
+    {
+      "epoch": 0.2173775671406003,
+      "grad_norm": 0.650054931640625,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 10.3502,
+      "step": 43
+    },
+    {
+      "epoch": 0.22243285939968405,
+      "grad_norm": 0.6490793824195862,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 10.3485,
+      "step": 44
+    },
+    {
+      "epoch": 0.22748815165876776,
+      "grad_norm": 0.6380521059036255,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 10.3507,
+      "step": 45
+    },
+    {
+      "epoch": 0.2325434439178515,
+      "grad_norm": 0.768058180809021,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 10.3388,
+      "step": 46
+    },
+    {
+      "epoch": 0.23759873617693522,
+      "grad_norm": 1.00645112991333,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 10.309,
+      "step": 47
+    },
+    {
+      "epoch": 0.24265402843601896,
+      "grad_norm": 1.031985878944397,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 10.3109,
+      "step": 48
+    },
+    {
+      "epoch": 0.24770932069510268,
+      "grad_norm": 1.3196580410003662,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 10.3179,
+      "step": 49
+    },
+    {
+      "epoch": 0.2527646129541864,
+      "grad_norm": 1.2216837406158447,
+      "learning_rate": 0.0,
+      "loss": 10.3203,
+      "step": 50
+    },
+    {
+      "epoch": 0.2527646129541864,
+      "eval_loss": 10.3431978225708,
+      "eval_runtime": 1.3051,
+      "eval_samples_per_second": 1021.385,
+      "eval_steps_per_second": 127.96,
+      "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": 21384029798400.0,
+  "total_flos": 42768059596800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null