Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ebdf1b48c51b87ba61738c2daa0f686e666adc4da2b111b770ec3d39dc85d2b
+oid sha256:1ac19f51c2148eeac5bdbfc2d3e82433e828c73e5aa7270e9ea0ba51328edd73
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51f44ddd221a3830cf2c975cc4f09a78b270ec0f1c3b6cec555929131eb4d0cb
+oid sha256:62eb26226a94c8d76df5618aef4d341d16283e48b8ecd422c001178a33d2856a
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e1d2be50a0535244244d5b8ab5eb6262c3e06caca3b5b7b1ff406ed8f2aeeab
+oid sha256:4ebe8dd4f8a10c734446f2a1158dedaefc538ae2d043d16b0568f8cd88c1ab0f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:123d716bc5ebb29ccb7a4f36f26016e0d513c39664c9f76b6f9982e61e2fa033
+oid sha256:28f136b7028e9a93341b429d91e1dde762ba3a33f684eb6c78c5432f1c952680
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ddf05dc3c78e063f7988074e041fce8ac18ca47da15097c65b542d41faa7784
+oid sha256:0461307e9338b6aa0e0568d7301d203c18e4a75bcf196f1201f361ae620ea073
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c34732c7dcf3b1569e6b698feaff197d48a676aedbba3d1d41c76e9e1f9079bb
+oid sha256:4469e3945fed34bb2b6bc1e64bcee57965a510691908b65159e88c9185b6d5db
 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": 10.368462562561035,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.14684287812041116,
+  "best_metric": 10.363272666931152,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.2936857562408223,
   "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": 315.488,
       "eval_steps_per_second": 39.608,
       "step": 25
+    },
+    {
+      "epoch": 0.1527165932452276,
+      "grad_norm": 0.21917545795440674,
+      "learning_rate": 5e-05,
+      "loss": 10.3686,
+      "step": 26
+    },
+    {
+      "epoch": 0.15859030837004406,
+      "grad_norm": 0.20469699800014496,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 10.3687,
+      "step": 27
+    },
+    {
+      "epoch": 0.1644640234948605,
+      "grad_norm": 0.20218636095523834,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 10.3679,
+      "step": 28
+    },
+    {
+      "epoch": 0.17033773861967694,
+      "grad_norm": 0.19212639331817627,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 10.3662,
+      "step": 29
+    },
+    {
+      "epoch": 0.1762114537444934,
+      "grad_norm": 0.18560166656970978,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 10.3675,
+      "step": 30
+    },
+    {
+      "epoch": 0.18208516886930984,
+      "grad_norm": 0.18543921411037445,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 10.368,
+      "step": 31
+    },
+    {
+      "epoch": 0.18795888399412627,
+      "grad_norm": 0.18739567697048187,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 10.3678,
+      "step": 32
+    },
+    {
+      "epoch": 0.19383259911894274,
+      "grad_norm": 0.1920151710510254,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 10.3679,
+      "step": 33
+    },
+    {
+      "epoch": 0.19970631424375918,
+      "grad_norm": 0.18959976732730865,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.3669,
+      "step": 34
+    },
+    {
+      "epoch": 0.2055800293685756,
+      "grad_norm": 0.1854933500289917,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 10.3668,
+      "step": 35
+    },
+    {
+      "epoch": 0.21145374449339208,
+      "grad_norm": 0.18347898125648499,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 10.3623,
+      "step": 36
+    },
+    {
+      "epoch": 0.2173274596182085,
+      "grad_norm": 0.1941113919019699,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 10.3596,
+      "step": 37
+    },
+    {
+      "epoch": 0.22320117474302498,
+      "grad_norm": 0.24184665083885193,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 10.3645,
+      "step": 38
+    },
+    {
+      "epoch": 0.2290748898678414,
+      "grad_norm": 0.24406494200229645,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 10.3634,
+      "step": 39
+    },
+    {
+      "epoch": 0.23494860499265785,
+      "grad_norm": 0.23579344153404236,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 10.3638,
+      "step": 40
+    },
+    {
+      "epoch": 0.24082232011747431,
+      "grad_norm": 0.2283434420824051,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 10.3634,
+      "step": 41
+    },
+    {
+      "epoch": 0.24669603524229075,
+      "grad_norm": 0.21662116050720215,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.3624,
+      "step": 42
+    },
+    {
+      "epoch": 0.2525697503671072,
+      "grad_norm": 0.21385407447814941,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 10.3656,
+      "step": 43
+    },
+    {
+      "epoch": 0.25844346549192365,
+      "grad_norm": 0.20657625794410706,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 10.3659,
+      "step": 44
+    },
+    {
+      "epoch": 0.2643171806167401,
+      "grad_norm": 0.20029610395431519,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 10.3655,
+      "step": 45
+    },
+    {
+      "epoch": 0.2701908957415565,
+      "grad_norm": 0.2030303031206131,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 10.365,
+      "step": 46
+    },
+    {
+      "epoch": 0.27606461086637296,
+      "grad_norm": 0.20757298171520233,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 10.3641,
+      "step": 47
+    },
+    {
+      "epoch": 0.28193832599118945,
+      "grad_norm": 0.20119069516658783,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 10.3643,
+      "step": 48
+    },
+    {
+      "epoch": 0.2878120411160059,
+      "grad_norm": 0.1982789784669876,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 10.3607,
+      "step": 49
+    },
+    {
+      "epoch": 0.2936857562408223,
+      "grad_norm": 0.20990411937236786,
+      "learning_rate": 0.0,
+      "loss": 10.3577,
+      "step": 50
+    },
+    {
+      "epoch": 0.2936857562408223,
+      "eval_loss": 10.363272666931152,
+      "eval_runtime": 3.6828,
+      "eval_samples_per_second": 311.451,
+      "eval_steps_per_second": 39.101,
+      "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": 21557775040512.0,
+  "total_flos": 43062090006528.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null