Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44cf4aa548441349f141a06d77d0d9708d393265b1c89fbf9e3cbc8c8bb69070
+oid sha256:59c0e34a59fc389816973753eeba66ed6a403cc4e83b30239e90ef4e33978ea0
 size 498804568

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da348d3a14df880e7d3527c297781ef83fcbc4946fcf9d01c1ab8f0dc7119dfb
+oid sha256:054f90bb5d95563f1c2ed400feac2537f6cd16db3e4a83581765cacbe5878bcd
 size 997931362

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bcbb1ed228fc6f3eaa4d82ee3c697e6d902c8993158447ff8a001fa1018dc71
+oid sha256:9db9f4fa9174b5ed593fc41d0dde88870e381249cf58e4ba656540474022eaeb
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f8f64f6555c220fff99a66668f97dcefc752cba5f8276dff3d3203ffb494624
+oid sha256:ad19df10e9ddc082a60de4fbd9a1c14f2f4b0443a4a75bc6ba2d653dfd15ec93
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0856d45485fb50567419b2ccce1dffb1636d7b003cb3c902d08b4aff805dbfdc
+oid sha256:246039295e3e44141a7203c84874cca0e24b74c196e7f8bf8995130a5225db4f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f97422e674366147420ae817995a50a96de7ec3ab3c87ef53dd341a3f4c4a1d4
+oid sha256:79840ebd984a9961d0b81d51dda6f4f18201a7f2ad603099d1898d81fe90234b
 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": 1.0795084238052368,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.075268817204301,
+  "best_metric": 0.7876038551330566,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.150537634408602,
   "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": 19.721,
       "eval_steps_per_second": 2.512,
       "step": 25
+    },
+    {
+      "epoch": 1.118279569892473,
+      "grad_norm": 4.564328670501709,
+      "learning_rate": 5e-05,
+      "loss": 1.2343,
+      "step": 26
+    },
+    {
+      "epoch": 1.1612903225806452,
+      "grad_norm": 3.6037137508392334,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.0317,
+      "step": 27
+    },
+    {
+      "epoch": 1.2043010752688172,
+      "grad_norm": 3.2914304733276367,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.9329,
+      "step": 28
+    },
+    {
+      "epoch": 1.2473118279569892,
+      "grad_norm": 5.4039154052734375,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.3014,
+      "step": 29
+    },
+    {
+      "epoch": 1.2903225806451613,
+      "grad_norm": 3.8691208362579346,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.9831,
+      "step": 30
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 4.34861946105957,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.0507,
+      "step": 31
+    },
+    {
+      "epoch": 1.3763440860215055,
+      "grad_norm": 2.965681314468384,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.1723,
+      "step": 32
+    },
+    {
+      "epoch": 1.4193548387096775,
+      "grad_norm": 3.439244508743286,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.9571,
+      "step": 33
+    },
+    {
+      "epoch": 1.4623655913978495,
+      "grad_norm": 2.797593593597412,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.8522,
+      "step": 34
+    },
+    {
+      "epoch": 1.5053763440860215,
+      "grad_norm": 2.8328845500946045,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.0963,
+      "step": 35
+    },
+    {
+      "epoch": 1.5483870967741935,
+      "grad_norm": 2.290050506591797,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.701,
+      "step": 36
+    },
+    {
+      "epoch": 1.5913978494623655,
+      "grad_norm": 3.077988386154175,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.8191,
+      "step": 37
+    },
+    {
+      "epoch": 1.6344086021505375,
+      "grad_norm": 2.5467429161071777,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.9073,
+      "step": 38
+    },
+    {
+      "epoch": 1.6774193548387095,
+      "grad_norm": 2.68570876121521,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.8795,
+      "step": 39
+    },
+    {
+      "epoch": 1.7204301075268817,
+      "grad_norm": 2.404557466506958,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.7958,
+      "step": 40
+    },
+    {
+      "epoch": 1.7634408602150538,
+      "grad_norm": 2.3604447841644287,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.8523,
+      "step": 41
+    },
+    {
+      "epoch": 1.8064516129032258,
+      "grad_norm": 1.8468281030654907,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.6095,
+      "step": 42
+    },
+    {
+      "epoch": 1.849462365591398,
+      "grad_norm": 3.724862813949585,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.7875,
+      "step": 43
+    },
+    {
+      "epoch": 1.89247311827957,
+      "grad_norm": 3.9843430519104004,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.906,
+      "step": 44
+    },
+    {
+      "epoch": 1.935483870967742,
+      "grad_norm": 1.6732141971588135,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.7148,
+      "step": 45
+    },
+    {
+      "epoch": 1.978494623655914,
+      "grad_norm": 2.5346105098724365,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.8121,
+      "step": 46
+    },
+    {
+      "epoch": 2.021505376344086,
+      "grad_norm": 5.31929349899292,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.3606,
+      "step": 47
+    },
+    {
+      "epoch": 2.064516129032258,
+      "grad_norm": 1.4526803493499756,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.6546,
+      "step": 48
+    },
+    {
+      "epoch": 2.10752688172043,
+      "grad_norm": 2.4552512168884277,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.819,
+      "step": 49
+    },
+    {
+      "epoch": 2.150537634408602,
+      "grad_norm": 1.7610336542129517,
+      "learning_rate": 0.0,
+      "loss": 0.816,
+      "step": 50
+    },
+    {
+      "epoch": 2.150537634408602,
+      "eval_loss": 0.7876038551330566,
+      "eval_runtime": 7.9591,
+      "eval_samples_per_second": 19.726,
+      "eval_steps_per_second": 2.513,
+      "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": 5.313687367712768e+17,
+  "total_flos": 1.0627374735425536e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null