Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6348e75088a3b8d70430d566cbf8c6a312dd6e4b5c146c679fb58936bc1de9e8
+oid sha256:4271092ea5ee41db3ab68ba90d93711c2703040487cbdaa17ed0d083082b1fbd
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30003f317c5deaee0b3b5d2381509cdba77b24be24a19fb1e0fca022103a475f
+oid sha256:07a7bf0e027d1bc008a772a4f8c8dce76d0d74eb969063b19ea1a98e592721f6
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56c1e034fa9c87bb74f339ea20b20cc785c1de4954889136ede6bc24f0849a99
+oid sha256:817116e5e50ffdc3225672d864cafd812c29ffc4056687822efc21ae8828affb
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47d0893c961bdd68c86c1d59813b792813255a8b8a1fb062498172405f4d09f6
+oid sha256:d22ace04cad4d69d176b3926bf15773e398e34719bae80c3702c908ae21529b5
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cd29cd1d61d9293b904362f74970cc6e442c8a2a3cd983667c61afbfb23089f
+oid sha256:2ce738f29ed713aba6ed1a7872f3bc18ce28df08d977df2c558113ea8ae5ab27
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:968942e1971d8271e86b4219c1384990e7a908fbc419006e5f7771aede5692d2
+oid sha256:272781e7ef40c39d8639ad2a218d548395e332fd5da3c56da18e3220e2675e64
 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": 1.6467342376708984,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.9803921568627451,
+  "best_metric": 1.6053956747055054,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.9607843137254903,
   "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": 37.932,
       "eval_steps_per_second": 4.852,
       "step": 25
+    },
+    {
+      "epoch": 1.0196078431372548,
+      "grad_norm": 0.2567368447780609,
+      "learning_rate": 5e-05,
+      "loss": 2.3639,
+      "step": 26
+    },
+    {
+      "epoch": 1.0588235294117647,
+      "grad_norm": 0.15659977495670319,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.4461,
+      "step": 27
+    },
+    {
+      "epoch": 1.0980392156862746,
+      "grad_norm": 0.15974704921245575,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.516,
+      "step": 28
+    },
+    {
+      "epoch": 1.1372549019607843,
+      "grad_norm": 0.1726524382829666,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.5337,
+      "step": 29
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 0.17776235938072205,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.69,
+      "step": 30
+    },
+    {
+      "epoch": 1.215686274509804,
+      "grad_norm": 0.2240626960992813,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.7757,
+      "step": 31
+    },
+    {
+      "epoch": 1.2549019607843137,
+      "grad_norm": 0.1685163676738739,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.4047,
+      "step": 32
+    },
+    {
+      "epoch": 1.2941176470588236,
+      "grad_norm": 0.16967864334583282,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.6108,
+      "step": 33
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.17146526277065277,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.5142,
+      "step": 34
+    },
+    {
+      "epoch": 1.3725490196078431,
+      "grad_norm": 0.17000821232795715,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.5808,
+      "step": 35
+    },
+    {
+      "epoch": 1.4117647058823528,
+      "grad_norm": 0.19302861392498016,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.6247,
+      "step": 36
+    },
+    {
+      "epoch": 1.4509803921568627,
+      "grad_norm": 0.2108043134212494,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.7185,
+      "step": 37
+    },
+    {
+      "epoch": 1.4901960784313726,
+      "grad_norm": 0.15931642055511475,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.0986,
+      "step": 38
+    },
+    {
+      "epoch": 1.5294117647058822,
+      "grad_norm": 0.20348595082759857,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.0148,
+      "step": 39
+    },
+    {
+      "epoch": 1.5686274509803921,
+      "grad_norm": 0.16206344962120056,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.5098,
+      "step": 40
+    },
+    {
+      "epoch": 1.607843137254902,
+      "grad_norm": 0.16438259184360504,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.5439,
+      "step": 41
+    },
+    {
+      "epoch": 1.6470588235294117,
+      "grad_norm": 0.17766502499580383,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.6254,
+      "step": 42
+    },
+    {
+      "epoch": 1.6862745098039216,
+      "grad_norm": 0.19429893791675568,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.6226,
+      "step": 43
+    },
+    {
+      "epoch": 1.7254901960784315,
+      "grad_norm": 0.1902369111776352,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.3382,
+      "step": 44
+    },
+    {
+      "epoch": 1.7647058823529411,
+      "grad_norm": 0.1995367556810379,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.7722,
+      "step": 45
+    },
+    {
+      "epoch": 1.803921568627451,
+      "grad_norm": 0.1625039279460907,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.4846,
+      "step": 46
+    },
+    {
+      "epoch": 1.843137254901961,
+      "grad_norm": 0.16078010201454163,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.5672,
+      "step": 47
+    },
+    {
+      "epoch": 1.8823529411764706,
+      "grad_norm": 0.17167764902114868,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.5941,
+      "step": 48
+    },
+    {
+      "epoch": 1.9215686274509802,
+      "grad_norm": 0.18821239471435547,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.657,
+      "step": 49
+    },
+    {
+      "epoch": 1.9607843137254903,
+      "grad_norm": 0.24672283232212067,
+      "learning_rate": 0.0,
+      "loss": 1.8528,
+      "step": 50
+    },
+    {
+      "epoch": 1.9607843137254903,
+      "eval_loss": 1.6053956747055054,
+      "eval_runtime": 4.5336,
+      "eval_samples_per_second": 37.939,
+      "eval_steps_per_second": 4.853,
+      "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": 2.8190589936939827e+17,
+  "total_flos": 5.639875509480325e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null