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:f95ad93a5402abe94f87cd2595949868c5297d573384f13d6ef0daf62c28f8a4
+oid sha256:31e31ce4374cac885539c8b2e3eef6dcefc77bcabd1281bfd8a191de1f9cbbe6
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b29f7f2cbde71ced93467747539999c8016c19be7b0427dbcd052748759b510
+oid sha256:bad7af1e77d5420342235736956d43b79be5aad99d8b2adc6f56275d7e5f11b7
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f2604b4e8f70b84bae2dccbf8451aa2a9b99c93297307ace95525b5103e6df9
+oid sha256:a208ea8bfb6b55e33103971a81566825933121df5dffb6dfbcbb4f379f6c89ff
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20ddb683720aff9e37b1f99ba4d50bf97b30833c9637a581f26834d89ae56096
+oid sha256:147256ddbdfc84a0d8f332259bb7e1786422735984ed2f16c4c71ca36b15acd8
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ac62a10d87f4ce7010e866837b2fb99ef400b3829535d75201235d819b677f2
+oid sha256:32acf2b0b5d5d9348f9df64db97bf8e71a912c4e9f0208aae8a3aee5d20d621f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43d19841e1b37aba867e65048bcdf3f66ca5080084b2bb133251d0d6e8b1f60a
+oid sha256:f3e20cc576035018cbd5b89201a9faec3108bfa50e408a8485174e9ef0c10890
 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": 5.3652663230896,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.936768149882904,
+  "best_metric": 5.152682781219482,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.8899297423887589,
   "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": 144.659,
       "eval_steps_per_second": 18.484,
       "step": 25
+    },
+    {
+      "epoch": 0.9742388758782201,
+      "grad_norm": 13.2687406539917,
+      "learning_rate": 5e-05,
+      "loss": 4.985,
+      "step": 26
+    },
+    {
+      "epoch": 1.0281030444964872,
+      "grad_norm": 7.853000640869141,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 9.0735,
+      "step": 27
+    },
+    {
+      "epoch": 1.0655737704918034,
+      "grad_norm": 4.046436309814453,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 4.8913,
+      "step": 28
+    },
+    {
+      "epoch": 1.1030444964871196,
+      "grad_norm": 3.963376760482788,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 4.8945,
+      "step": 29
+    },
+    {
+      "epoch": 1.1405152224824355,
+      "grad_norm": 4.583006858825684,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 4.8019,
+      "step": 30
+    },
+    {
+      "epoch": 1.1779859484777517,
+      "grad_norm": 6.275968551635742,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 4.7463,
+      "step": 31
+    },
+    {
+      "epoch": 1.215456674473068,
+      "grad_norm": 9.818097114562988,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 5.049,
+      "step": 32
+    },
+    {
+      "epoch": 1.2529274004683841,
+      "grad_norm": 4.594455242156982,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 3.8698,
+      "step": 33
+    },
+    {
+      "epoch": 1.2903981264637001,
+      "grad_norm": 5.024101257324219,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 5.8764,
+      "step": 34
+    },
+    {
+      "epoch": 1.3278688524590163,
+      "grad_norm": 3.9479949474334717,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 4.9597,
+      "step": 35
+    },
+    {
+      "epoch": 1.3653395784543325,
+      "grad_norm": 4.403995037078857,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 4.8615,
+      "step": 36
+    },
+    {
+      "epoch": 1.4028103044496487,
+      "grad_norm": 5.2892255783081055,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 4.8566,
+      "step": 37
+    },
+    {
+      "epoch": 1.440281030444965,
+      "grad_norm": 6.962310314178467,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 4.8168,
+      "step": 38
+    },
+    {
+      "epoch": 1.4777517564402811,
+      "grad_norm": 12.050715446472168,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 4.8133,
+      "step": 39
+    },
+    {
+      "epoch": 1.5152224824355973,
+      "grad_norm": 3.8929972648620605,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 4.6656,
+      "step": 40
+    },
+    {
+      "epoch": 1.5526932084309133,
+      "grad_norm": 4.548728942871094,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 4.9074,
+      "step": 41
+    },
+    {
+      "epoch": 1.5901639344262295,
+      "grad_norm": 4.101768970489502,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 4.86,
+      "step": 42
+    },
+    {
+      "epoch": 1.6276346604215457,
+      "grad_norm": 4.838189125061035,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 4.7823,
+      "step": 43
+    },
+    {
+      "epoch": 1.6651053864168617,
+      "grad_norm": 5.12868595123291,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 4.5814,
+      "step": 44
+    },
+    {
+      "epoch": 1.7025761124121779,
+      "grad_norm": 8.626150131225586,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 4.7972,
+      "step": 45
+    },
+    {
+      "epoch": 1.740046838407494,
+      "grad_norm": 3.8954572677612305,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 3.8564,
+      "step": 46
+    },
+    {
+      "epoch": 1.7775175644028103,
+      "grad_norm": 5.1777238845825195,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 5.694,
+      "step": 47
+    },
+    {
+      "epoch": 1.8149882903981265,
+      "grad_norm": 4.219235897064209,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 4.7488,
+      "step": 48
+    },
+    {
+      "epoch": 1.8524590163934427,
+      "grad_norm": 3.980339527130127,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 4.875,
+      "step": 49
+    },
+    {
+      "epoch": 1.8899297423887589,
+      "grad_norm": 5.265361309051514,
+      "learning_rate": 0.0,
+      "loss": 4.5209,
+      "step": 50
+    },
+    {
+      "epoch": 1.8899297423887589,
+      "eval_loss": 5.152682781219482,
+      "eval_runtime": 1.2438,
+      "eval_samples_per_second": 144.72,
+      "eval_steps_per_second": 18.492,
+      "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": 1.47650456322048e+16,
+  "total_flos": 2.95300912644096e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null