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:d6d612a4b556fda3ffbdc94e168850a456ec5d5cfea53024b6acec13afd55246
+oid sha256:8d4cc67e90b204bab0e95f4939d6046c38a708a38e09b7bf9416c3509af08d68
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7208b2fc1693b4137506277ef4170dcf85f261f42a7c3fa77f83fa9eab406c5f
+oid sha256:8b1c7b392ac59d7d8555f2f9f815093e09c5e7ec08ad7cea366e2644e4c0c90a
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a4a4f5a570ff59d460a1315f6817f9576c81b3c92fa74d8d76a196325006ce4
+oid sha256:4c610f0971cef331989dce54d8f1cde403a7c6ba3bdd6e61b397766484f94ad2
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc140d454dc21311d968a1fcd87e6e8e4f3bfe529dcd970cd2f603cb5021c148
+oid sha256:d3ed26d2291ef0f2d081bcefc9e75802b9cc6d5aa741092fdd44e3b6663c180d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:861a877e01d88173e124e284305ac429d4f3b27a20a23d3b2b3def7a26e2d465
+oid sha256:c311819a7d1d1d1ab0215277f73d24df05c14e35d37762e15218c0972b55578e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86fac4d9b85f5853df7254fbab4611ce4d9f15b959be830a856b9076701912bd
+oid sha256:07cdb1c4434efb04bba7ea36a4b43adb0db8168b16ba6467e3c52e07dcfb3ba4
 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": 0.7349157929420471,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.059092923622396216,
+  "best_metric": 0.43964827060699463,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.11818584724479243,
   "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": 39.582,
       "eval_steps_per_second": 4.956,
       "step": 25
+    },
+    {
+      "epoch": 0.06145664056729207,
+      "grad_norm": 6.81027364730835,
+      "learning_rate": 5e-05,
+      "loss": 0.7863,
+      "step": 26
+    },
+    {
+      "epoch": 0.06382035751218791,
+      "grad_norm": 6.804386615753174,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.6702,
+      "step": 27
+    },
+    {
+      "epoch": 0.06618407445708377,
+      "grad_norm": 3.710777521133423,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.5357,
+      "step": 28
+    },
+    {
+      "epoch": 0.06854779140197961,
+      "grad_norm": 1.793501853942871,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.5255,
+      "step": 29
+    },
+    {
+      "epoch": 0.07091150834687546,
+      "grad_norm": 2.5684709548950195,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.4421,
+      "step": 30
+    },
+    {
+      "epoch": 0.07327522529177131,
+      "grad_norm": 2.64495587348938,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.4837,
+      "step": 31
+    },
+    {
+      "epoch": 0.07563894223666716,
+      "grad_norm": 2.0679728984832764,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.5774,
+      "step": 32
+    },
+    {
+      "epoch": 0.078002659181563,
+      "grad_norm": 2.1068263053894043,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.5622,
+      "step": 33
+    },
+    {
+      "epoch": 0.08036637612645886,
+      "grad_norm": 1.217808723449707,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.547,
+      "step": 34
+    },
+    {
+      "epoch": 0.0827300930713547,
+      "grad_norm": 1.464884877204895,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.6351,
+      "step": 35
+    },
+    {
+      "epoch": 0.08509381001625055,
+      "grad_norm": 2.206184148788452,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.7301,
+      "step": 36
+    },
+    {
+      "epoch": 0.0874575269611464,
+      "grad_norm": 2.669191837310791,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.7922,
+      "step": 37
+    },
+    {
+      "epoch": 0.08982124390604225,
+      "grad_norm": 1.2713346481323242,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.4818,
+      "step": 38
+    },
+    {
+      "epoch": 0.0921849608509381,
+      "grad_norm": 2.1288211345672607,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.4209,
+      "step": 39
+    },
+    {
+      "epoch": 0.09454867779583395,
+      "grad_norm": 2.2356045246124268,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.4351,
+      "step": 40
+    },
+    {
+      "epoch": 0.0969123947407298,
+      "grad_norm": 1.6320451498031616,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.3995,
+      "step": 41
+    },
+    {
+      "epoch": 0.09927611168562564,
+      "grad_norm": 1.082404613494873,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.3726,
+      "step": 42
+    },
+    {
+      "epoch": 0.1016398286305215,
+      "grad_norm": 0.9784598350524902,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.408,
+      "step": 43
+    },
+    {
+      "epoch": 0.10400354557541734,
+      "grad_norm": 1.1016899347305298,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.401,
+      "step": 44
+    },
+    {
+      "epoch": 0.1063672625203132,
+      "grad_norm": 1.2457271814346313,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.5021,
+      "step": 45
+    },
+    {
+      "epoch": 0.10873097946520904,
+      "grad_norm": 1.1428277492523193,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.4453,
+      "step": 46
+    },
+    {
+      "epoch": 0.11109469641010489,
+      "grad_norm": 1.4190499782562256,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.4054,
+      "step": 47
+    },
+    {
+      "epoch": 0.11345841335500075,
+      "grad_norm": 1.0377637147903442,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.5298,
+      "step": 48
+    },
+    {
+      "epoch": 0.11582213029989659,
+      "grad_norm": 1.4322923421859741,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.5594,
+      "step": 49
+    },
+    {
+      "epoch": 0.11818584724479243,
+      "grad_norm": 2.3901617527008057,
+      "learning_rate": 0.0,
+      "loss": 0.5083,
+      "step": 50
+    },
+    {
+      "epoch": 0.11818584724479243,
+      "eval_loss": 0.43964827060699463,
+      "eval_runtime": 72.0723,
+      "eval_samples_per_second": 39.558,
+      "eval_steps_per_second": 4.953,
+      "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": 5.29768176943104e+16,
+  "total_flos": 1.059536353886208e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null