Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b853fd06dcaf068cb07764bc33f61864d674d8916566fb499776090dc01ec74
+oid sha256:4295896dccf910479f8a866f75f644b49963815293d0041205f1684e1c67acc4
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:437a83776be6319fc7463f7f05f75c6a544a566f13ec3abb4400a93ca8b2a882
+oid sha256:47232455ecee4343b139406c77a3ddb6469b61c552f6c0386969654b56ebc88b
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af846382a06bff6d09055808d2084e4b5ccef4a212e15adbee771bf5ca80241b
+oid sha256:92e5562be1d3f563da7a6e57a0dcc96d281ac5f679c62aa7c8f6dc0591d82650
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5a085f789d05a13d13caea30a1c5284a39f65ace93cba5bb32f84fcaa2437d0
+oid sha256:10d4f4c182153edbeb3e48c18518736fc928a5df349fae4299e7e7c049eb29c4
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3e4dbbe6be21418b4a327766d8a8c82d58d70478e1c8f490ba91f58b2637bf0
+oid sha256:bce1a987ae6c360785107d24b69d4d6aceac25a671bd9c6a3b3aae5eaa5d7b19
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0ce71fa4c4f3b1f6e9aa9aec6b326e8919abfc71ce3ff28a9dae6167b50b809
+oid sha256:e4b70c3c490e79872e0dfe0643c6efadbf820cb3d775756a6c330e2d7275794c
 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": 0.35994160175323486,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.547945205479452,
+  "best_metric": 0.3289429247379303,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.095890410958904,
   "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": 33.668,
       "eval_steps_per_second": 4.263,
       "step": 25
+    },
+    {
+      "epoch": 0.5698630136986301,
+      "grad_norm": 0.18687774240970612,
+      "learning_rate": 5e-05,
+      "loss": 0.3405,
+      "step": 26
+    },
+    {
+      "epoch": 0.5917808219178082,
+      "grad_norm": 0.3074064254760742,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.3813,
+      "step": 27
+    },
+    {
+      "epoch": 0.6136986301369863,
+      "grad_norm": 0.2549058496952057,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.3335,
+      "step": 28
+    },
+    {
+      "epoch": 0.6356164383561644,
+      "grad_norm": 0.26571619510650635,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.3624,
+      "step": 29
+    },
+    {
+      "epoch": 0.6575342465753424,
+      "grad_norm": 0.15630757808685303,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.3252,
+      "step": 30
+    },
+    {
+      "epoch": 0.6794520547945205,
+      "grad_norm": 0.16660596430301666,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.3038,
+      "step": 31
+    },
+    {
+      "epoch": 0.7013698630136986,
+      "grad_norm": 0.17555654048919678,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.3429,
+      "step": 32
+    },
+    {
+      "epoch": 0.7232876712328767,
+      "grad_norm": 0.23803046345710754,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.3609,
+      "step": 33
+    },
+    {
+      "epoch": 0.7452054794520548,
+      "grad_norm": 0.4200612008571625,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.3764,
+      "step": 34
+    },
+    {
+      "epoch": 0.7671232876712328,
+      "grad_norm": 0.3633013963699341,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.3541,
+      "step": 35
+    },
+    {
+      "epoch": 0.7890410958904109,
+      "grad_norm": 0.24594148993492126,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.3537,
+      "step": 36
+    },
+    {
+      "epoch": 0.810958904109589,
+      "grad_norm": 0.22163063287734985,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.3045,
+      "step": 37
+    },
+    {
+      "epoch": 0.8328767123287671,
+      "grad_norm": 0.2199605107307434,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.357,
+      "step": 38
+    },
+    {
+      "epoch": 0.8547945205479452,
+      "grad_norm": 0.12918148934841156,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.3086,
+      "step": 39
+    },
+    {
+      "epoch": 0.8767123287671232,
+      "grad_norm": 0.14422573149204254,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.3898,
+      "step": 40
+    },
+    {
+      "epoch": 0.8986301369863013,
+      "grad_norm": 0.15807737410068512,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.353,
+      "step": 41
+    },
+    {
+      "epoch": 0.9205479452054794,
+      "grad_norm": 0.1642392873764038,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.3235,
+      "step": 42
+    },
+    {
+      "epoch": 0.9424657534246575,
+      "grad_norm": 0.16775958240032196,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.3054,
+      "step": 43
+    },
+    {
+      "epoch": 0.9643835616438357,
+      "grad_norm": 0.16809241473674774,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.3338,
+      "step": 44
+    },
+    {
+      "epoch": 0.9863013698630136,
+      "grad_norm": 0.21692153811454773,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.3834,
+      "step": 45
+    },
+    {
+      "epoch": 1.0082191780821919,
+      "grad_norm": 0.24826471507549286,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.4381,
+      "step": 46
+    },
+    {
+      "epoch": 1.0301369863013699,
+      "grad_norm": 0.22392581403255463,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.3558,
+      "step": 47
+    },
+    {
+      "epoch": 1.0520547945205478,
+      "grad_norm": 0.1663098931312561,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.3249,
+      "step": 48
+    },
+    {
+      "epoch": 1.073972602739726,
+      "grad_norm": 0.1651916652917862,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.3191,
+      "step": 49
+    },
+    {
+      "epoch": 1.095890410958904,
+      "grad_norm": 0.13541460037231445,
+      "learning_rate": 0.0,
+      "loss": 0.3003,
+      "step": 50
+    },
+    {
+      "epoch": 1.095890410958904,
+      "eval_loss": 0.3289429247379303,
+      "eval_runtime": 9.3344,
+      "eval_samples_per_second": 32.996,
+      "eval_steps_per_second": 4.178,
+      "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": 3.0844441853952e+17,
+  "total_flos": 6.09155760273752e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null