Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b35eea28725b65f7891387643d806e102ed9ad9c948d05defdf01e61a5cd12f
+oid sha256:272a44d9e49292b65361105a7ae3d5c2cbfaeca12ab69656749e2622a4e01c86
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58ac9a1aa4f5a20480afa36c780b179ea2c57a7ba615931955fec4dce4cebad0
+oid sha256:ecc280e2db5474c7cece9fa5a6d14e97d224ba39ead8b748ba7b9831d5f936f4
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbd3b332d744111830efd0fa789d91ed6100351d0847bcf3549926eea71422e8
+oid sha256:7ae75b6da67582b7d77feaadd791d9a6468952db330831063ac49974070e0334
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:693380d7780b275cab7cdbd2c152bebe2eeab3ca832afc452bbf1a31981491aa
+oid sha256:3e3830835d6e24ed395f30629fbf8f47c9088ca5ec192281488160b6fd167b98
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2f1406cb82de5b91ac8401f66e5382bb362a30ae07788576aab97ca1c221765
+oid sha256:4267d8713cf554bf4b6661a2c66237353a8835ce4eb5311a2b2e0f36e32bd2ae
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a44969136895b262c633034ba0f54979d05b6a14779bd38ac32d49d44caf1e3
+oid sha256:43c86e8b09b93063d9db099572b761e53b12335ce688a67db5a13146b84b7ae2
 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": 0.03719233721494675,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0566491998300524,
+  "best_metric": 0.025335997343063354,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.1132983996601048,
   "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": 130.93,
       "eval_steps_per_second": 16.383,
       "step": 25
+    },
+    {
+      "epoch": 0.0589151678232545,
+      "grad_norm": 2.314321279525757,
+      "learning_rate": 5e-05,
+      "loss": 0.4477,
+      "step": 26
+    },
+    {
+      "epoch": 0.061181135816456594,
+      "grad_norm": 0.6433771252632141,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0116,
+      "step": 27
+    },
+    {
+      "epoch": 0.06344710380965869,
+      "grad_norm": 0.34855279326438904,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0054,
+      "step": 28
+    },
+    {
+      "epoch": 0.06571307180286079,
+      "grad_norm": 0.6224886775016785,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0107,
+      "step": 29
+    },
+    {
+      "epoch": 0.06797903979606289,
+      "grad_norm": 0.6813771724700928,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.005,
+      "step": 30
+    },
+    {
+      "epoch": 0.07024500778926497,
+      "grad_norm": 0.5452752113342285,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0065,
+      "step": 31
+    },
+    {
+      "epoch": 0.07251097578246707,
+      "grad_norm": 0.4141976237297058,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0022,
+      "step": 32
+    },
+    {
+      "epoch": 0.07477694377566917,
+      "grad_norm": 0.5566349625587463,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0064,
+      "step": 33
+    },
+    {
+      "epoch": 0.07704291176887126,
+      "grad_norm": 0.6780135631561279,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0079,
+      "step": 34
+    },
+    {
+      "epoch": 0.07930887976207336,
+      "grad_norm": 0.04653328284621239,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0005,
+      "step": 35
+    },
+    {
+      "epoch": 0.08157484775527546,
+      "grad_norm": 0.061018314212560654,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0004,
+      "step": 36
+    },
+    {
+      "epoch": 0.08384081574847756,
+      "grad_norm": 0.03196936100721359,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0003,
+      "step": 37
+    },
+    {
+      "epoch": 0.08610678374167965,
+      "grad_norm": 1.5225857496261597,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.2704,
+      "step": 38
+    },
+    {
+      "epoch": 0.08837275173488174,
+      "grad_norm": 1.1271251440048218,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0143,
+      "step": 39
+    },
+    {
+      "epoch": 0.09063871972808384,
+      "grad_norm": 0.19105099141597748,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0022,
+      "step": 40
+    },
+    {
+      "epoch": 0.09290468772128593,
+      "grad_norm": 0.13457505404949188,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0017,
+      "step": 41
+    },
+    {
+      "epoch": 0.09517065571448803,
+      "grad_norm": 0.036084841936826706,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0004,
+      "step": 42
+    },
+    {
+      "epoch": 0.09743662370769013,
+      "grad_norm": 0.3573283851146698,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.004,
+      "step": 43
+    },
+    {
+      "epoch": 0.09970259170089223,
+      "grad_norm": 0.285297155380249,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0023,
+      "step": 44
+    },
+    {
+      "epoch": 0.10196855969409432,
+      "grad_norm": 0.13393811881542206,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0014,
+      "step": 45
+    },
+    {
+      "epoch": 0.10423452768729642,
+      "grad_norm": 0.010668603703379631,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0001,
+      "step": 46
+    },
+    {
+      "epoch": 0.10650049568049852,
+      "grad_norm": 0.04618118703365326,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0004,
+      "step": 47
+    },
+    {
+      "epoch": 0.1087664636737006,
+      "grad_norm": 0.01658078096807003,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0002,
+      "step": 48
+    },
+    {
+      "epoch": 0.1110324316669027,
+      "grad_norm": 0.06205086410045624,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0004,
+      "step": 49
+    },
+    {
+      "epoch": 0.1132983996601048,
+      "grad_norm": 0.006261133123189211,
+      "learning_rate": 0.0,
+      "loss": 0.0001,
+      "step": 50
+    },
+    {
+      "epoch": 0.1132983996601048,
+      "eval_loss": 0.025335997343063354,
+      "eval_runtime": 22.8454,
+      "eval_samples_per_second": 130.136,
+      "eval_steps_per_second": 16.283,
+      "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": 1.4857327165308928e+16,
+  "total_flos": 2.978847951683584e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null