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:e8df9adffe65a1e94c4037d32e0b6e767d76adae443e289574a0f4a3c296c2a9
+oid sha256:5bc9bd7ccdee5589acc0bf706bb265749a069c3fe7ceb5787ab664c72d2b5e15
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91e8df8da51c302d8be69fed5f3498afd162f4776a23c01469afcfe390503fc9
+oid sha256:3986e92db28997a824c97167d03764575574bf270001b66d28d6e91ec371faf7
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d58bae8df39d78369d353498d420663bd47e568454dbb5071348cd59dea23d73
+oid sha256:3c1dc3fc5c275afe7028cb71398fbb7864c546b1d1537f23f977359be9e3e6ba
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8406036e30585494eae558e18f4e4a9789052c4d4ca1f61bf117dbc3ab962fd
+oid sha256:3a56059646f644dc24f6bc500ff6715dc0f175547351e6706aff1becfa01b76c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1a7572d355ff2d243ac38dd0875cf20618f6ac27c33cd5c3033560c3955c21a
+oid sha256:44f217916fafd14f764d73eb45887e5f739ff93ef804675ee737f9936cf02604
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59e7851525cad255dce2ab95c3080ceb61abac1e5a383dd59468a785f010daf9
+oid sha256:250b328bec3221766effe5b8874e810adadf92f7b6b04c50e3cf5cfe69c9f35b
 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": 0.5439428687095642,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.027754648903691368,
+  "best_metric": 0.5298166275024414,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.055509297807382736,
   "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": 34.013,
       "eval_steps_per_second": 4.254,
       "step": 25
+    },
+    {
+      "epoch": 0.028864834859839022,
+      "grad_norm": 0.07082349061965942,
+      "learning_rate": 5e-05,
+      "loss": 0.5417,
+      "step": 26
+    },
+    {
+      "epoch": 0.02997502081598668,
+      "grad_norm": 0.09529879689216614,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.4697,
+      "step": 27
+    },
+    {
+      "epoch": 0.031085206772134333,
+      "grad_norm": 0.11979064345359802,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.5269,
+      "step": 28
+    },
+    {
+      "epoch": 0.03219539272828199,
+      "grad_norm": 0.15223853290081024,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.5231,
+      "step": 29
+    },
+    {
+      "epoch": 0.03330557868442964,
+      "grad_norm": 0.17808681726455688,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.5009,
+      "step": 30
+    },
+    {
+      "epoch": 0.034415764640577294,
+      "grad_norm": 0.1959284096956253,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.5218,
+      "step": 31
+    },
+    {
+      "epoch": 0.035525950596724955,
+      "grad_norm": 0.19149121642112732,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.5211,
+      "step": 32
+    },
+    {
+      "epoch": 0.03663613655287261,
+      "grad_norm": 0.21555660665035248,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.5526,
+      "step": 33
+    },
+    {
+      "epoch": 0.03774632250902026,
+      "grad_norm": 0.23048672080039978,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.5356,
+      "step": 34
+    },
+    {
+      "epoch": 0.038856508465167916,
+      "grad_norm": 0.2359524667263031,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.5408,
+      "step": 35
+    },
+    {
+      "epoch": 0.03996669442131557,
+      "grad_norm": 0.27337896823883057,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.5737,
+      "step": 36
+    },
+    {
+      "epoch": 0.041076880377463224,
+      "grad_norm": 0.3115023970603943,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.5634,
+      "step": 37
+    },
+    {
+      "epoch": 0.04218706633361088,
+      "grad_norm": 0.09126698970794678,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.6497,
+      "step": 38
+    },
+    {
+      "epoch": 0.04329725228975854,
+      "grad_norm": 0.0780349001288414,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.4434,
+      "step": 39
+    },
+    {
+      "epoch": 0.04440743824590619,
+      "grad_norm": 0.09226205199956894,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.4756,
+      "step": 40
+    },
+    {
+      "epoch": 0.045517624202053845,
+      "grad_norm": 0.10075278580188751,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.5042,
+      "step": 41
+    },
+    {
+      "epoch": 0.0466278101582015,
+      "grad_norm": 0.10810760408639908,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.4929,
+      "step": 42
+    },
+    {
+      "epoch": 0.04773799611434915,
+      "grad_norm": 0.12063668668270111,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.5035,
+      "step": 43
+    },
+    {
+      "epoch": 0.04884818207049681,
+      "grad_norm": 0.13385652005672455,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.5197,
+      "step": 44
+    },
+    {
+      "epoch": 0.04995836802664446,
+      "grad_norm": 0.14498774707317352,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.4995,
+      "step": 45
+    },
+    {
+      "epoch": 0.051068553982792114,
+      "grad_norm": 0.15357857942581177,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.4836,
+      "step": 46
+    },
+    {
+      "epoch": 0.052178739938939775,
+      "grad_norm": 0.2189844846725464,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.5309,
+      "step": 47
+    },
+    {
+      "epoch": 0.05328892589508743,
+      "grad_norm": 0.2006743997335434,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.5585,
+      "step": 48
+    },
+    {
+      "epoch": 0.05439911185123508,
+      "grad_norm": 0.24543078243732452,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.5591,
+      "step": 49
+    },
+    {
+      "epoch": 0.055509297807382736,
+      "grad_norm": 0.4042859673500061,
+      "learning_rate": 0.0,
+      "loss": 0.6439,
+      "step": 50
+    },
+    {
+      "epoch": 0.055509297807382736,
+      "eval_loss": 0.5298166275024414,
+      "eval_runtime": 177.5866,
+      "eval_samples_per_second": 34.169,
+      "eval_steps_per_second": 4.274,
+      "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": 2.6361262648590336e+17,
+  "total_flos": 5.2738959989538816e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null