Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a37ada957b075120153e288324f4c71230e630ccaa1ed1ca975758767b20a15
+oid sha256:b8793356e70ec58c4af9aafea7c18369d2b101df1ff354111068156b4116ac1b
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9385a854a7813ffed7b6f9e6f467eb885fc8baff8fb21d466f871f747367274
+oid sha256:fbcf5f750d1c173dd6a003f84cbd66a3c580da237f8790610a7b8a0f1ee0869e
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fbac82872220d3ac9953a299414c2543ae3ae584a2e149fd69ee4a069bad6d5
+oid sha256:b2584b6f6763beda15afd241e5567b8d5ce277c4ef06e8663d1a46080aace779
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfb50b0d14c08fcf0ff0fbb89d29698b97fe5cc1f6cfe0aace66cd2d68752ef3
+oid sha256:33c5604ad79dfaba64bb29fad5a8c634fa2bb73b72f46d10215da41a40151e2c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f35898e0d5606e3d735135579a3a4634214e92ce934bf5e26df39d3e847279b
+oid sha256:03ab41d4322b33b2263ba36a6cc4a79fea1d7efc34bd497b3c81d9cee63f65e2
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2f8667c4a6275f5aab75b2dc7a11ca2d16320fd652feb77597a810c36c5d6ec
+oid sha256:2b183f01b3d9bafb8c8b4e3a7be229cb829b8904c45fbb38fe401499a0615ad5
 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": 0.706183910369873,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.25046963055729493,
+  "best_metric": 0.6975266933441162,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.5009392611145899,
   "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": 14.61,
       "eval_steps_per_second": 1.845,
       "step": 25
+    },
+    {
+      "epoch": 0.2604884157795867,
+      "grad_norm": 1.7407032251358032,
+      "learning_rate": 5e-05,
+      "loss": 0.7019,
+      "step": 26
+    },
+    {
+      "epoch": 0.27050720100187853,
+      "grad_norm": 2.0007925033569336,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.717,
+      "step": 27
+    },
+    {
+      "epoch": 0.2805259862241703,
+      "grad_norm": 0.8222341537475586,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.7022,
+      "step": 28
+    },
+    {
+      "epoch": 0.2905447714464621,
+      "grad_norm": 0.5266323089599609,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.6961,
+      "step": 29
+    },
+    {
+      "epoch": 0.3005635566687539,
+      "grad_norm": 1.0686484575271606,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.6998,
+      "step": 30
+    },
+    {
+      "epoch": 0.3105823418910457,
+      "grad_norm": 1.4659148454666138,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.7096,
+      "step": 31
+    },
+    {
+      "epoch": 0.3206011271133375,
+      "grad_norm": 1.5614680051803589,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.7331,
+      "step": 32
+    },
+    {
+      "epoch": 0.3306199123356293,
+      "grad_norm": 1.1308493614196777,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.6886,
+      "step": 33
+    },
+    {
+      "epoch": 0.3406386975579211,
+      "grad_norm": 0.8040462136268616,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.683,
+      "step": 34
+    },
+    {
+      "epoch": 0.3506574827802129,
+      "grad_norm": 0.9638981223106384,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.6955,
+      "step": 35
+    },
+    {
+      "epoch": 0.3606762680025047,
+      "grad_norm": 1.0209765434265137,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.7049,
+      "step": 36
+    },
+    {
+      "epoch": 0.3706950532247965,
+      "grad_norm": 1.262820839881897,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.7136,
+      "step": 37
+    },
+    {
+      "epoch": 0.3807138384470883,
+      "grad_norm": 2.151529312133789,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.7393,
+      "step": 38
+    },
+    {
+      "epoch": 0.3907326236693801,
+      "grad_norm": 1.1610045433044434,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.7056,
+      "step": 39
+    },
+    {
+      "epoch": 0.4007514088916719,
+      "grad_norm": 1.2098160982131958,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.7006,
+      "step": 40
+    },
+    {
+      "epoch": 0.4107701941139637,
+      "grad_norm": 0.9664765000343323,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.6956,
+      "step": 41
+    },
+    {
+      "epoch": 0.4207889793362555,
+      "grad_norm": 1.203643560409546,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.7046,
+      "step": 42
+    },
+    {
+      "epoch": 0.4308077645585473,
+      "grad_norm": 0.6147630214691162,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.6929,
+      "step": 43
+    },
+    {
+      "epoch": 0.44082654978083907,
+      "grad_norm": 0.6237002611160278,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.694,
+      "step": 44
+    },
+    {
+      "epoch": 0.45084533500313084,
+      "grad_norm": 0.5813843011856079,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.6934,
+      "step": 45
+    },
+    {
+      "epoch": 0.46086412022542267,
+      "grad_norm": 1.0662013292312622,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.6976,
+      "step": 46
+    },
+    {
+      "epoch": 0.47088290544771444,
+      "grad_norm": 0.3259460926055908,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.6966,
+      "step": 47
+    },
+    {
+      "epoch": 0.48090169067000627,
+      "grad_norm": 0.7798888683319092,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.6943,
+      "step": 48
+    },
+    {
+      "epoch": 0.49092047589229804,
+      "grad_norm": 0.5741135478019714,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.6957,
+      "step": 49
+    },
+    {
+      "epoch": 0.5009392611145899,
+      "grad_norm": 1.043524146080017,
+      "learning_rate": 0.0,
+      "loss": 0.6907,
+      "step": 50
+    },
+    {
+      "epoch": 0.5009392611145899,
+      "eval_loss": 0.6975266933441162,
+      "eval_runtime": 46.0667,
+      "eval_samples_per_second": 14.609,
+      "eval_steps_per_second": 1.845,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null