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:fb52b9f5522d37d401ba16e0385405002fd97b8f7bc76f3224aceeee492b22b3
+oid sha256:887692221ce800c58e31ca474d73570a7ded959a3f253c21eb8c51e3b08feb69
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d55a6cb3c3fe6eaf4fb5382e1d9314594c69a39690e18c6bf2a1098dc2be9841
+oid sha256:96d0db19a57c99f2df798d19a82eab63203a00396a6863a757fdea7007366bd0
 size 113994

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8918ab6488ea2b6c6218a380476dd8e8d93aa884317ee9ebc7daa72f290b6cc
+oid sha256:6db5cd4c91b5f7b00717c9bdd60f16020cdf1633a96704e585b9763503781cdb
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d460e03e7be36bb6953fe212537c7b547040551976fa2365fb0785ec8dd29212
+oid sha256:965808f5157f6cf0a0bdd73585636de09f28a680fa37fe722424c61f276460c8
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31c6148f522d68a5ec4bd049aae50ed9dc2d9bd80caec4d95085da65a54ca7f2
+oid sha256:3746bcf8fd123c91d754401501888b3400d64af751ee70dec16b94542d05f816
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b36f1cae49ffe853c7463b4cd856a8fa7e8997c9954f42c905d89f63d07182d9
+oid sha256:7c06d959e528fbc56583fccb8962c34c61ceeaa5df148697fd488008ae9f0940
 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": 11.93093490600586,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.022120223414256485,
+  "best_metric": 11.93070125579834,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.04424044682851297,
   "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": 503.343,
       "eval_steps_per_second": 62.934,
       "step": 25
+    },
+    {
+      "epoch": 0.023005032350826744,
+      "grad_norm": 0.012165733613073826,
+      "learning_rate": 5e-05,
+      "loss": 11.9318,
+      "step": 26
+    },
+    {
+      "epoch": 0.023889841287397004,
+      "grad_norm": 0.014179449528455734,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 11.9317,
+      "step": 27
+    },
+    {
+      "epoch": 0.024774650223967264,
+      "grad_norm": 0.012790637090802193,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 11.9315,
+      "step": 28
+    },
+    {
+      "epoch": 0.02565945916053752,
+      "grad_norm": 0.014043393544852734,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 11.9309,
+      "step": 29
+    },
+    {
+      "epoch": 0.02654426809710778,
+      "grad_norm": 0.015668494626879692,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 11.9306,
+      "step": 30
+    },
+    {
+      "epoch": 0.02742907703367804,
+      "grad_norm": 0.01923270709812641,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 11.9311,
+      "step": 31
+    },
+    {
+      "epoch": 0.0283138859702483,
+      "grad_norm": 0.015900423750281334,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 11.9315,
+      "step": 32
+    },
+    {
+      "epoch": 0.02919869490681856,
+      "grad_norm": 0.02023705281317234,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 11.9309,
+      "step": 33
+    },
+    {
+      "epoch": 0.030083503843388818,
+      "grad_norm": 0.02101036161184311,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 11.929,
+      "step": 34
+    },
+    {
+      "epoch": 0.030968312779959078,
+      "grad_norm": 0.026951618492603302,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 11.9296,
+      "step": 35
+    },
+    {
+      "epoch": 0.031853121716529334,
+      "grad_norm": 0.029996080324053764,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 11.9302,
+      "step": 36
+    },
+    {
+      "epoch": 0.032737930653099594,
+      "grad_norm": 0.03874776139855385,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 11.9289,
+      "step": 37
+    },
+    {
+      "epoch": 0.03362273958966985,
+      "grad_norm": 0.018332069739699364,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.9324,
+      "step": 38
+    },
+    {
+      "epoch": 0.03450754852624011,
+      "grad_norm": 0.012665345333516598,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 11.9312,
+      "step": 39
+    },
+    {
+      "epoch": 0.03539235746281037,
+      "grad_norm": 0.013432266190648079,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 11.93,
+      "step": 40
+    },
+    {
+      "epoch": 0.03627716639938063,
+      "grad_norm": 0.014370406977832317,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 11.931,
+      "step": 41
+    },
+    {
+      "epoch": 0.03716197533595089,
+      "grad_norm": 0.01412659976631403,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 11.9325,
+      "step": 42
+    },
+    {
+      "epoch": 0.03804678427252115,
+      "grad_norm": 0.01652354560792446,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 11.9302,
+      "step": 43
+    },
+    {
+      "epoch": 0.03893159320909141,
+      "grad_norm": 0.020123157650232315,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 11.931,
+      "step": 44
+    },
+    {
+      "epoch": 0.03981640214566167,
+      "grad_norm": 0.01787555031478405,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 11.9308,
+      "step": 45
+    },
+    {
+      "epoch": 0.04070121108223193,
+      "grad_norm": 0.01903703808784485,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 11.9314,
+      "step": 46
+    },
+    {
+      "epoch": 0.04158602001880219,
+      "grad_norm": 0.022099262103438377,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 11.9287,
+      "step": 47
+    },
+    {
+      "epoch": 0.04247082895537245,
+      "grad_norm": 0.022947920486330986,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 11.9296,
+      "step": 48
+    },
+    {
+      "epoch": 0.04335563789194271,
+      "grad_norm": 0.03329804167151451,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 11.9314,
+      "step": 49
+    },
+    {
+      "epoch": 0.04424044682851297,
+      "grad_norm": 0.06478450447320938,
+      "learning_rate": 0.0,
+      "loss": 11.9282,
+      "step": 50
+    },
+    {
+      "epoch": 0.04424044682851297,
+      "eval_loss": 11.93070125579834,
+      "eval_runtime": 15.0267,
+      "eval_samples_per_second": 506.698,
+      "eval_steps_per_second": 63.354,
+      "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": 521247129600.0,
+  "total_flos": 1042494259200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null