Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a0ff00f26a5ce68905aac3f44a68643b647fba551dd1060771d62c22ebdb5b3
+oid sha256:fad9d687823174673ef46b8459ceeeb7acff21e1c01bcd9040d2e2b436d3a9b5
 size 125048

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5d007c0802c95961bdcf10d7a25ddb97e839f7d2d304b27dd6b8a2964950814
+oid sha256:27fbdaadd028c4a8e7e013653a7fb85ea5046be4fe22ec176cab0c471fd61d16
 size 259694

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c0d221d391772c5177ac94ead6b1d7c6e5fda2059a23f98645e3bacab6683d0
+oid sha256:b9f177b0a616544991c355a602fc44359f85919cccd4f774e3c451b32fbb269a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a38ad17f0f7476a5f7b9b785f6e23624a0ac9b27eafc85afc0dce8c81e212e1
+oid sha256:e1c7cc8c226859ad1f10589b4b41d61124d17e3baee535e70f0e7e619af15392
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3247bb85794644364c6a2ecf98a508363e1c1f245d9d4902665955e4cbd77a5
+oid sha256:a1c22792a095b966806a41ea996662ee03de4efce375ccd4430dd7ea2234debb
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9124a1f49216fd35d436ffff577a58691e98ed5c78836500a130e7974aed6561
+oid sha256:dcbc50f08905c98f54e275f2313fd0fa99c117a0b84c439a7f0c680e4471e93f
 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": 11.06025218963623,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.014089468122578372,
+  "best_metric": 11.053731918334961,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.028178936245156744,
   "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": 381.846,
       "eval_steps_per_second": 47.755,
       "step": 25
+    },
+    {
+      "epoch": 0.014653046847481508,
+      "grad_norm": 2.4210100173950195,
+      "learning_rate": 5e-05,
+      "loss": 11.0712,
+      "step": 26
+    },
+    {
+      "epoch": 0.015216625572384642,
+      "grad_norm": 2.481902837753296,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 11.0683,
+      "step": 27
+    },
+    {
+      "epoch": 0.015780204297287777,
+      "grad_norm": 2.5407965183258057,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 11.0656,
+      "step": 28
+    },
+    {
+      "epoch": 0.016343783022190913,
+      "grad_norm": 2.7125489711761475,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 11.0636,
+      "step": 29
+    },
+    {
+      "epoch": 0.016907361747094046,
+      "grad_norm": 2.6007189750671387,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 11.0622,
+      "step": 30
+    },
+    {
+      "epoch": 0.01747094047199718,
+      "grad_norm": 2.8290154933929443,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 11.0612,
+      "step": 31
+    },
+    {
+      "epoch": 0.018034519196900318,
+      "grad_norm": 2.8195149898529053,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 11.0589,
+      "step": 32
+    },
+    {
+      "epoch": 0.01859809792180345,
+      "grad_norm": 3.0784177780151367,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 11.0566,
+      "step": 33
+    },
+    {
+      "epoch": 0.019161676646706587,
+      "grad_norm": 3.2739195823669434,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 11.051,
+      "step": 34
+    },
+    {
+      "epoch": 0.019725255371609723,
+      "grad_norm": 3.4489872455596924,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 11.0483,
+      "step": 35
+    },
+    {
+      "epoch": 0.020288834096512855,
+      "grad_norm": 3.652323007583618,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 11.0443,
+      "step": 36
+    },
+    {
+      "epoch": 0.02085241282141599,
+      "grad_norm": 4.315981864929199,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 11.035,
+      "step": 37
+    },
+    {
+      "epoch": 0.021415991546319128,
+      "grad_norm": 3.317058801651001,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.0681,
+      "step": 38
+    },
+    {
+      "epoch": 0.02197957027122226,
+      "grad_norm": 2.5080556869506836,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 11.0645,
+      "step": 39
+    },
+    {
+      "epoch": 0.022543148996125396,
+      "grad_norm": 2.5103037357330322,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 11.0626,
+      "step": 40
+    },
+    {
+      "epoch": 0.023106727721028533,
+      "grad_norm": 2.451432943344116,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 11.0599,
+      "step": 41
+    },
+    {
+      "epoch": 0.023670306445931665,
+      "grad_norm": 2.5236127376556396,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 11.0584,
+      "step": 42
+    },
+    {
+      "epoch": 0.0242338851708348,
+      "grad_norm": 2.873950719833374,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 11.0588,
+      "step": 43
+    },
+    {
+      "epoch": 0.024797463895737937,
+      "grad_norm": 2.6781861782073975,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 11.0546,
+      "step": 44
+    },
+    {
+      "epoch": 0.02536104262064107,
+      "grad_norm": 3.1395905017852783,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 11.0512,
+      "step": 45
+    },
+    {
+      "epoch": 0.025924621345544206,
+      "grad_norm": 3.0906121730804443,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 11.0513,
+      "step": 46
+    },
+    {
+      "epoch": 0.026488200070447342,
+      "grad_norm": 3.3439362049102783,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 11.0448,
+      "step": 47
+    },
+    {
+      "epoch": 0.027051778795350475,
+      "grad_norm": 3.662097930908203,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 11.0452,
+      "step": 48
+    },
+    {
+      "epoch": 0.02761535752025361,
+      "grad_norm": 3.9063897132873535,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 11.0423,
+      "step": 49
+    },
+    {
+      "epoch": 0.028178936245156744,
+      "grad_norm": 4.108514785766602,
+      "learning_rate": 0.0,
+      "loss": 11.0579,
+      "step": 50
+    },
+    {
+      "epoch": 0.028178936245156744,
+      "eval_loss": 11.053731918334961,
+      "eval_runtime": 31.3031,
+      "eval_samples_per_second": 381.879,
+      "eval_steps_per_second": 47.759,
+      "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": 2101346304000.0,
+  "total_flos": 4202692608000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null