Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56cf50b29146b9b5fe744bd7d45466192fdcc8353f6f1f673267528016bc6d4f
+oid sha256:1f67ff7314557a608f34a5f7737df330d241b752a556d554c0cba91236f693c6
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f134330323cf71326381a85fd5488d269086862d69de3b7693e710bf338c9949
+oid sha256:14248f66d6f2619860de32f35e44b7ba0e595a476be30ab1941bf34b5d07522b
 size 113994

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7598b6f39885dabd4fb474d1d98b608a282ca745245663fa3ce638f02b4f7bad
+oid sha256:16826b2fce8db3fe3ab2b027d70f573e114425a7eeb7ceffb623f5295d998b1f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efb52b3f6669e3b2f7e1f0f322e7e88281c8a1eec782436e0d8afed5eed27c34
+oid sha256:eeefda0b7c471f34d53e0c4cd6318033e32c4b4c947b810ca391e01bc88d9655
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2da7c96ce784b18749e468e78ac57dea202a8cbe3fcbbf9082a8e11d1c60b2f5
+oid sha256:ba69ff26889ca94f33b819509860c7a6c6d70561e64080cd64aec8806c318077
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad66b02dbdcda1b8a7d887267601393d0f18bf4fa60e97ceb659ddd247cad4b2
+oid sha256:7861627398ce6d12addb4b180d8bba983e6751c77b273904adb14449f3d0391c
 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": 11.931645393371582,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.3888888888888888,
+  "best_metric": 11.930959701538086,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.7777777777777777,
   "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": 435.707,
       "eval_steps_per_second": 57.614,
       "step": 25
+    },
+    {
+      "epoch": 1.4444444444444444,
+      "grad_norm": 0.017678676173090935,
+      "learning_rate": 5e-05,
+      "loss": 11.9328,
+      "step": 26
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.021845893934369087,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 11.9308,
+      "step": 27
+    },
+    {
+      "epoch": 1.5555555555555556,
+      "grad_norm": 0.022769257426261902,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 11.9299,
+      "step": 28
+    },
+    {
+      "epoch": 1.6111111111111112,
+      "grad_norm": 0.026064997538924217,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 11.9315,
+      "step": 29
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.017668651416897774,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 11.9318,
+      "step": 30
+    },
+    {
+      "epoch": 1.7222222222222223,
+      "grad_norm": 0.02388639561831951,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 11.9326,
+      "step": 31
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 0.0233757346868515,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 11.9302,
+      "step": 32
+    },
+    {
+      "epoch": 1.8333333333333335,
+      "grad_norm": 0.02187464013695717,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 11.9291,
+      "step": 33
+    },
+    {
+      "epoch": 1.8888888888888888,
+      "grad_norm": 0.023511428385972977,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 11.9305,
+      "step": 34
+    },
+    {
+      "epoch": 1.9444444444444444,
+      "grad_norm": 0.025736413896083832,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 11.9306,
+      "step": 35
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.02582811564207077,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 11.9313,
+      "step": 36
+    },
+    {
+      "epoch": 2.0555555555555554,
+      "grad_norm": 0.02202489972114563,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 11.9324,
+      "step": 37
+    },
+    {
+      "epoch": 2.111111111111111,
+      "grad_norm": 0.024345090612769127,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.9282,
+      "step": 38
+    },
+    {
+      "epoch": 2.1666666666666665,
+      "grad_norm": 0.02134646661579609,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 11.9291,
+      "step": 39
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.026549415662884712,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 11.9334,
+      "step": 40
+    },
+    {
+      "epoch": 2.2777777777777777,
+      "grad_norm": 0.02680145390331745,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 11.932,
+      "step": 41
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 0.02874022163450718,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 11.9292,
+      "step": 42
+    },
+    {
+      "epoch": 2.388888888888889,
+      "grad_norm": 0.02543819695711136,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 11.9291,
+      "step": 43
+    },
+    {
+      "epoch": 2.4444444444444446,
+      "grad_norm": 0.02165454439818859,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 11.9291,
+      "step": 44
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.02238444611430168,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 11.9317,
+      "step": 45
+    },
+    {
+      "epoch": 2.5555555555555554,
+      "grad_norm": 0.03011086955666542,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 11.929,
+      "step": 46
+    },
+    {
+      "epoch": 2.611111111111111,
+      "grad_norm": 0.024565398693084717,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 11.9307,
+      "step": 47
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.028965452685952187,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 11.9326,
+      "step": 48
+    },
+    {
+      "epoch": 2.7222222222222223,
+      "grad_norm": 0.028163012117147446,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 11.9299,
+      "step": 49
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 0.02760309912264347,
+      "learning_rate": 0.0,
+      "loss": 11.9299,
+      "step": 50
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "eval_loss": 11.930959701538086,
+      "eval_runtime": 0.2723,
+      "eval_samples_per_second": 444.413,
+      "eval_steps_per_second": 58.765,
+      "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