Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:066372100e59f9bbf244eb45a24674a114a09e0f4b3fe9872293c2bf6ddcb6ce
+oid sha256:8a840ef8911a54282c79e3a30c3bd7ceffdb8d7bc538482b0bb6d21e48d2bf8f
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad0e03c645cce83736f1192d9c8e6467b83a1dc312bf91257001799c9878cf91
+oid sha256:4cab0f4eaa8b837b9d11ac0cf7df09bec3aae4ee41c02ffd6b8bb8f89a282d20
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ade36b14dfdaca9213b377b12145f1d95afc695166fe63d9fab95bbd84c023ac
+oid sha256:62a9d43fd942c53428b8b0567abc5052d30717aee499e7e461d54f82f03aa129
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d270648c3c7cfea284af46d89db1a33ce9b1963a365650bb5b6278c9e439ca0
+oid sha256:ac1472cc48b9756805272b4e5e7ea5f95dbeacea7d8d3fea8596b98f618a09e7
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4517da5e8cf77a829cb8cd3c52b4b9af16e4d568d2ca7d06a28e7cf8b4aaa2f
+oid sha256:e7032556ea01e3a730b502fb64d00ca55704263bcec3c80225d30c60ccb5878c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e772cf66a3ba7e5cc72c8a00a2b745c8057d5048c155ba1566478398d0620b4
+oid sha256:8b9177c1cb3dd077b8f09cb630ad1cd1775aa4f1413bffb09d2a45e7f53367f6
 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": 1.8497321605682373,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.3257328990228013,
+  "best_metric": 1.6364974975585938,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6514657980456026,
   "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": 14.753,
       "eval_steps_per_second": 1.855,
       "step": 25
+    },
+    {
+      "epoch": 0.33876221498371334,
+      "grad_norm": 3.126537322998047,
+      "learning_rate": 5e-05,
+      "loss": 2.334,
+      "step": 26
+    },
+    {
+      "epoch": 0.3517915309446254,
+      "grad_norm": 2.8516461849212646,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 2.2191,
+      "step": 27
+    },
+    {
+      "epoch": 0.36482084690553745,
+      "grad_norm": 2.3945906162261963,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.9688,
+      "step": 28
+    },
+    {
+      "epoch": 0.3778501628664495,
+      "grad_norm": 2.310314893722534,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 2.0874,
+      "step": 29
+    },
+    {
+      "epoch": 0.39087947882736157,
+      "grad_norm": 1.7133766412734985,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.7127,
+      "step": 30
+    },
+    {
+      "epoch": 0.40390879478827363,
+      "grad_norm": 1.4484285116195679,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.85,
+      "step": 31
+    },
+    {
+      "epoch": 0.4169381107491857,
+      "grad_norm": 1.6178475618362427,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.8242,
+      "step": 32
+    },
+    {
+      "epoch": 0.42996742671009774,
+      "grad_norm": 1.761211633682251,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.8236,
+      "step": 33
+    },
+    {
+      "epoch": 0.44299674267100975,
+      "grad_norm": 1.6516574621200562,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.6752,
+      "step": 34
+    },
+    {
+      "epoch": 0.4560260586319218,
+      "grad_norm": 1.892453670501709,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.5268,
+      "step": 35
+    },
+    {
+      "epoch": 0.46905537459283386,
+      "grad_norm": 2.1260995864868164,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.4358,
+      "step": 36
+    },
+    {
+      "epoch": 0.4820846905537459,
+      "grad_norm": 2.8658289909362793,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.1276,
+      "step": 37
+    },
+    {
+      "epoch": 0.495114006514658,
+      "grad_norm": 1.7747468948364258,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.8955,
+      "step": 38
+    },
+    {
+      "epoch": 0.50814332247557,
+      "grad_norm": 1.4957735538482666,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.9969,
+      "step": 39
+    },
+    {
+      "epoch": 0.5211726384364821,
+      "grad_norm": 1.5842951536178589,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.945,
+      "step": 40
+    },
+    {
+      "epoch": 0.5342019543973942,
+      "grad_norm": 1.5380773544311523,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.8555,
+      "step": 41
+    },
+    {
+      "epoch": 0.5472312703583062,
+      "grad_norm": 1.4480125904083252,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.8338,
+      "step": 42
+    },
+    {
+      "epoch": 0.5602605863192183,
+      "grad_norm": 1.4359397888183594,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.8938,
+      "step": 43
+    },
+    {
+      "epoch": 0.5732899022801303,
+      "grad_norm": 1.5077005624771118,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.7053,
+      "step": 44
+    },
+    {
+      "epoch": 0.5863192182410424,
+      "grad_norm": 1.3663792610168457,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.5489,
+      "step": 45
+    },
+    {
+      "epoch": 0.5993485342019544,
+      "grad_norm": 1.5573303699493408,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.6144,
+      "step": 46
+    },
+    {
+      "epoch": 0.6123778501628665,
+      "grad_norm": 1.746208667755127,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.7701,
+      "step": 47
+    },
+    {
+      "epoch": 0.6254071661237784,
+      "grad_norm": 1.730631709098816,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.3525,
+      "step": 48
+    },
+    {
+      "epoch": 0.6384364820846905,
+      "grad_norm": 1.7781802415847778,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.1731,
+      "step": 49
+    },
+    {
+      "epoch": 0.6514657980456026,
+      "grad_norm": 2.566715955734253,
+      "learning_rate": 0.0,
+      "loss": 0.5103,
+      "step": 50
+    },
+    {
+      "epoch": 0.6514657980456026,
+      "eval_loss": 1.6364974975585938,
+      "eval_runtime": 34.9713,
+      "eval_samples_per_second": 14.784,
+      "eval_steps_per_second": 1.859,
+      "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