Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:061a47724973db7caf811de6a890bf9fc499fb17f60dce4105591584c7b53b0d
+oid sha256:0e5538f8d5a2e5aa6731500af3f98ab200c1aa89fa9808ed3aecab0cf032738f
 size 166182480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8ff776bc9a2f677bdb6aa9da3d6a8f319634a4244ba93a4d926b278d7dc958b
+oid sha256:65c8fa09e8114af352c6a7465ffa0da8d9aea4aefb9c1ed1a627dca611fa8f9c
 size 332574358

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eac3e5b11e05a592d4548ac40d586f394330ce4d19ab5372db8ed2b3d62c6e53
+oid sha256:63dda041607609e714748e5ce0bbc3ee6901f6300066835e37bf999ca0a47650
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b341d61bd51eab20562a4de56994db6e3f496e4caefea72cefb7cde82206307d
+oid sha256:1324c1c15552879350607c8fab3b0f962835b4a0b62c552e4ef5e029f83c1bd1
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b06f03763a49036d38fcad862ae0fb2c4ab3b3dfcef889dbc11a30d4fb5636bd
+oid sha256:ee8179fbc55e55e73f73574930fbc34123386dc54da5b4289ab3ec8946ac87f4
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3f1ad1ff8c1dd7fb86ad4e369e1b49b481ece6c94cfef9ade3097e422ee07de
+oid sha256:9975386f5542c1cd9206e241d5be90253c065ca72de5ed3cadce882ea052109b
 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": 0.21203623712062836,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.27229407760381213,
+  "best_metric": 0.16587750613689423,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.5445881552076243,
   "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": 48.488,
       "eval_steps_per_second": 6.11,
       "step": 25
+    },
+    {
+      "epoch": 0.2831858407079646,
+      "grad_norm": 1.9654167890548706,
+      "learning_rate": 5e-05,
+      "loss": 0.2569,
+      "step": 26
+    },
+    {
+      "epoch": 0.29407760381211706,
+      "grad_norm": 1.501623272895813,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.2404,
+      "step": 27
+    },
+    {
+      "epoch": 0.3049693669162696,
+      "grad_norm": 1.7291406393051147,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.2169,
+      "step": 28
+    },
+    {
+      "epoch": 0.31586113002042204,
+      "grad_norm": 1.3261122703552246,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.2232,
+      "step": 29
+    },
+    {
+      "epoch": 0.32675289312457456,
+      "grad_norm": 1.0543931722640991,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.1568,
+      "step": 30
+    },
+    {
+      "epoch": 0.337644656228727,
+      "grad_norm": 1.1441091299057007,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.2081,
+      "step": 31
+    },
+    {
+      "epoch": 0.3485364193328795,
+      "grad_norm": 1.2155985832214355,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.169,
+      "step": 32
+    },
+    {
+      "epoch": 0.359428182437032,
+      "grad_norm": 1.9344199895858765,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.1921,
+      "step": 33
+    },
+    {
+      "epoch": 0.37031994554118447,
+      "grad_norm": 1.575245976448059,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.1606,
+      "step": 34
+    },
+    {
+      "epoch": 0.381211708645337,
+      "grad_norm": 1.478620171546936,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.2003,
+      "step": 35
+    },
+    {
+      "epoch": 0.39210347174948945,
+      "grad_norm": 2.045692205429077,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.181,
+      "step": 36
+    },
+    {
+      "epoch": 0.4029952348536419,
+      "grad_norm": 1.66561758518219,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.2042,
+      "step": 37
+    },
+    {
+      "epoch": 0.41388699795779443,
+      "grad_norm": 1.607456088066101,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.2265,
+      "step": 38
+    },
+    {
+      "epoch": 0.4247787610619469,
+      "grad_norm": 1.426287293434143,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.1721,
+      "step": 39
+    },
+    {
+      "epoch": 0.43567052416609936,
+      "grad_norm": 1.4206467866897583,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.1766,
+      "step": 40
+    },
+    {
+      "epoch": 0.4465622872702519,
+      "grad_norm": 1.2468781471252441,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.1932,
+      "step": 41
+    },
+    {
+      "epoch": 0.45745405037440434,
+      "grad_norm": 1.3370360136032104,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.2293,
+      "step": 42
+    },
+    {
+      "epoch": 0.46834581347855686,
+      "grad_norm": 1.1221462488174438,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.1564,
+      "step": 43
+    },
+    {
+      "epoch": 0.4792375765827093,
+      "grad_norm": 0.933812141418457,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.1989,
+      "step": 44
+    },
+    {
+      "epoch": 0.4901293396868618,
+      "grad_norm": 1.0940755605697632,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.161,
+      "step": 45
+    },
+    {
+      "epoch": 0.5010211027910143,
+      "grad_norm": 1.0236101150512695,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.1711,
+      "step": 46
+    },
+    {
+      "epoch": 0.5119128658951668,
+      "grad_norm": 0.8983817100524902,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.1697,
+      "step": 47
+    },
+    {
+      "epoch": 0.5228046289993192,
+      "grad_norm": 1.1592609882354736,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.1596,
+      "step": 48
+    },
+    {
+      "epoch": 0.5336963921034718,
+      "grad_norm": 1.2694193124771118,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.1864,
+      "step": 49
+    },
+    {
+      "epoch": 0.5445881552076243,
+      "grad_norm": 1.018462896347046,
+      "learning_rate": 0.0,
+      "loss": 0.1808,
+      "step": 50
+    },
+    {
+      "epoch": 0.5445881552076243,
+      "eval_loss": 0.16587750613689423,
+      "eval_runtime": 12.7544,
+      "eval_samples_per_second": 48.532,
+      "eval_steps_per_second": 6.116,
+      "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": 8.1240447254528e+16,
+  "total_flos": 1.62480894509056e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null