Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08d3c6b1b3d3347b8844ecf5a6e439b1c76b17c6424e766f73c4a17076e2ea96
+oid sha256:3487b0c2fae3de0a8a8eb95616e8f63774d074c2348146b86ffcb3e24950b45b
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8edb1b69bac09ef98e6712ab782999a89cebd57520e3a09d82e726ecaacbce50
+oid sha256:82ee2a2c818f810a56dbfdfcedbe805dcfe147e2f4ef80aebc90485788fb2d71
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e8c993e17f574582bbdf375a30b60fd7f753cf01ebe1610726876720b0d525e
+oid sha256:c46cba11b3cd19db671b030569d961e46872ee55e202ddac47d4c52d2ce4c29e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9da0dcdd22a594ec175ef64641e5dc8330c21cf7dcd39a8ca48f8b78d9f4d170
+oid sha256:ab0b5955ab4ecca75153d5338b637e3b553b33dfeb8c1eff287d41e9f9df9786
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:466ee3d856adb420b3330651a92737b153bb1786e3a7f276f95b714ad7843b03
+oid sha256:876492b5a0e1ef4be3998a2dbd592b23586ba6fa221efedd089b1ca0871911e6
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26cbb3b6e563d1d62beb07208146ecb1fc77d13be8a7934714bea3928231d965
+oid sha256:85e188fe49b6a77ced53c465ccce4460002060e795c958af20c7fdaf5047ca4b
 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": 0.7943152189254761,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.15521924718665114,
+  "best_metric": 0.7737893462181091,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.3104384943733023,
   "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": 37.49,
       "eval_steps_per_second": 4.699,
       "step": 25
+    },
+    {
+      "epoch": 0.1614280170741172,
+      "grad_norm": 5.23841667175293,
+      "learning_rate": 5e-05,
+      "loss": 9.8368,
+      "step": 26
+    },
+    {
+      "epoch": 0.16763678696158324,
+      "grad_norm": 5.7673845291137695,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 10.8755,
+      "step": 27
+    },
+    {
+      "epoch": 0.1738455568490493,
+      "grad_norm": 5.600522518157959,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 11.0521,
+      "step": 28
+    },
+    {
+      "epoch": 0.18005432673651534,
+      "grad_norm": 6.365645885467529,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 12.0322,
+      "step": 29
+    },
+    {
+      "epoch": 0.18626309662398138,
+      "grad_norm": 6.707865238189697,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 12.6653,
+      "step": 30
+    },
+    {
+      "epoch": 0.19247186651144743,
+      "grad_norm": 7.5599470138549805,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 13.075,
+      "step": 31
+    },
+    {
+      "epoch": 0.19868063639891345,
+      "grad_norm": 8.722418785095215,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 13.3499,
+      "step": 32
+    },
+    {
+      "epoch": 0.2048894062863795,
+      "grad_norm": 9.730953216552734,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 13.1077,
+      "step": 33
+    },
+    {
+      "epoch": 0.21109817617384555,
+      "grad_norm": 10.38156509399414,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 13.8026,
+      "step": 34
+    },
+    {
+      "epoch": 0.2173069460613116,
+      "grad_norm": 10.160839080810547,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 12.9016,
+      "step": 35
+    },
+    {
+      "epoch": 0.22351571594877764,
+      "grad_norm": 10.482645988464355,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 13.2112,
+      "step": 36
+    },
+    {
+      "epoch": 0.2297244858362437,
+      "grad_norm": 11.845269203186035,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 13.9177,
+      "step": 37
+    },
+    {
+      "epoch": 0.23593325572370974,
+      "grad_norm": 12.381589889526367,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 12.3886,
+      "step": 38
+    },
+    {
+      "epoch": 0.2421420256111758,
+      "grad_norm": 4.745333194732666,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 10.1707,
+      "step": 39
+    },
+    {
+      "epoch": 0.24835079549864184,
+      "grad_norm": 5.162703990936279,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 11.67,
+      "step": 40
+    },
+    {
+      "epoch": 0.25455956538610786,
+      "grad_norm": 5.442695617675781,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 11.7045,
+      "step": 41
+    },
+    {
+      "epoch": 0.2607683352735739,
+      "grad_norm": 6.069660186767578,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 12.5223,
+      "step": 42
+    },
+    {
+      "epoch": 0.26697710516103995,
+      "grad_norm": 6.3282060623168945,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 13.0054,
+      "step": 43
+    },
+    {
+      "epoch": 0.273185875048506,
+      "grad_norm": 6.965819835662842,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 12.6465,
+      "step": 44
+    },
+    {
+      "epoch": 0.27939464493597205,
+      "grad_norm": 7.949313640594482,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 12.9014,
+      "step": 45
+    },
+    {
+      "epoch": 0.2856034148234381,
+      "grad_norm": 8.53378677368164,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 13.3003,
+      "step": 46
+    },
+    {
+      "epoch": 0.29181218471090414,
+      "grad_norm": 9.08571720123291,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 12.9489,
+      "step": 47
+    },
+    {
+      "epoch": 0.2980209545983702,
+      "grad_norm": 10.644171714782715,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 12.9775,
+      "step": 48
+    },
+    {
+      "epoch": 0.30422972448583624,
+      "grad_norm": 11.406867027282715,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 14.2686,
+      "step": 49
+    },
+    {
+      "epoch": 0.3104384943733023,
+      "grad_norm": 16.482465744018555,
+      "learning_rate": 0.0,
+      "loss": 15.1204,
+      "step": 50
+    },
+    {
+      "epoch": 0.3104384943733023,
+      "eval_loss": 0.7737893462181091,
+      "eval_runtime": 28.9523,
+      "eval_samples_per_second": 37.475,
+      "eval_steps_per_second": 4.697,
+      "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": 2.8449238450962432e+17,
+  "total_flos": 5.6880795595309056e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null