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:bc06f8fb2d1632050ee5340f4ab7502108fafc768e20c3c6b033d780ae244d23
+oid sha256:94efbb6c46dd1cc72b2ec1f9c1598a74bcadf96197896bf2cc8dc5db9b556b87
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fda89b9787d54fa6972b4a5f1ff7cfe5539fabdcc2a804caddeb3b9bfa979a5a
+oid sha256:30a52b5148a8738d71609424415fe43c68e002ad598ed03a4727764ef2d8b0af
 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": 0.7947022318840027,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.15521924718665114,
+  "best_metric": 0.7740952372550964,
+  "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": 36.759,
       "eval_steps_per_second": 4.608,
       "step": 25
+    },
+    {
+      "epoch": 0.1614280170741172,
+      "grad_norm": 5.082066535949707,
+      "learning_rate": 5e-05,
+      "loss": 9.8421,
+      "step": 26
+    },
+    {
+      "epoch": 0.16763678696158324,
+      "grad_norm": 5.646501064300537,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 10.8886,
+      "step": 27
+    },
+    {
+      "epoch": 0.1738455568490493,
+      "grad_norm": 5.460198402404785,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 11.0623,
+      "step": 28
+    },
+    {
+      "epoch": 0.18005432673651534,
+      "grad_norm": 6.139311790466309,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 12.0344,
+      "step": 29
+    },
+    {
+      "epoch": 0.18626309662398138,
+      "grad_norm": 6.533102035522461,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 12.672,
+      "step": 30
+    },
+    {
+      "epoch": 0.19247186651144743,
+      "grad_norm": 7.447323322296143,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 13.082,
+      "step": 31
+    },
+    {
+      "epoch": 0.19868063639891345,
+      "grad_norm": 8.437141418457031,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 13.3574,
+      "step": 32
+    },
+    {
+      "epoch": 0.2048894062863795,
+      "grad_norm": 9.51140308380127,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 13.1222,
+      "step": 33
+    },
+    {
+      "epoch": 0.21109817617384555,
+      "grad_norm": 10.1847562789917,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 13.8075,
+      "step": 34
+    },
+    {
+      "epoch": 0.2173069460613116,
+      "grad_norm": 9.696736335754395,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 12.9002,
+      "step": 35
+    },
+    {
+      "epoch": 0.22351571594877764,
+      "grad_norm": 10.21894645690918,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 13.2216,
+      "step": 36
+    },
+    {
+      "epoch": 0.2297244858362437,
+      "grad_norm": 11.558626174926758,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 13.9245,
+      "step": 37
+    },
+    {
+      "epoch": 0.23593325572370974,
+      "grad_norm": 11.94530963897705,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 12.3904,
+      "step": 38
+    },
+    {
+      "epoch": 0.2421420256111758,
+      "grad_norm": 4.622230052947998,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 10.1714,
+      "step": 39
+    },
+    {
+      "epoch": 0.24835079549864184,
+      "grad_norm": 5.022961139678955,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 11.678,
+      "step": 40
+    },
+    {
+      "epoch": 0.25455956538610786,
+      "grad_norm": 5.296011924743652,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 11.71,
+      "step": 41
+    },
+    {
+      "epoch": 0.2607683352735739,
+      "grad_norm": 5.8643412590026855,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 12.5232,
+      "step": 42
+    },
+    {
+      "epoch": 0.26697710516103995,
+      "grad_norm": 6.14801025390625,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 13.006,
+      "step": 43
+    },
+    {
+      "epoch": 0.273185875048506,
+      "grad_norm": 6.819303035736084,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 12.6432,
+      "step": 44
+    },
+    {
+      "epoch": 0.27939464493597205,
+      "grad_norm": 7.7182722091674805,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 12.9021,
+      "step": 45
+    },
+    {
+      "epoch": 0.2856034148234381,
+      "grad_norm": 8.286754608154297,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 13.2977,
+      "step": 46
+    },
+    {
+      "epoch": 0.29181218471090414,
+      "grad_norm": 8.834489822387695,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 12.9507,
+      "step": 47
+    },
+    {
+      "epoch": 0.2980209545983702,
+      "grad_norm": 10.305696487426758,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 12.9905,
+      "step": 48
+    },
+    {
+      "epoch": 0.30422972448583624,
+      "grad_norm": 11.25792121887207,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 14.2701,
+      "step": 49
+    },
+    {
+      "epoch": 0.3104384943733023,
+      "grad_norm": 16.177717208862305,
+      "learning_rate": 0.0,
+      "loss": 15.1178,
+      "step": 50
+    },
+    {
+      "epoch": 0.3104384943733023,
+      "eval_loss": 0.7740952372550964,
+      "eval_runtime": 29.1943,
+      "eval_samples_per_second": 37.165,
+      "eval_steps_per_second": 4.658,
+      "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