Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3886dcceb88b9286b8ae1e70dc4e66a621984553041a313467bbbe1eaba010db
+oid sha256:767e9d86f4cb689284107d56144fd22c314ad83fc0f9562c8f6843af4ee94606
 size 90207248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:276d67b491cda6246dec29b67a06fbdaf0b940a101188f3d4c4a02dd9b86cfd5
+oid sha256:2b09ff2fabf58662e3f8dad152232957838fe03cefe512a5f929f33e7cf4c4e8
 size 180543866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed681a3a77ec1f87a0d312d1e3a77f2140af7f0f4e68037ff8780b501e5c3e43
+oid sha256:21a671a065dc691b9f6cfb4265a3cbe447c094050e78c8ee163b1403969e9966
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b24cae9bb2939406849b8014f1d2e511fb99c803ec98b3aba4d07c85416fa3d
+oid sha256:6c4ee5b7f4f515385e614803bd882d404d4b9310ea6cbb2d44b95ffc3f2ce625
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cd877b2609e321b5df458bb432148f8158f1c0c10ed62fbed6c41244868efcc
+oid sha256:fff838b9294bba3058f788948aa8936ad895375333aa349adb2735b9c5d81791
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eec3c4ed5ad0ca0727c60b4f972b5d784502ac03e5aba187e3a8db75170d4840
+oid sha256:c7e5bc69cdfbdd2703595794379cf7ddad5e0d8c9b285fe2cfc963845e9c061c
 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": 0.03744269162416458,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.005947071067499257,
+  "best_metric": 0.021467845886945724,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.011894142134998514,
   "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": 40.799,
       "eval_steps_per_second": 5.1,
       "step": 25
+    },
+    {
+      "epoch": 0.006184953910199227,
+      "grad_norm": 5.12270975112915,
+      "learning_rate": 5e-05,
+      "loss": 0.0628,
+      "step": 26
+    },
+    {
+      "epoch": 0.006422836752899197,
+      "grad_norm": 0.4506359100341797,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0383,
+      "step": 27
+    },
+    {
+      "epoch": 0.006660719595599167,
+      "grad_norm": 0.2883658707141876,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0116,
+      "step": 28
+    },
+    {
+      "epoch": 0.006898602438299138,
+      "grad_norm": 0.3664928376674652,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0157,
+      "step": 29
+    },
+    {
+      "epoch": 0.007136485280999108,
+      "grad_norm": 0.5137994289398193,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0344,
+      "step": 30
+    },
+    {
+      "epoch": 0.007374368123699078,
+      "grad_norm": 0.3177562952041626,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0086,
+      "step": 31
+    },
+    {
+      "epoch": 0.0076122509663990486,
+      "grad_norm": 0.3575591742992401,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0141,
+      "step": 32
+    },
+    {
+      "epoch": 0.00785013380909902,
+      "grad_norm": 0.6437414288520813,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0474,
+      "step": 33
+    },
+    {
+      "epoch": 0.00808801665179899,
+      "grad_norm": 0.5256926417350769,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0398,
+      "step": 34
+    },
+    {
+      "epoch": 0.008325899494498959,
+      "grad_norm": 0.528218150138855,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0182,
+      "step": 35
+    },
+    {
+      "epoch": 0.00856378233719893,
+      "grad_norm": 0.4154456853866577,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0144,
+      "step": 36
+    },
+    {
+      "epoch": 0.0088016651798989,
+      "grad_norm": 0.2326408475637436,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0052,
+      "step": 37
+    },
+    {
+      "epoch": 0.00903954802259887,
+      "grad_norm": 0.6743408441543579,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0477,
+      "step": 38
+    },
+    {
+      "epoch": 0.009277430865298841,
+      "grad_norm": 0.47138625383377075,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0158,
+      "step": 39
+    },
+    {
+      "epoch": 0.00951531370799881,
+      "grad_norm": 0.7161089181900024,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0229,
+      "step": 40
+    },
+    {
+      "epoch": 0.00975319655069878,
+      "grad_norm": 0.5954609513282776,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0255,
+      "step": 41
+    },
+    {
+      "epoch": 0.009991079393398751,
+      "grad_norm": 0.6990079283714294,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0256,
+      "step": 42
+    },
+    {
+      "epoch": 0.010228962236098722,
+      "grad_norm": 0.3620032072067261,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0108,
+      "step": 43
+    },
+    {
+      "epoch": 0.010466845078798692,
+      "grad_norm": 0.24278657138347626,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0361,
+      "step": 44
+    },
+    {
+      "epoch": 0.010704727921498661,
+      "grad_norm": 0.24923881888389587,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0229,
+      "step": 45
+    },
+    {
+      "epoch": 0.010942610764198632,
+      "grad_norm": 0.18173465132713318,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0215,
+      "step": 46
+    },
+    {
+      "epoch": 0.011180493606898602,
+      "grad_norm": 0.14647623896598816,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0184,
+      "step": 47
+    },
+    {
+      "epoch": 0.011418376449598573,
+      "grad_norm": 0.18817275762557983,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0171,
+      "step": 48
+    },
+    {
+      "epoch": 0.011656259292298543,
+      "grad_norm": 0.2422836571931839,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0185,
+      "step": 49
+    },
+    {
+      "epoch": 0.011894142134998514,
+      "grad_norm": 0.5552806258201599,
+      "learning_rate": 0.0,
+      "loss": 0.0471,
+      "step": 50
+    },
+    {
+      "epoch": 0.011894142134998514,
+      "eval_loss": 0.021467845886945724,
+      "eval_runtime": 693.0444,
+      "eval_samples_per_second": 40.863,
+      "eval_steps_per_second": 5.108,
+      "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": 3.922555365962547e+16,
+  "total_flos": 7.842663714573517e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null