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:d80e35c3c4c5f614dabd6b22bd083743d8b8c6351e5d569735aef0574ee08b7d
+oid sha256:d44f1e79747fbded2d95b97020b91060ef16754113142b9cf0f6df0ea8ded6cf
 size 166182480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ff751c2565b87639418020372cc29473e1a3e6e54e47498911bce6c7cb0bb72
+oid sha256:9a6d7d8d4a8cf8ea7bed1f96dad158ae10e58e4f14e1300e2bbab594ef9312ac
 size 332574358

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86fe9fb8091f703d308c836dd6b19b6c6b2ac830395245c6cd7a88308c911f85
+oid sha256:8053be342754e8eb4182688af1587986b84eaa57eedc8b8e19f4431f217febd0
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faac1eef4b3a4873ab366fa720d15397ab685b96d9d88a66a96b25a9e89b430c
+oid sha256:0d7ae916f94808f77165cc48f9cf96a91a98efb3aa1e4fee4c425886427ae26b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:797be33b8e43cd615514df9fb734d4d20d5b946c8c92db137379d5d94c0da016
+oid sha256:79e7718edcbe6e0ae2a564a1867af334b630310338fe5ae0e8a31f82184bb58e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:054678afacfc60051c8380d0be448c3cbccc140ed10b512841ddf1b10e15c098
+oid sha256:3ee3511b7ad6892c794e4d90bff5605b777afbc099467182cb9700af883a7bd6
 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": 2.1801815032958984,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.3194888178913738,
+  "best_metric": 1.9690523147583008,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6389776357827476,
   "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": 49.716,
       "eval_steps_per_second": 6.226,
       "step": 25
+    },
+    {
+      "epoch": 0.33226837060702874,
+      "grad_norm": 3.1555850505828857,
+      "learning_rate": 5e-05,
+      "loss": 2.7737,
+      "step": 26
+    },
+    {
+      "epoch": 0.3450479233226837,
+      "grad_norm": 3.189253330230713,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 2.6303,
+      "step": 27
+    },
+    {
+      "epoch": 0.35782747603833864,
+      "grad_norm": 2.7232983112335205,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.3977,
+      "step": 28
+    },
+    {
+      "epoch": 0.3706070287539936,
+      "grad_norm": 2.5928525924682617,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 2.4877,
+      "step": 29
+    },
+    {
+      "epoch": 0.38338658146964855,
+      "grad_norm": 2.2546591758728027,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 2.4363,
+      "step": 30
+    },
+    {
+      "epoch": 0.3961661341853035,
+      "grad_norm": 2.2360236644744873,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 2.2867,
+      "step": 31
+    },
+    {
+      "epoch": 0.40894568690095845,
+      "grad_norm": 2.709982395172119,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.265,
+      "step": 32
+    },
+    {
+      "epoch": 0.4217252396166134,
+      "grad_norm": 2.5096139907836914,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 2.1913,
+      "step": 33
+    },
+    {
+      "epoch": 0.43450479233226835,
+      "grad_norm": 2.7589054107666016,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.1013,
+      "step": 34
+    },
+    {
+      "epoch": 0.4472843450479233,
+      "grad_norm": 2.6283981800079346,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.8382,
+      "step": 35
+    },
+    {
+      "epoch": 0.46006389776357826,
+      "grad_norm": 2.599478244781494,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.476,
+      "step": 36
+    },
+    {
+      "epoch": 0.4728434504792332,
+      "grad_norm": 3.168750524520874,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.1022,
+      "step": 37
+    },
+    {
+      "epoch": 0.48562300319488816,
+      "grad_norm": 2.388570785522461,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.2588,
+      "step": 38
+    },
+    {
+      "epoch": 0.4984025559105431,
+      "grad_norm": 1.9153763055801392,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.3374,
+      "step": 39
+    },
+    {
+      "epoch": 0.5111821086261981,
+      "grad_norm": 2.0474133491516113,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.3056,
+      "step": 40
+    },
+    {
+      "epoch": 0.5239616613418531,
+      "grad_norm": 2.0961573123931885,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 2.4279,
+      "step": 41
+    },
+    {
+      "epoch": 0.536741214057508,
+      "grad_norm": 1.869411826133728,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.2039,
+      "step": 42
+    },
+    {
+      "epoch": 0.549520766773163,
+      "grad_norm": 2.0868279933929443,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.3414,
+      "step": 43
+    },
+    {
+      "epoch": 0.5623003194888179,
+      "grad_norm": 2.301476240158081,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.4253,
+      "step": 44
+    },
+    {
+      "epoch": 0.5750798722044729,
+      "grad_norm": 2.090371608734131,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 2.1862,
+      "step": 45
+    },
+    {
+      "epoch": 0.5878594249201278,
+      "grad_norm": 2.2954154014587402,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 2.0252,
+      "step": 46
+    },
+    {
+      "epoch": 0.6006389776357828,
+      "grad_norm": 2.319589138031006,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.8494,
+      "step": 47
+    },
+    {
+      "epoch": 0.6134185303514377,
+      "grad_norm": 2.208622932434082,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.5522,
+      "step": 48
+    },
+    {
+      "epoch": 0.6261980830670927,
+      "grad_norm": 2.477149248123169,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.5403,
+      "step": 49
+    },
+    {
+      "epoch": 0.6389776357827476,
+      "grad_norm": 2.278909206390381,
+      "learning_rate": 0.0,
+      "loss": 0.4689,
+      "step": 50
+    },
+    {
+      "epoch": 0.6389776357827476,
+      "eval_loss": 1.9690523147583008,
+      "eval_runtime": 10.6008,
+      "eval_samples_per_second": 49.713,
+      "eval_steps_per_second": 6.226,
+      "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