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:e1dea0534b20c8867abf72d6c165157d72adbb99f2a7298707ed0b52df757c08
+oid sha256:e94f59f84ea6fb17410e5c2487bb52a832b314b0bd391534799fa496b8615567
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3454b86f11cc184bc1ee2535f1acbdca806cac7382b16a3c8a21008a2a723aa
+oid sha256:922557ee616941df7f366573c0c4b57d7afb1da234d5272fb1fd377ecbae6881
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d848d69c75f58c3a013a8f27a0ffb6259bab620c9565749c73243a6ab8040644
+oid sha256:a7b779bdd0bb29dc56dcfa345d05ec2380c7d61e0b11a48b89d58a4618e89ba0
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b6ff7df595cbcdcfd300eb6eac24565bb1a3c77639a19766e858a75c707948a
+oid sha256:03e89cfefa990441c692d94e6b527e3c3b4c378de302aaa2823b708c845cd052
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55f38f745bbd7948addd863f12ebef9231d64f88f7f2efdf62e8525fbbabee3c
+oid sha256:bb726fb7b545e2686b92f91a3cb86be5b23d7c0280f0288110c7bfe463338a06
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d7e616bf71d4cc3c1df2c06f6e89d0c0b0ecaecc76cee30905891ca065c57d2
+oid sha256:a5a9ce5a8c975065bb609d22b1cbb1ea6aae11ad4fecdf1abb17ef10a81e763f
 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": 5.323215484619141,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.11280315848843768,
+  "best_metric": 5.28487491607666,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.22560631697687536,
   "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": 87.63,
       "eval_steps_per_second": 10.976,
       "step": 25
+    },
+    {
+      "epoch": 0.11731528482797518,
+      "grad_norm": 0.5437615513801575,
+      "learning_rate": 5e-05,
+      "loss": 5.3644,
+      "step": 26
+    },
+    {
+      "epoch": 0.1218274111675127,
+      "grad_norm": 0.6228774785995483,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 5.2771,
+      "step": 27
+    },
+    {
+      "epoch": 0.1263395375070502,
+      "grad_norm": 0.5897179245948792,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 5.3137,
+      "step": 28
+    },
+    {
+      "epoch": 0.1308516638465877,
+      "grad_norm": 0.6028752326965332,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 5.3606,
+      "step": 29
+    },
+    {
+      "epoch": 0.1353637901861252,
+      "grad_norm": 0.5325168967247009,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 5.3051,
+      "step": 30
+    },
+    {
+      "epoch": 0.13987591652566272,
+      "grad_norm": 0.5063620805740356,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 5.2901,
+      "step": 31
+    },
+    {
+      "epoch": 0.14438804286520024,
+      "grad_norm": 0.4882858395576477,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 5.2739,
+      "step": 32
+    },
+    {
+      "epoch": 0.14890016920473773,
+      "grad_norm": 0.4943495988845825,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 5.3036,
+      "step": 33
+    },
+    {
+      "epoch": 0.15341229554427524,
+      "grad_norm": 0.4519631266593933,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 5.318,
+      "step": 34
+    },
+    {
+      "epoch": 0.15792442188381275,
+      "grad_norm": 0.502394437789917,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 5.3522,
+      "step": 35
+    },
+    {
+      "epoch": 0.16243654822335024,
+      "grad_norm": 0.46117448806762695,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 5.3156,
+      "step": 36
+    },
+    {
+      "epoch": 0.16694867456288776,
+      "grad_norm": 0.5970073342323303,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 5.3131,
+      "step": 37
+    },
+    {
+      "epoch": 0.17146080090242527,
+      "grad_norm": 0.5500613451004028,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 5.3299,
+      "step": 38
+    },
+    {
+      "epoch": 0.17597292724196278,
+      "grad_norm": 0.537351667881012,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 5.3052,
+      "step": 39
+    },
+    {
+      "epoch": 0.18048505358150027,
+      "grad_norm": 0.6283145546913147,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 5.2214,
+      "step": 40
+    },
+    {
+      "epoch": 0.18499717992103779,
+      "grad_norm": 0.582278311252594,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 5.3105,
+      "step": 41
+    },
+    {
+      "epoch": 0.1895093062605753,
+      "grad_norm": 0.5104334354400635,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 5.3162,
+      "step": 42
+    },
+    {
+      "epoch": 0.19402143260011281,
+      "grad_norm": 0.4248177409172058,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 5.2871,
+      "step": 43
+    },
+    {
+      "epoch": 0.1985335589396503,
+      "grad_norm": 0.41239920258522034,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 5.2435,
+      "step": 44
+    },
+    {
+      "epoch": 0.20304568527918782,
+      "grad_norm": 0.42970484495162964,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 5.2902,
+      "step": 45
+    },
+    {
+      "epoch": 0.20755781161872533,
+      "grad_norm": 0.3964599668979645,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 5.3027,
+      "step": 46
+    },
+    {
+      "epoch": 0.21206993795826284,
+      "grad_norm": 0.3762015998363495,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 5.307,
+      "step": 47
+    },
+    {
+      "epoch": 0.21658206429780033,
+      "grad_norm": 0.46960142254829407,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 5.307,
+      "step": 48
+    },
+    {
+      "epoch": 0.22109419063733785,
+      "grad_norm": 0.4847152829170227,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 5.3012,
+      "step": 49
+    },
+    {
+      "epoch": 0.22560631697687536,
+      "grad_norm": 0.5823029279708862,
+      "learning_rate": 0.0,
+      "loss": 5.2784,
+      "step": 50
+    },
+    {
+      "epoch": 0.22560631697687536,
+      "eval_loss": 5.28487491607666,
+      "eval_runtime": 17.0383,
+      "eval_samples_per_second": 87.626,
+      "eval_steps_per_second": 10.975,
+      "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": 5.29768176943104e+16,
+  "total_flos": 1.059536353886208e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null