Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e8c2338ea4c5369458a58c3d12d451730a181c60a4f649fa295a4907a369e9d
+oid sha256:0fba1cf3b4d7509e9ccdfb410bbda3177b9603a663638221c8c4c825dab9c703
 size 550593184

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d04032754301748f970c8da73b62b69f1809baf0066f9df7f2fb82ce1efb948c
+oid sha256:2ae011e10c733905433d32c6998dd25d3cabf2cd3c9bba1f33a5432daf414b43
 size 1101572914

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34e736e85aaa91ecdc4bc7aabf1b26e69e6e6d4312aae2735dc8b591079e9593
+oid sha256:a8ec73e67ed2904091f75d9115484712944e4ad70e3fb6b23e08066d89f0fe0e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5039a16d3dfa624b574e5cc95ceeff29006716a406ce4f2bb8bffd1d46942d89
+oid sha256:3075baf367785aa4f5dc476afa1875f465d47efdcd857286322389c0b270dd57
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dff478104748396e325f5fa31cca8ad05f9019443711a5487b428b109df0a25c
+oid sha256:e0fb5b64e7562c749de6842825f8c5a4950104faf6f09ad3e833049b6eeba635
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d5b23d4cf37c0442791a2394970a2476f06e81d320c57052b1671e76e99dde4
+oid sha256:6de80a0161cfb6a00a637905dcaa3cfe3452bdf79dfd2b05850bcd90a880e05e
 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": 0.17070253193378448,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.2151694459386767,
+  "best_metric": 0.1474180370569229,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.4303388918773534,
   "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": 18.765,
       "eval_steps_per_second": 2.349,
       "step": 25
+    },
+    {
+      "epoch": 0.22377622377622378,
+      "grad_norm": 1.3157997131347656,
+      "learning_rate": 5e-05,
+      "loss": 0.1844,
+      "step": 26
+    },
+    {
+      "epoch": 0.23238300161377085,
+      "grad_norm": 1.5786244869232178,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.1856,
+      "step": 27
+    },
+    {
+      "epoch": 0.24098977945131791,
+      "grad_norm": 1.4797031879425049,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.1923,
+      "step": 28
+    },
+    {
+      "epoch": 0.24959655728886498,
+      "grad_norm": 1.3135018348693848,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.1545,
+      "step": 29
+    },
+    {
+      "epoch": 0.258203335126412,
+      "grad_norm": 0.7757309079170227,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.1495,
+      "step": 30
+    },
+    {
+      "epoch": 0.2668101129639591,
+      "grad_norm": 0.3259675204753876,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.1615,
+      "step": 31
+    },
+    {
+      "epoch": 0.27541689080150616,
+      "grad_norm": 0.931290328502655,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.1578,
+      "step": 32
+    },
+    {
+      "epoch": 0.28402366863905326,
+      "grad_norm": 0.6277098059654236,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.169,
+      "step": 33
+    },
+    {
+      "epoch": 0.2926304464766003,
+      "grad_norm": 0.8366173505783081,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.1595,
+      "step": 34
+    },
+    {
+      "epoch": 0.3012372243141474,
+      "grad_norm": 0.5190151929855347,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.1427,
+      "step": 35
+    },
+    {
+      "epoch": 0.30984400215169444,
+      "grad_norm": 0.6579331755638123,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.1588,
+      "step": 36
+    },
+    {
+      "epoch": 0.31845077998924154,
+      "grad_norm": 0.419669508934021,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.1486,
+      "step": 37
+    },
+    {
+      "epoch": 0.3270575578267886,
+      "grad_norm": 1.265913486480713,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.2152,
+      "step": 38
+    },
+    {
+      "epoch": 0.3356643356643357,
+      "grad_norm": 0.9634343385696411,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.16,
+      "step": 39
+    },
+    {
+      "epoch": 0.3442711135018827,
+      "grad_norm": 1.310472011566162,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.1567,
+      "step": 40
+    },
+    {
+      "epoch": 0.3528778913394298,
+      "grad_norm": 1.4859728813171387,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.1651,
+      "step": 41
+    },
+    {
+      "epoch": 0.36148466917697686,
+      "grad_norm": 0.327387273311615,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.1324,
+      "step": 42
+    },
+    {
+      "epoch": 0.37009144701452396,
+      "grad_norm": 0.47807979583740234,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.1191,
+      "step": 43
+    },
+    {
+      "epoch": 0.378698224852071,
+      "grad_norm": 0.46331387758255005,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.1532,
+      "step": 44
+    },
+    {
+      "epoch": 0.3873050026896181,
+      "grad_norm": 0.4438972473144531,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.1326,
+      "step": 45
+    },
+    {
+      "epoch": 0.39591178052716514,
+      "grad_norm": 0.9701945781707764,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.1572,
+      "step": 46
+    },
+    {
+      "epoch": 0.40451855836471223,
+      "grad_norm": 0.7769740223884583,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.155,
+      "step": 47
+    },
+    {
+      "epoch": 0.4131253362022593,
+      "grad_norm": 0.9505748152732849,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.1522,
+      "step": 48
+    },
+    {
+      "epoch": 0.42173211403980637,
+      "grad_norm": 2.1793980598449707,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.1555,
+      "step": 49
+    },
+    {
+      "epoch": 0.4303388918773534,
+      "grad_norm": 2.068118095397949,
+      "learning_rate": 0.0,
+      "loss": 0.1583,
+      "step": 50
+    },
+    {
+      "epoch": 0.4303388918773534,
+      "eval_loss": 0.1474180370569229,
+      "eval_runtime": 41.7113,
+      "eval_samples_per_second": 18.772,
+      "eval_steps_per_second": 2.349,
+      "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": 5.555785010511872e+17,
+  "total_flos": 1.1111570021023744e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null