Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:839df87b1aa13caa5878e173b90322c701ed4b686ff7aa24f4e587bb4fa0f5fa
+oid sha256:0750a99e12289b2987679bd74ad4bbdf0f51fd926d8bf9d3848e1ef8673b17bd
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b575c07a036e5a5a4e5e7961990e308b33130a6218ef9c5984c5585f36b6ac56
+oid sha256:1354b0166bde04a476b221f20977db7c6f8889e7e434adb2d81bfe906290e4eb
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f192c4d368ee721fb7b08b182dace35a68387c5e6f9e6c350dd657d46bc62e1b
+oid sha256:867e605f8682b871874b769f67903fc2c5bd7506bd23d339bf4baa25c86470de
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f2956869d53e44a011adfb36ff6a3957eb1bbb1bdbff2508cc9f705921dae91
+oid sha256:c5648cfa1ac4afd9e6f7e8a58d05fe65432b800da8ce1b90cee1755da5ac4d91
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:094adbc5bf01ee448d2e0724e937dcf557226a2a76da25530fc0e8a48e413010
+oid sha256:685f0a2443a8683bc7902393ee3ee7cff947774783b34aa2c4d1f9a3fbd509fc
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:508ad8f629063b9a9129ce962e2e855d73a2b3f006af0ed8c7680bbd7d68451a
+oid sha256:545067fe0b1928c4f20438777b00ffa594b740effe38662931c368ddcf9bcad3
 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": 0.06095504388213158,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.007052186177715092,
+  "best_metric": 0.03815676271915436,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.014104372355430184,
   "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": 37.505,
       "eval_steps_per_second": 4.689,
       "step": 25
+    },
+    {
+      "epoch": 0.007334273624823695,
+      "grad_norm": 1.1075620651245117,
+      "learning_rate": 5e-05,
+      "loss": 0.0845,
+      "step": 26
+    },
+    {
+      "epoch": 0.007616361071932299,
+      "grad_norm": 0.8992208242416382,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0661,
+      "step": 27
+    },
+    {
+      "epoch": 0.007898448519040903,
+      "grad_norm": 0.9340633153915405,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0432,
+      "step": 28
+    },
+    {
+      "epoch": 0.008180535966149507,
+      "grad_norm": 1.0387746095657349,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0787,
+      "step": 29
+    },
+    {
+      "epoch": 0.00846262341325811,
+      "grad_norm": 0.9487574100494385,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0525,
+      "step": 30
+    },
+    {
+      "epoch": 0.008744710860366713,
+      "grad_norm": 1.0404561758041382,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.05,
+      "step": 31
+    },
+    {
+      "epoch": 0.009026798307475317,
+      "grad_norm": 0.8051718473434448,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0493,
+      "step": 32
+    },
+    {
+      "epoch": 0.00930888575458392,
+      "grad_norm": 0.47407007217407227,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0185,
+      "step": 33
+    },
+    {
+      "epoch": 0.009590973201692525,
+      "grad_norm": 1.1965396404266357,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0496,
+      "step": 34
+    },
+    {
+      "epoch": 0.009873060648801129,
+      "grad_norm": 0.8554047346115112,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0348,
+      "step": 35
+    },
+    {
+      "epoch": 0.010155148095909733,
+      "grad_norm": 0.5990251302719116,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.022,
+      "step": 36
+    },
+    {
+      "epoch": 0.010437235543018336,
+      "grad_norm": 0.4175862967967987,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0243,
+      "step": 37
+    },
+    {
+      "epoch": 0.010719322990126939,
+      "grad_norm": 0.7823725342750549,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0384,
+      "step": 38
+    },
+    {
+      "epoch": 0.011001410437235543,
+      "grad_norm": 0.5732550024986267,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0436,
+      "step": 39
+    },
+    {
+      "epoch": 0.011283497884344146,
+      "grad_norm": 0.7381021976470947,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0311,
+      "step": 40
+    },
+    {
+      "epoch": 0.01156558533145275,
+      "grad_norm": 0.7738580107688904,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0475,
+      "step": 41
+    },
+    {
+      "epoch": 0.011847672778561354,
+      "grad_norm": 0.739055335521698,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0292,
+      "step": 42
+    },
+    {
+      "epoch": 0.012129760225669958,
+      "grad_norm": 1.1671977043151855,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0565,
+      "step": 43
+    },
+    {
+      "epoch": 0.012411847672778562,
+      "grad_norm": 0.6021670699119568,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0347,
+      "step": 44
+    },
+    {
+      "epoch": 0.012693935119887164,
+      "grad_norm": 0.6920357346534729,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0291,
+      "step": 45
+    },
+    {
+      "epoch": 0.012976022566995768,
+      "grad_norm": 0.42046383023262024,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0132,
+      "step": 46
+    },
+    {
+      "epoch": 0.013258110014104372,
+      "grad_norm": 0.5549576878547668,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.028,
+      "step": 47
+    },
+    {
+      "epoch": 0.013540197461212976,
+      "grad_norm": 0.5346555709838867,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0223,
+      "step": 48
+    },
+    {
+      "epoch": 0.01382228490832158,
+      "grad_norm": 5.4132866859436035,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0755,
+      "step": 49
+    },
+    {
+      "epoch": 0.014104372355430184,
+      "grad_norm": 1.7002118825912476,
+      "learning_rate": 0.0,
+      "loss": 0.0479,
+      "step": 50
+    },
+    {
+      "epoch": 0.014104372355430184,
+      "eval_loss": 0.03815676271915436,
+      "eval_runtime": 637.1574,
+      "eval_samples_per_second": 37.482,
+      "eval_steps_per_second": 4.686,
+      "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": 2.987771858905989e+17,
+  "total_flos": 5.977408742935757e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null