Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40b8fab9495914d917760270fb2288c092161861d6edb3cbc08cb69e1a680f0c
+oid sha256:d97387a168b8324c3c0e6ce95da6b22f628a934e40f3ca8e9a368f409d1b5d60
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:425ebc9e344c2714a04234827c2601ea2d79a4cf264899f82f36e19b68c9edb2
+oid sha256:65ebbbe8fe2898b62213e8051a8eaff2bbe6a267ef5d97c0ee3c35c726468156
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:392da4140017150b8d398edc4b538ef38dbc8f4689f3a420a82ece6c45d0d233
+oid sha256:6b8efda10a41bc31fd8508829a418350e4727b415e6f5dd36e4cce68583571e9
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1ce34fcad5b45fba6e1054f3d4e0dee54bdb7bff106b71a1f4ae8644f4499fe
+oid sha256:ac7a4ca70b41246f02ac085e49ff807b49d5959225be6547ae1a9fda02899648
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:531500faef14b3dc9453169ab4dd6befeea317705d37df8653d3f1c4a7cf304b
+oid sha256:e15a4bddfdd5a038d128bfa5cc3d21bba0d718941653385c9fac1fdd5d1dd73d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5abd135c16b1a63f4341428e38300a8af25efbb7344f469ce487bbd4336b94d
+oid sha256:3785c1b406f0ca6c1297b356122ec31c2d103f0cc30c2e94503e3639668caf6b
 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": 0.7837062478065491,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.4836759371221282,
+  "best_metric": 0.7657374739646912,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.9673518742442564,
   "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": 30.618,
       "eval_steps_per_second": 3.86,
       "step": 25
+    },
+    {
+      "epoch": 0.5030229746070133,
+      "grad_norm": 0.07031340897083282,
+      "learning_rate": 5e-05,
+      "loss": 0.7878,
+      "step": 26
+    },
+    {
+      "epoch": 0.5223700120918985,
+      "grad_norm": 0.07707154750823975,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.786,
+      "step": 27
+    },
+    {
+      "epoch": 0.5417170495767836,
+      "grad_norm": 0.0745035782456398,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.9134,
+      "step": 28
+    },
+    {
+      "epoch": 0.5610640870616687,
+      "grad_norm": 0.06669345498085022,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.8154,
+      "step": 29
+    },
+    {
+      "epoch": 0.5804111245465539,
+      "grad_norm": 0.0690491795539856,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.8274,
+      "step": 30
+    },
+    {
+      "epoch": 0.599758162031439,
+      "grad_norm": 0.07264308631420135,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.8744,
+      "step": 31
+    },
+    {
+      "epoch": 0.619105199516324,
+      "grad_norm": 0.07223401218652725,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.9257,
+      "step": 32
+    },
+    {
+      "epoch": 0.6384522370012092,
+      "grad_norm": 0.0706273689866066,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.9225,
+      "step": 33
+    },
+    {
+      "epoch": 0.6577992744860943,
+      "grad_norm": 0.07520892471075058,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.9234,
+      "step": 34
+    },
+    {
+      "epoch": 0.6771463119709794,
+      "grad_norm": 0.08015627413988113,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.8068,
+      "step": 35
+    },
+    {
+      "epoch": 0.6964933494558646,
+      "grad_norm": 0.09883278608322144,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.6502,
+      "step": 36
+    },
+    {
+      "epoch": 0.7158403869407497,
+      "grad_norm": 0.1318332403898239,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.4271,
+      "step": 37
+    },
+    {
+      "epoch": 0.7351874244256348,
+      "grad_norm": 0.08774442225694656,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.7714,
+      "step": 38
+    },
+    {
+      "epoch": 0.75453446191052,
+      "grad_norm": 0.06477252393960953,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.8214,
+      "step": 39
+    },
+    {
+      "epoch": 0.7738814993954051,
+      "grad_norm": 0.0652678981423378,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.8322,
+      "step": 40
+    },
+    {
+      "epoch": 0.7932285368802902,
+      "grad_norm": 0.06607598066329956,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.8466,
+      "step": 41
+    },
+    {
+      "epoch": 0.8125755743651754,
+      "grad_norm": 0.06954794377088547,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.882,
+      "step": 42
+    },
+    {
+      "epoch": 0.8319226118500604,
+      "grad_norm": 0.07791940122842789,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.9292,
+      "step": 43
+    },
+    {
+      "epoch": 0.8512696493349455,
+      "grad_norm": 0.07262781262397766,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.8562,
+      "step": 44
+    },
+    {
+      "epoch": 0.8706166868198307,
+      "grad_norm": 0.070536307990551,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.8477,
+      "step": 45
+    },
+    {
+      "epoch": 0.8899637243047158,
+      "grad_norm": 0.0720757469534874,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.896,
+      "step": 46
+    },
+    {
+      "epoch": 0.909310761789601,
+      "grad_norm": 0.07141188532114029,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.7931,
+      "step": 47
+    },
+    {
+      "epoch": 0.9286577992744861,
+      "grad_norm": 0.08638662099838257,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.7604,
+      "step": 48
+    },
+    {
+      "epoch": 0.9480048367593712,
+      "grad_norm": 0.10718564689159393,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.5603,
+      "step": 49
+    },
+    {
+      "epoch": 0.9673518742442564,
+      "grad_norm": 0.21608486771583557,
+      "learning_rate": 0.0,
+      "loss": 0.2008,
+      "step": 50
+    },
+    {
+      "epoch": 0.9673518742442564,
+      "eval_loss": 0.7657374739646912,
+      "eval_runtime": 11.6416,
+      "eval_samples_per_second": 29.979,
+      "eval_steps_per_second": 3.78,
+      "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": 3.005355905987379e+17,
+  "total_flos": 5.991379090433638e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null