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:f7a94f19e3895601db6708367a3699f3a5bf72e8c2bc3e1c7673567fbe2916a7
+oid sha256:8a9d70273e6e39b552e898d1d8e2d16080f17f52a6b5e36ba635e698b03f442e
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c513947e56de83043824fa56200eb2a5ca6f9918a5f93ff3318eeb7c40555bf0
+oid sha256:8dfd0e603949c8eaf67f16e002c9fbc13f26192fe1fc2c250b7da1db9ccef0a4
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aec8c10ce7d407c6ffa5364a396175cb13a894363c3c64fb4e7ee55f2882a53e
+oid sha256:59588d2a2405fdc7ccc0f2f148a0c8e1466849ca3fc089ef0a578685aa92dbdd
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:988cf927165dd6b0b442898f5b0197ba9a0ce9720f2fb0538d720f1058581048
+oid sha256:b00651fee8cca76592d07e6f3132ca76584a7d6aa7bb6bce03a1a629e4186330
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99dcff0d2c277b7cc16cb9f35ee2ae7b97d176608d9c79b211d97164972d2018
+oid sha256:dedc600e738d551b0e4467af11c97f3cb4a6c3fbf8542a1fb893851a57dceb2e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0750aa478e60b7cb89a49523acec6c47b7c228185c0387be39452d6dd906c92
+oid sha256:20e360ec841f5c9e35d9df231c8c8093e504b70d7cc94d346cc8872a89dc6383
 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": 0.45955586433410645,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.24024024024024024,
+  "best_metric": 0.3007971942424774,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.4804804804804805,
   "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": 48.336,
       "eval_steps_per_second": 6.068,
       "step": 25
+    },
+    {
+      "epoch": 0.24984984984984984,
+      "grad_norm": 5.062581539154053,
+      "learning_rate": 5e-05,
+      "loss": 0.4846,
+      "step": 26
+    },
+    {
+      "epoch": 0.2594594594594595,
+      "grad_norm": 5.369364261627197,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.4504,
+      "step": 27
+    },
+    {
+      "epoch": 0.2690690690690691,
+      "grad_norm": 9.659736633300781,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.2836,
+      "step": 28
+    },
+    {
+      "epoch": 0.2786786786786787,
+      "grad_norm": 6.549679756164551,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.4753,
+      "step": 29
+    },
+    {
+      "epoch": 0.2882882882882883,
+      "grad_norm": 6.411563873291016,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.4494,
+      "step": 30
+    },
+    {
+      "epoch": 0.2978978978978979,
+      "grad_norm": 5.894447326660156,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.38,
+      "step": 31
+    },
+    {
+      "epoch": 0.3075075075075075,
+      "grad_norm": 3.534438133239746,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.4184,
+      "step": 32
+    },
+    {
+      "epoch": 0.3171171171171171,
+      "grad_norm": 2.5293240547180176,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.4075,
+      "step": 33
+    },
+    {
+      "epoch": 0.3267267267267267,
+      "grad_norm": 1.8533108234405518,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.3149,
+      "step": 34
+    },
+    {
+      "epoch": 0.33633633633633636,
+      "grad_norm": 2.5232226848602295,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.4054,
+      "step": 35
+    },
+    {
+      "epoch": 0.34594594594594597,
+      "grad_norm": 1.6775366067886353,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.393,
+      "step": 36
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 2.5080814361572266,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.3019,
+      "step": 37
+    },
+    {
+      "epoch": 0.3651651651651652,
+      "grad_norm": 2.5424108505249023,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.3511,
+      "step": 38
+    },
+    {
+      "epoch": 0.3747747747747748,
+      "grad_norm": 2.8998568058013916,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.3987,
+      "step": 39
+    },
+    {
+      "epoch": 0.3843843843843844,
+      "grad_norm": 5.538645267486572,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.2767,
+      "step": 40
+    },
+    {
+      "epoch": 0.393993993993994,
+      "grad_norm": 4.446637153625488,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.2942,
+      "step": 41
+    },
+    {
+      "epoch": 0.4036036036036036,
+      "grad_norm": 2.0864498615264893,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.3179,
+      "step": 42
+    },
+    {
+      "epoch": 0.4132132132132132,
+      "grad_norm": 2.080223321914673,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.2306,
+      "step": 43
+    },
+    {
+      "epoch": 0.4228228228228228,
+      "grad_norm": 2.7075343132019043,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.2878,
+      "step": 44
+    },
+    {
+      "epoch": 0.43243243243243246,
+      "grad_norm": 2.4655637741088867,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.3793,
+      "step": 45
+    },
+    {
+      "epoch": 0.44204204204204206,
+      "grad_norm": 1.119294285774231,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.2866,
+      "step": 46
+    },
+    {
+      "epoch": 0.45165165165165166,
+      "grad_norm": 1.4257920980453491,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.3256,
+      "step": 47
+    },
+    {
+      "epoch": 0.46126126126126127,
+      "grad_norm": 1.6645019054412842,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.2609,
+      "step": 48
+    },
+    {
+      "epoch": 0.4708708708708709,
+      "grad_norm": 1.221898078918457,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.3151,
+      "step": 49
+    },
+    {
+      "epoch": 0.4804804804804805,
+      "grad_norm": 1.8430705070495605,
+      "learning_rate": 0.0,
+      "loss": 0.3629,
+      "step": 50
+    },
+    {
+      "epoch": 0.4804804804804805,
+      "eval_loss": 0.3007971942424774,
+      "eval_runtime": 14.4599,
+      "eval_samples_per_second": 48.479,
+      "eval_steps_per_second": 6.086,
+      "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": 4.16708196040704e+16,
+  "total_flos": 8.33416392081408e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null