Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f8f3bfb7bf8d42f44d27e05288ca4ef16bf2414bcbe271240f88b2092ec468c
+oid sha256:870290fa243c302fda98ca3229454c42653828a03c7165b91710fead6ff6a0c4
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53d5ef4470f8ad4ea4c3c5942ed5ffd6e09278a1c35767609acbb7a5d1847e6e
+oid sha256:db97cd84d29b94db39213e58266ca6688ce84e9fc19e410f53b108fb519c6594
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d3c52812d23515cce55193eda792ef3eebbe32549afed6e430ac992062c5c47
+oid sha256:f7e1ba411076ce3ce91c1812c93fb358b8d655db0f798425ee980c59a68b0b10
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85a04279899b765601c8ff61a570389b4efd1b29731830b00e3ca38b27729e9c
+oid sha256:cbb3cd00575c66f1a693ada0f4b1701423937fb8bf84de8366781ecca7448d0c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40851870756d258a37d7ded068136bf9daab0c70443da05d4e66c0764bf94b45
+oid sha256:a93c65d28247a1eb34f09b4883589cd37c2beede17a33453b934f180c04c94d2
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5ef068bde5692330e195b59e05e03ab162d8aad7aad52e6871275d294a29cd9
+oid sha256:81ef16ffbe23fef7665c25de93cd8e782ab0665bf5261a5127536afc30ce831b
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.11834373325109482,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.5763688760806917,
+  "best_metric": 0.10753310471773148,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.1527377521613833,
   "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": 27.939,
       "eval_steps_per_second": 7.264,
       "step": 25
+    },
+    {
+      "epoch": 0.5994236311239193,
+      "grad_norm": 0.6624820232391357,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.1217,
+      "step": 26
+    },
+    {
+      "epoch": 0.622478386167147,
+      "grad_norm": 0.2384788691997528,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.115,
+      "step": 27
+    },
+    {
+      "epoch": 0.6455331412103746,
+      "grad_norm": 0.3248678743839264,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.1141,
+      "step": 28
+    },
+    {
+      "epoch": 0.6685878962536023,
+      "grad_norm": 0.5772506594657898,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.1194,
+      "step": 29
+    },
+    {
+      "epoch": 0.69164265129683,
+      "grad_norm": 0.42324402928352356,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.112,
+      "step": 30
+    },
+    {
+      "epoch": 0.7146974063400576,
+      "grad_norm": 0.17195899784564972,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.1031,
+      "step": 31
+    },
+    {
+      "epoch": 0.7377521613832853,
+      "grad_norm": 0.25521713495254517,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.1012,
+      "step": 32
+    },
+    {
+      "epoch": 0.760806916426513,
+      "grad_norm": 0.5595422983169556,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.1242,
+      "step": 33
+    },
+    {
+      "epoch": 0.7838616714697406,
+      "grad_norm": 0.7196804881095886,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.1323,
+      "step": 34
+    },
+    {
+      "epoch": 0.8069164265129684,
+      "grad_norm": 0.39797908067703247,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.1204,
+      "step": 35
+    },
+    {
+      "epoch": 0.829971181556196,
+      "grad_norm": 0.3196485638618469,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.1179,
+      "step": 36
+    },
+    {
+      "epoch": 0.8530259365994236,
+      "grad_norm": 0.12551093101501465,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.1145,
+      "step": 37
+    },
+    {
+      "epoch": 0.8760806916426513,
+      "grad_norm": 0.3175306022167206,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.1141,
+      "step": 38
+    },
+    {
+      "epoch": 0.899135446685879,
+      "grad_norm": 0.2804529070854187,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.1132,
+      "step": 39
+    },
+    {
+      "epoch": 0.9221902017291066,
+      "grad_norm": 0.32564985752105713,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.1073,
+      "step": 40
+    },
+    {
+      "epoch": 0.9452449567723343,
+      "grad_norm": 0.23975223302841187,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.1059,
+      "step": 41
+    },
+    {
+      "epoch": 0.968299711815562,
+      "grad_norm": 0.29123538732528687,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.1047,
+      "step": 42
+    },
+    {
+      "epoch": 0.9913544668587896,
+      "grad_norm": 0.239503875374794,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0909,
+      "step": 43
+    },
+    {
+      "epoch": 1.0144092219020173,
+      "grad_norm": 0.10593405365943909,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.1865,
+      "step": 44
+    },
+    {
+      "epoch": 1.037463976945245,
+      "grad_norm": 0.21131445467472076,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.1164,
+      "step": 45
+    },
+    {
+      "epoch": 1.0605187319884726,
+      "grad_norm": 0.21675923466682434,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.1111,
+      "step": 46
+    },
+    {
+      "epoch": 1.0835734870317002,
+      "grad_norm": 0.18550635874271393,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.1154,
+      "step": 47
+    },
+    {
+      "epoch": 1.106628242074928,
+      "grad_norm": 0.1325715333223343,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.1117,
+      "step": 48
+    },
+    {
+      "epoch": 1.1296829971181557,
+      "grad_norm": 0.21587017178535461,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.1103,
+      "step": 49
+    },
+    {
+      "epoch": 1.1527377521613833,
+      "grad_norm": 0.08946828544139862,
+      "learning_rate": 1e-05,
+      "loss": 0.1079,
+      "step": 50
+    },
+    {
+      "epoch": 1.1527377521613833,
+      "eval_loss": 0.10753310471773148,
+      "eval_runtime": 1.7908,
+      "eval_samples_per_second": 27.92,
+      "eval_steps_per_second": 7.259,
+      "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": 1,
   "trial_name": null,
   "trial_params": null