Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:839a32dc6ad93b0b75df1a3d99b5bd82fa4e32227185e478b09954f3143bfd3f
+oid sha256:def1de9e0a24c46efbb4c4501c2583bf24a4425aff2bc4ba5b766c234a9dc0b5
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a6d40f9e5c4074563e63c4afedc1d88d9f5e987f5fc4b77f457862d85c23144
+oid sha256:2e81c9bff4adfe4929470dd3883160bffa5f65321ca20ee75cbbb2cfdd51a799
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e5703bcae5d0bc5f7a6f2506fcf5663128b75c322387e5465b068215eca5e04
+oid sha256:74ec5cc3726df4e998ea92ebae21033c0eb074f8d6ad5d8a9279da744ece2ef6
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:961bb862cb07b188e575646dd5d0dfbbcffff4de16512df839618a37db0b2e01
+oid sha256:9d956491cea33a29fb966c2295082c2fdf2d0877954269d330b92eca3436662f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf45a453fc6449ba138ff24ab2a9c6d75569458f050d3e219411ee7eaf505a2d
+oid sha256:f162be6dcb26a21fc9888901c8d7ebdad85b82f3db4b022f5581f1596b607d2d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32b76ee6a0fecb49ca5cc71efc96aeb52b030fb5d1674924b15b36e89815c802
+oid sha256:f6c61b9709608c657ecc36e81f74e9fcd74ab5f186313e5c0ff7cd29cb24f37f
 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": 11.760405540466309,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.010689756540794784,
+  "best_metric": 11.758439064025879,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.021379513081589568,
   "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": 126.842,
       "eval_steps_per_second": 32.979,
       "step": 25
+    },
+    {
+      "epoch": 0.011117346802426575,
+      "grad_norm": 0.0947161465883255,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 11.7612,
+      "step": 26
+    },
+    {
+      "epoch": 0.011544937064058366,
+      "grad_norm": 0.0553748682141304,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 11.7607,
+      "step": 27
+    },
+    {
+      "epoch": 0.011972527325690157,
+      "grad_norm": 0.05844997987151146,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 11.7609,
+      "step": 28
+    },
+    {
+      "epoch": 0.012400117587321948,
+      "grad_norm": 0.05783386155962944,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 11.7611,
+      "step": 29
+    },
+    {
+      "epoch": 0.01282770784895374,
+      "grad_norm": 0.061772510409355164,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 11.7603,
+      "step": 30
+    },
+    {
+      "epoch": 0.01325529811058553,
+      "grad_norm": 0.06448950618505478,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 11.7604,
+      "step": 31
+    },
+    {
+      "epoch": 0.013682888372217322,
+      "grad_norm": 0.06722883880138397,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 11.7601,
+      "step": 32
+    },
+    {
+      "epoch": 0.014110478633849115,
+      "grad_norm": 0.06685524433851242,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 11.7607,
+      "step": 33
+    },
+    {
+      "epoch": 0.014538068895480906,
+      "grad_norm": 0.06618436425924301,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 11.7594,
+      "step": 34
+    },
+    {
+      "epoch": 0.014965659157112697,
+      "grad_norm": 0.07597427815198898,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 11.7591,
+      "step": 35
+    },
+    {
+      "epoch": 0.015393249418744488,
+      "grad_norm": 0.08120574802160263,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 11.7585,
+      "step": 36
+    },
+    {
+      "epoch": 0.01582083968037628,
+      "grad_norm": 0.07383999228477478,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 11.7593,
+      "step": 37
+    },
+    {
+      "epoch": 0.01624842994200807,
+      "grad_norm": 0.09645941108465195,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 11.7583,
+      "step": 38
+    },
+    {
+      "epoch": 0.01667602020363986,
+      "grad_norm": 0.06341534852981567,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 11.7606,
+      "step": 39
+    },
+    {
+      "epoch": 0.017103610465271653,
+      "grad_norm": 0.06619752943515778,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 11.7593,
+      "step": 40
+    },
+    {
+      "epoch": 0.017531200726903444,
+      "grad_norm": 0.07469940930604935,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 11.7589,
+      "step": 41
+    },
+    {
+      "epoch": 0.017958790988535235,
+      "grad_norm": 0.08176931738853455,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 11.7585,
+      "step": 42
+    },
+    {
+      "epoch": 0.018386381250167026,
+      "grad_norm": 0.07405959814786911,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 11.7593,
+      "step": 43
+    },
+    {
+      "epoch": 0.018813971511798817,
+      "grad_norm": 0.07433359324932098,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 11.7595,
+      "step": 44
+    },
+    {
+      "epoch": 0.01924156177343061,
+      "grad_norm": 0.07951745390892029,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 11.7585,
+      "step": 45
+    },
+    {
+      "epoch": 0.019669152035062403,
+      "grad_norm": 0.07772774249315262,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 11.7587,
+      "step": 46
+    },
+    {
+      "epoch": 0.020096742296694194,
+      "grad_norm": 0.08244699239730835,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 11.7572,
+      "step": 47
+    },
+    {
+      "epoch": 0.020524332558325985,
+      "grad_norm": 0.08685096353292465,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 11.7573,
+      "step": 48
+    },
+    {
+      "epoch": 0.020951922819957777,
+      "grad_norm": 0.08589866757392883,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 11.7589,
+      "step": 49
+    },
+    {
+      "epoch": 0.021379513081589568,
+      "grad_norm": 0.09261184185743332,
+      "learning_rate": 1e-05,
+      "loss": 11.7566,
+      "step": 50
+    },
+    {
+      "epoch": 0.021379513081589568,
+      "eval_loss": 11.758439064025879,
+      "eval_runtime": 0.4257,
+      "eval_samples_per_second": 117.455,
+      "eval_steps_per_second": 30.538,
+      "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": 83172214702080.0,
+  "total_flos": 166344429404160.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null