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:fb695dfd0a2e8c8313ecf5818516684ddbabd7afe6f743f995994a4ab561b8d5
+oid sha256:bb5a339f1f335cfb0cc0086f3dcfc48c40a025d432552428962aeaf18a5202ad
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f92ba43c8003752a6c9a05082176b7b844b7a89b52bc355e9252f4dd604190d2
+oid sha256:e2a4c30fc12a44c7036242e3988ef4f83416e462ef4662f88e1de4564e4460c9
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23419b942b7f981df836e919220873f3f5edb282d8b5ad30328c478401278b73
+oid sha256:be21fc80b928053b85a72bee05aef32cc32cbaba4dd867826cdce4423fd92fae
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d251ab78e475692115a188ced24cf2450bf6d21b1d4cce3ac997d5df09a5cee3
+oid sha256:20ba3de26c434e1c5880e38cfe7f0b608cd628cd4b94ca6d9be21c82801f5b70
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:911c3730aaeb015ffcda90e83d4d439769840e360e37ef5865bb8d482cd18878
+oid sha256:5ea0d6596b4cc8ab5dfb922834fef13b4f1f29d2b9cf72be60b5e0e89d8aa11a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:597c0fd6cdc34f3a05dfd7044e718628dbd26c756f74841d34a411696b04b9bd
+oid sha256:7fd486abc7e691f2a9d85d2d53867b445cd722f35412ea2134d75f1c9b935584
 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": 1.3774296045303345,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.061833359097232955,
+  "best_metric": 1.3438785076141357,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.12366671819446591,
   "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": 36.615,
       "eval_steps_per_second": 9.52,
       "step": 25
+    },
+    {
+      "epoch": 0.06430669346112228,
+      "grad_norm": 0.1969248652458191,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.3588,
+      "step": 26
+    },
+    {
+      "epoch": 0.06678002782501159,
+      "grad_norm": 0.24957776069641113,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.3729,
+      "step": 27
+    },
+    {
+      "epoch": 0.06925336218890091,
+      "grad_norm": 0.2782116234302521,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.3884,
+      "step": 28
+    },
+    {
+      "epoch": 0.07172669655279024,
+      "grad_norm": 0.2921300530433655,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.3412,
+      "step": 29
+    },
+    {
+      "epoch": 0.07420003091667955,
+      "grad_norm": 0.30862900614738464,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.3763,
+      "step": 30
+    },
+    {
+      "epoch": 0.07667336528056887,
+      "grad_norm": 0.34051671624183655,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.3367,
+      "step": 31
+    },
+    {
+      "epoch": 0.07914669964445818,
+      "grad_norm": 0.4773139953613281,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.4185,
+      "step": 32
+    },
+    {
+      "epoch": 0.0816200340083475,
+      "grad_norm": 0.5584874749183655,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.4915,
+      "step": 33
+    },
+    {
+      "epoch": 0.08409336837223683,
+      "grad_norm": 0.6597000360488892,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.5256,
+      "step": 34
+    },
+    {
+      "epoch": 0.08656670273612614,
+      "grad_norm": 0.8497105836868286,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.5762,
+      "step": 35
+    },
+    {
+      "epoch": 0.08904003710001546,
+      "grad_norm": 1.0561015605926514,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.5835,
+      "step": 36
+    },
+    {
+      "epoch": 0.09151337146390477,
+      "grad_norm": 1.5521297454833984,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.9923,
+      "step": 37
+    },
+    {
+      "epoch": 0.0939867058277941,
+      "grad_norm": 0.2739869952201843,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.3051,
+      "step": 38
+    },
+    {
+      "epoch": 0.09646004019168342,
+      "grad_norm": 0.24728912115097046,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.3731,
+      "step": 39
+    },
+    {
+      "epoch": 0.09893337455557273,
+      "grad_norm": 0.2915448248386383,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.4264,
+      "step": 40
+    },
+    {
+      "epoch": 0.10140670891946205,
+      "grad_norm": 0.2829023599624634,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.3681,
+      "step": 41
+    },
+    {
+      "epoch": 0.10388004328335136,
+      "grad_norm": 0.2981795072555542,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.4102,
+      "step": 42
+    },
+    {
+      "epoch": 0.10635337764724069,
+      "grad_norm": 0.3205282390117645,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.4092,
+      "step": 43
+    },
+    {
+      "epoch": 0.10882671201113,
+      "grad_norm": 0.37935322523117065,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.4686,
+      "step": 44
+    },
+    {
+      "epoch": 0.11130004637501932,
+      "grad_norm": 0.47622013092041016,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.4391,
+      "step": 45
+    },
+    {
+      "epoch": 0.11377338073890864,
+      "grad_norm": 0.5806944370269775,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.3553,
+      "step": 46
+    },
+    {
+      "epoch": 0.11624671510279797,
+      "grad_norm": 0.7040004730224609,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.5695,
+      "step": 47
+    },
+    {
+      "epoch": 0.11872004946668728,
+      "grad_norm": 0.8034400343894958,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.593,
+      "step": 48
+    },
+    {
+      "epoch": 0.1211933838305766,
+      "grad_norm": 1.028380274772644,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.8959,
+      "step": 49
+    },
+    {
+      "epoch": 0.12366671819446591,
+      "grad_norm": 2.6162054538726807,
+      "learning_rate": 1e-05,
+      "loss": 2.087,
+      "step": 50
+    },
+    {
+      "epoch": 0.12366671819446591,
+      "eval_loss": 1.3438785076141357,
+      "eval_runtime": 1.3345,
+      "eval_samples_per_second": 37.467,
+      "eval_steps_per_second": 9.742,
+      "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": 1,
   "trial_name": null,
   "trial_params": null