Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9944a0b8a0b1130e18eca8db9a6156af02c275fbe4fd3b4210ced47e3549c367
+oid sha256:a7e51ef2b2e6e9c14425e2a5aaafbe52ff5ccaf7cbc140fd1255cd22202c38e3
 size 166182480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:166cd56307489801950e55c50c6a09bc8bc381c3d0d45d95df87992134a5eada
+oid sha256:5521d118516d15d92b5331b8c094c36338be9f3f351427ecd763c405102397fa
 size 332574358

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca8046234ce587d856764d33e0f9603a6de81b2df53ed9950c7b41b2ec75e67f
+oid sha256:a54ac5ed93bb72f1c7eda627c952ba274b5aad32063a2ae24cbe6bdfe109b31e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5379be9fc3b30a76b2877c6bd7518aa51b907c1ead88adb596b6926e6b7a8e63
+oid sha256:ed08dc428308226a753b62a09e542aabc715e40a8cc828921bb7773227c9c717
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b58b99ce07e1218eb310215ec17eed81aeb3c18e9c779a3f7e51355d4387cf5
+oid sha256:196c9b64aa70610f538355a21814a074521ae9dea0c8533e280876b20f705e21
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd59b2b3374e1ed9f3e29ffaa2194670332d405ccafd530faa3e43768ca3ebc7
+oid sha256:5780e7d661d5a9e3373a06692833cbc024b8dda875344df2663839539f481c46
 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": 0.5987976789474487,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.13788348845225784,
+  "best_metric": 0.2970764636993408,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.2757669769045157,
   "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": 24.167,
       "eval_steps_per_second": 6.283,
       "step": 25
+    },
+    {
+      "epoch": 0.14339882799034814,
+      "grad_norm": 14.616813659667969,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.3624,
+      "step": 26
+    },
+    {
+      "epoch": 0.14891416752843847,
+      "grad_norm": 14.416601181030273,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.4517,
+      "step": 27
+    },
+    {
+      "epoch": 0.15442950706652878,
+      "grad_norm": 14.185774803161621,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.4198,
+      "step": 28
+    },
+    {
+      "epoch": 0.1599448466046191,
+      "grad_norm": 14.199448585510254,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.2981,
+      "step": 29
+    },
+    {
+      "epoch": 0.1654601861427094,
+      "grad_norm": 14.281562805175781,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.1186,
+      "step": 30
+    },
+    {
+      "epoch": 0.1709755256807997,
+      "grad_norm": 9.70438289642334,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.6196,
+      "step": 31
+    },
+    {
+      "epoch": 0.17649086521889004,
+      "grad_norm": 1.0650125741958618,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0159,
+      "step": 32
+    },
+    {
+      "epoch": 0.18200620475698034,
+      "grad_norm": 2.1456191539764404,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.0318,
+      "step": 33
+    },
+    {
+      "epoch": 0.18752154429507067,
+      "grad_norm": 2.722893714904785,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0416,
+      "step": 34
+    },
+    {
+      "epoch": 0.19303688383316098,
+      "grad_norm": 2.7244069576263428,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.0413,
+      "step": 35
+    },
+    {
+      "epoch": 0.19855222337125128,
+      "grad_norm": 2.097538948059082,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.0319,
+      "step": 36
+    },
+    {
+      "epoch": 0.2040675629093416,
+      "grad_norm": 1.3665951490402222,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.0206,
+      "step": 37
+    },
+    {
+      "epoch": 0.2095829024474319,
+      "grad_norm": 8.16921329498291,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.4333,
+      "step": 38
+    },
+    {
+      "epoch": 0.21509824198552224,
+      "grad_norm": 13.686884880065918,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.74,
+      "step": 39
+    },
+    {
+      "epoch": 0.22061358152361255,
+      "grad_norm": 13.585527420043945,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.7545,
+      "step": 40
+    },
+    {
+      "epoch": 0.22612892106170285,
+      "grad_norm": 13.636950492858887,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.7381,
+      "step": 41
+    },
+    {
+      "epoch": 0.23164426059979318,
+      "grad_norm": 13.520855903625488,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.6922,
+      "step": 42
+    },
+    {
+      "epoch": 0.23715960013788348,
+      "grad_norm": 12.375536918640137,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.5961,
+      "step": 43
+    },
+    {
+      "epoch": 0.2426749396759738,
+      "grad_norm": 1.4398314952850342,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0221,
+      "step": 44
+    },
+    {
+      "epoch": 0.2481902792140641,
+      "grad_norm": 1.7233232259750366,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0263,
+      "step": 45
+    },
+    {
+      "epoch": 0.2537056187521544,
+      "grad_norm": 1.8829046487808228,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0288,
+      "step": 46
+    },
+    {
+      "epoch": 0.2592209582902447,
+      "grad_norm": 1.798218011856079,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0273,
+      "step": 47
+    },
+    {
+      "epoch": 0.2647362978283351,
+      "grad_norm": 1.6327126026153564,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.025,
+      "step": 48
+    },
+    {
+      "epoch": 0.2702516373664254,
+      "grad_norm": 1.388482689857483,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0213,
+      "step": 49
+    },
+    {
+      "epoch": 0.2757669769045157,
+      "grad_norm": 1.101733922958374,
+      "learning_rate": 1e-05,
+      "loss": 0.0169,
+      "step": 50
+    },
+    {
+      "epoch": 0.2757669769045157,
+      "eval_loss": 0.2970764636993408,
+      "eval_runtime": 2.0581,
+      "eval_samples_per_second": 24.294,
+      "eval_steps_per_second": 6.317,
+      "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": 8.1240447254528e+16,
+  "total_flos": 1.62480894509056e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null