Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65ba6ce7165316f6ef88d2f8e00615d941a6eb53397e41d82bd795fad4654b0e
+oid sha256:3da13e12402905cdd7d2912b4793e087541a445d9ce2364aed5c897b3453c1a1
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:729d51e0c77c25e805d281654ade3eead80c739c8cbc2ef2d3e8098fbfbdcfe7
+oid sha256:a650d887f02f9e5e6cb1e40c2af3a90fcdef0c68c9345ca56a070b6a0b00203e
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f12f1a7c319805d3add6688c9a2c96f0c1009753643d99dbb8b0af5a20ed2323
+oid sha256:965318139b972b05eef03e8104bd31158943642d8c2db6ccd2fecddb48d67074
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:025fb5806484a8f554a1af4f7ac7c1d7b70db5003d6b053ac701cb5a7dde56d5
+oid sha256:365ff96858035f0956281e3e52f018d5870148e119fa1fe72bca18338034760b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd09deb8b81e54c59f3ebc9c3eabf69eab26f0d967c83c98cdf2574f800e13a8
+oid sha256:8b3b463947ac3861007d03afbe81f0d967f921ef4e444c54e96dcad886051028
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9746012fcf6a201e69a105d7493cc6d2b14fdbd5224f779dfeec6c693b93aeb
+oid sha256:0de37e1a93c9e433bccd6365582ba6ef514d9eee07e93821b8779bf068a948d8
 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": 1.9989453554153442,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.5383580080753702,
+  "best_metric": 1.9585036039352417,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.0767160161507403,
   "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": 21.679,
       "eval_steps_per_second": 5.636,
       "step": 25
+    },
+    {
+      "epoch": 0.5598923283983849,
+      "grad_norm": 4.498115539550781,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 65.8819,
+      "step": 26
+    },
+    {
+      "epoch": 0.5814266487213997,
+      "grad_norm": 4.602976322174072,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 65.7282,
+      "step": 27
+    },
+    {
+      "epoch": 0.6029609690444145,
+      "grad_norm": 5.164878845214844,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 64.1922,
+      "step": 28
+    },
+    {
+      "epoch": 0.6244952893674294,
+      "grad_norm": 5.493595600128174,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 63.0684,
+      "step": 29
+    },
+    {
+      "epoch": 0.6460296096904441,
+      "grad_norm": 5.563244342803955,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 62.7678,
+      "step": 30
+    },
+    {
+      "epoch": 0.6675639300134589,
+      "grad_norm": 4.930936813354492,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 61.9361,
+      "step": 31
+    },
+    {
+      "epoch": 0.6890982503364738,
+      "grad_norm": 4.097081661224365,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 58.2433,
+      "step": 32
+    },
+    {
+      "epoch": 0.7106325706594886,
+      "grad_norm": 3.6659867763519287,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 59.146,
+      "step": 33
+    },
+    {
+      "epoch": 0.7321668909825033,
+      "grad_norm": 3.9649877548217773,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 55.3594,
+      "step": 34
+    },
+    {
+      "epoch": 0.7537012113055181,
+      "grad_norm": 5.052422523498535,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 58.547,
+      "step": 35
+    },
+    {
+      "epoch": 0.775235531628533,
+      "grad_norm": 7.707125186920166,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 65.0094,
+      "step": 36
+    },
+    {
+      "epoch": 0.7967698519515478,
+      "grad_norm": 6.823256015777588,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 64.2297,
+      "step": 37
+    },
+    {
+      "epoch": 0.8183041722745625,
+      "grad_norm": 5.60520076751709,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 63.7831,
+      "step": 38
+    },
+    {
+      "epoch": 0.8398384925975774,
+      "grad_norm": 4.831979751586914,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 63.5944,
+      "step": 39
+    },
+    {
+      "epoch": 0.8613728129205922,
+      "grad_norm": 4.534188747406006,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 64.0645,
+      "step": 40
+    },
+    {
+      "epoch": 0.882907133243607,
+      "grad_norm": 5.040567398071289,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 64.2196,
+      "step": 41
+    },
+    {
+      "epoch": 0.9044414535666218,
+      "grad_norm": 3.988529920578003,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 61.5929,
+      "step": 42
+    },
+    {
+      "epoch": 0.9259757738896366,
+      "grad_norm": 3.7538902759552,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 58.979,
+      "step": 43
+    },
+    {
+      "epoch": 0.9475100942126514,
+      "grad_norm": 4.008431911468506,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 59.3505,
+      "step": 44
+    },
+    {
+      "epoch": 0.9690444145356663,
+      "grad_norm": 4.040865898132324,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 56.4883,
+      "step": 45
+    },
+    {
+      "epoch": 0.990578734858681,
+      "grad_norm": 4.638698101043701,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 55.8449,
+      "step": 46
+    },
+    {
+      "epoch": 1.012113055181696,
+      "grad_norm": 5.850164413452148,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 63.1024,
+      "step": 47
+    },
+    {
+      "epoch": 1.0336473755047106,
+      "grad_norm": 6.791426658630371,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 64.9107,
+      "step": 48
+    },
+    {
+      "epoch": 1.0551816958277254,
+      "grad_norm": 5.96373987197876,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 65.2047,
+      "step": 49
+    },
+    {
+      "epoch": 1.0767160161507403,
+      "grad_norm": 5.147349834442139,
+      "learning_rate": 1e-05,
+      "loss": 62.8758,
+      "step": 50
+    },
+    {
+      "epoch": 1.0767160161507403,
+      "eval_loss": 1.9585036039352417,
+      "eval_runtime": 2.3042,
+      "eval_samples_per_second": 21.699,
+      "eval_steps_per_second": 5.642,
+      "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": 2.6345086191140864e+17,
+  "total_flos": 5.2665520021621965e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null