Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:026d612a134481064f9102438ff4ac7e8d45148862b6af4d1a2f725bcef564ba
+oid sha256:f786056644d53d0f5d3d9cdc90dd38ea0013ab6284b97b033a8c20030116e4f5
 size 90207248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfb09bd8f4575003f8721b94e0e4df2fedc30099dcffea0f4a148a9c51991b73
+oid sha256:710acb9ffb0a41db42cbe148f9ac7c0746b9a81f3d9f78319295b42c1dbcced9
 size 180543866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:538c3b6d9967e2f6e66acc7c5c6f276741f2221d0f18611ec3f7edd143178b72
+oid sha256:938dc60aa469cc007283b74957b8c8cacde11db80a3652f1123febf781b09d3d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b3504750dcbd307dd2d34d51aea9715ee3fa6f2358fdd87b1c0dabd46d50201
+oid sha256:f2d077532750dad4e6bf0ff88ab6963db2ad191b45c393fd8410d7db939cbd36
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da827883fba43b985c0a334171216c8faa586eb642224e61fa78e7f96d080387
+oid sha256:4cb595b83afc2e493757812d2e63bb84d94ee527aab676faf62a19fa0ea4d842
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1c35cb3bcc98f0287cdc57defd16fb436268eb7599951fe12e2dacfd59cf367
+oid sha256:34754f1aeda08e2c59b006eab3b0ba6d27b4bcffbfd75a0ea991496a0393a7c0
 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": 0.6234197616577148,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.4925373134328357,
+  "best_metric": 0.46706730127334595,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.9850746268656714,
   "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": 91.288,
       "eval_steps_per_second": 23.735,
       "step": 25
+    },
+    {
+      "epoch": 1.5522388059701493,
+      "grad_norm": 1.2679883241653442,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.6249,
+      "step": 26
+    },
+    {
+      "epoch": 1.6119402985074627,
+      "grad_norm": 1.1665154695510864,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.6001,
+      "step": 27
+    },
+    {
+      "epoch": 1.671641791044776,
+      "grad_norm": 1.2832471132278442,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.5607,
+      "step": 28
+    },
+    {
+      "epoch": 1.7313432835820897,
+      "grad_norm": 1.2532341480255127,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.605,
+      "step": 29
+    },
+    {
+      "epoch": 1.7910447761194028,
+      "grad_norm": 0.9181452989578247,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.5312,
+      "step": 30
+    },
+    {
+      "epoch": 1.8507462686567164,
+      "grad_norm": 1.0095727443695068,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.5491,
+      "step": 31
+    },
+    {
+      "epoch": 1.9104477611940298,
+      "grad_norm": 1.0146640539169312,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.4843,
+      "step": 32
+    },
+    {
+      "epoch": 1.9701492537313432,
+      "grad_norm": 1.0201386213302612,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.5598,
+      "step": 33
+    },
+    {
+      "epoch": 2.029850746268657,
+      "grad_norm": 1.2566463947296143,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.5806,
+      "step": 34
+    },
+    {
+      "epoch": 2.08955223880597,
+      "grad_norm": 1.1451953649520874,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.5185,
+      "step": 35
+    },
+    {
+      "epoch": 2.1492537313432836,
+      "grad_norm": 1.1555943489074707,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.4616,
+      "step": 36
+    },
+    {
+      "epoch": 2.208955223880597,
+      "grad_norm": 1.0790717601776123,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.4342,
+      "step": 37
+    },
+    {
+      "epoch": 2.2686567164179103,
+      "grad_norm": 0.8986020088195801,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.4887,
+      "step": 38
+    },
+    {
+      "epoch": 2.328358208955224,
+      "grad_norm": 0.936444878578186,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.4496,
+      "step": 39
+    },
+    {
+      "epoch": 2.388059701492537,
+      "grad_norm": 0.9543986916542053,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.4424,
+      "step": 40
+    },
+    {
+      "epoch": 2.4477611940298507,
+      "grad_norm": 1.245566725730896,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.4677,
+      "step": 41
+    },
+    {
+      "epoch": 2.5074626865671643,
+      "grad_norm": 0.9546048641204834,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.4777,
+      "step": 42
+    },
+    {
+      "epoch": 2.5671641791044775,
+      "grad_norm": 0.859067440032959,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.4685,
+      "step": 43
+    },
+    {
+      "epoch": 2.626865671641791,
+      "grad_norm": 0.9560415148735046,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.4458,
+      "step": 44
+    },
+    {
+      "epoch": 2.6865671641791042,
+      "grad_norm": 1.2271660566329956,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.4315,
+      "step": 45
+    },
+    {
+      "epoch": 2.746268656716418,
+      "grad_norm": 1.0750199556350708,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.4651,
+      "step": 46
+    },
+    {
+      "epoch": 2.8059701492537314,
+      "grad_norm": 1.072292685508728,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.4574,
+      "step": 47
+    },
+    {
+      "epoch": 2.8656716417910446,
+      "grad_norm": 0.9041290283203125,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.4365,
+      "step": 48
+    },
+    {
+      "epoch": 2.925373134328358,
+      "grad_norm": 0.9276415109634399,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.4438,
+      "step": 49
+    },
+    {
+      "epoch": 2.9850746268656714,
+      "grad_norm": 0.9930983781814575,
+      "learning_rate": 1e-05,
+      "loss": 0.5146,
+      "step": 50
+    },
+    {
+      "epoch": 2.9850746268656714,
+      "eval_loss": 0.46706730127334595,
+      "eval_runtime": 0.5399,
+      "eval_samples_per_second": 92.605,
+      "eval_steps_per_second": 24.077,
+      "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": 3.91521434075136e+16,
+  "total_flos": 7.83042868150272e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null