Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b702aadf01d77b214f872694969a61511a282763c5ee08a0cf4fa87c99f4984
+oid sha256:046e87e81420ca9060dfa40963b4422061f72d6eafb0a5d0fc607485197a24bb
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16f611c28b2c5de2be1ddb2dbc2b17f5426f8bb2088d40d8a61dc20f52b27edf
+oid sha256:cba2c52aaf5587cdf5066c234eca05bcaedaf2c09eb58c342e03d33f573b1abf
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4512795d176028cd572d5b13049b124a4d563b0724f76b1f3166fc89f912d05
+oid sha256:aa47165d0b231b49e9439f4fc7831eded1b2102ccb7c500ab01e81ad396690ae
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3c25d8770b8399ca86070cd4beebc85ba7fcfd052d46802e0a751af1b6b9d8e
+oid sha256:8c6c5acd314a10d449156637a38972d106d3430a026d1d64354edc928586e1a9
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fd36fba0c5ddcf37a7bd8a8886ff887ef5477282dea1dad65b3c54ba79e691d
+oid sha256:a9405e802193b74b98120b7fd5274673d4fe432c75c6a6737b3584cb8591bc18
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51924e125011267acf78f0473e5a2a5f661e40acdad62fb2e7797c88f2d9059b
+oid sha256:0fd04aba88066e6ec7515b2fc1981bbab2b31f877cbb75ba3d995f170bbbb79d
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.0010330178774893284,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.033783783783783786,
+  "best_metric": 0.0006301512476056814,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.06756756756756757,
   "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": 33.014,
       "eval_steps_per_second": 4.133,
       "step": 25
+    },
+    {
+      "epoch": 0.03513513513513514,
+      "grad_norm": 0.059504590928554535,
+      "learning_rate": 5e-05,
+      "loss": 0.0017,
+      "step": 26
+    },
+    {
+      "epoch": 0.03648648648648649,
+      "grad_norm": 0.051970165222883224,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0005,
+      "step": 27
+    },
+    {
+      "epoch": 0.03783783783783784,
+      "grad_norm": 0.041706208139657974,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0006,
+      "step": 28
+    },
+    {
+      "epoch": 0.03918918918918919,
+      "grad_norm": 0.025141162797808647,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0005,
+      "step": 29
+    },
+    {
+      "epoch": 0.04054054054054054,
+      "grad_norm": 0.024181494489312172,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0004,
+      "step": 30
+    },
+    {
+      "epoch": 0.041891891891891894,
+      "grad_norm": 0.0042442684061825275,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0002,
+      "step": 31
+    },
+    {
+      "epoch": 0.043243243243243246,
+      "grad_norm": 0.07526511698961258,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0009,
+      "step": 32
+    },
+    {
+      "epoch": 0.0445945945945946,
+      "grad_norm": 0.007108128629624844,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0002,
+      "step": 33
+    },
+    {
+      "epoch": 0.04594594594594595,
+      "grad_norm": 0.06577383726835251,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0006,
+      "step": 34
+    },
+    {
+      "epoch": 0.0472972972972973,
+      "grad_norm": 0.006310014054179192,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0002,
+      "step": 35
+    },
+    {
+      "epoch": 0.04864864864864865,
+      "grad_norm": 0.019449524581432343,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0004,
+      "step": 36
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.01652936451137066,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0005,
+      "step": 37
+    },
+    {
+      "epoch": 0.051351351351351354,
+      "grad_norm": 0.0990108922123909,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0044,
+      "step": 38
+    },
+    {
+      "epoch": 0.052702702702702706,
+      "grad_norm": 0.06821031123399734,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0011,
+      "step": 39
+    },
+    {
+      "epoch": 0.05405405405405406,
+      "grad_norm": 0.01180900540202856,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0004,
+      "step": 40
+    },
+    {
+      "epoch": 0.05540540540540541,
+      "grad_norm": 0.03767711669206619,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0008,
+      "step": 41
+    },
+    {
+      "epoch": 0.05675675675675676,
+      "grad_norm": 0.015823999419808388,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0001,
+      "step": 42
+    },
+    {
+      "epoch": 0.05810810810810811,
+      "grad_norm": 0.13913719356060028,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0006,
+      "step": 43
+    },
+    {
+      "epoch": 0.05945945945945946,
+      "grad_norm": 0.021133115515112877,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0003,
+      "step": 44
+    },
+    {
+      "epoch": 0.060810810810810814,
+      "grad_norm": 0.03227214142680168,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0012,
+      "step": 45
+    },
+    {
+      "epoch": 0.062162162162162166,
+      "grad_norm": 0.00861811637878418,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0002,
+      "step": 46
+    },
+    {
+      "epoch": 0.06351351351351352,
+      "grad_norm": 0.00826831255108118,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0002,
+      "step": 47
+    },
+    {
+      "epoch": 0.06486486486486487,
+      "grad_norm": 0.03811093792319298,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0004,
+      "step": 48
+    },
+    {
+      "epoch": 0.06621621621621622,
+      "grad_norm": 0.018121542409062386,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0003,
+      "step": 49
+    },
+    {
+      "epoch": 0.06756756756756757,
+      "grad_norm": 0.3153094947338104,
+      "learning_rate": 0.0,
+      "loss": 0.004,
+      "step": 50
+    },
+    {
+      "epoch": 0.06756756756756757,
+      "eval_loss": 0.0006301512476056814,
+      "eval_runtime": 150.859,
+      "eval_samples_per_second": 33.044,
+      "eval_steps_per_second": 4.136,
+      "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": 2.9859068337822106e+17,
+  "total_flos": 5.969948642440643e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null