Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2138e5e84a7cd0e3a274005feebd24ef9129bdd381dde34fb0c9b373d521a3e2
+oid sha256:40301c8d214653e61e8f5c4965492337eb672d8937073a7999bdc086f5de0702
 size 166182480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f44e8241585dd8d3a43f4c97d44676b091e84e1d59b4c3f43cea6c77c6fd737d
+oid sha256:822be74936cd12e24ebff7679e8a5c5a073bf248ad3db731762743a51e0370cd
 size 332574358

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dfeedb5d161ef8740b0587e45146da1f9d89590458422b1d2570ce95f10e3da
+oid sha256:cf0b4c09a1563ffdddbceda696c9585cb83b0c823df9392104fa8c85bc050011
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ef5d5463f8a2cb3dce83501ef78d8f2c0b61febd45397495db0f3a4d033a102
+oid sha256:76c592077e663239d6131acf33b2dbb642ed52ea75cdcec31060ce1bd3b06259
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dcd199a49e930f02b47628e62244ff084425c9645a2d30124abb3ba38a0b6f9
+oid sha256:18a44fac865b8da6aae507d378ca97fbddc929523e8be73359620532ff7c2f8e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fe0bc3b9ca33f9a845ac844a71b99a2c2f00bcc7cf0263a81a3e7a6497953ad
+oid sha256:c075282c2a7e2b2c533df10be5d7054dc4502942f508a483443d986c5a5a5100
 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": 0.758933961391449,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.34572169403630076,
+  "best_metric": 0.6049863696098328,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6914433880726015,
   "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": 24.173,
       "eval_steps_per_second": 6.285,
       "step": 25
+    },
+    {
+      "epoch": 0.3595505617977528,
+      "grad_norm": 3.900346040725708,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.6268,
+      "step": 26
+    },
+    {
+      "epoch": 0.37337942955920483,
+      "grad_norm": 1.8691695928573608,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.5065,
+      "step": 27
+    },
+    {
+      "epoch": 0.38720829732065687,
+      "grad_norm": 2.709653377532959,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.5134,
+      "step": 28
+    },
+    {
+      "epoch": 0.4010371650821089,
+      "grad_norm": 4.127618789672852,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.7177,
+      "step": 29
+    },
+    {
+      "epoch": 0.41486603284356094,
+      "grad_norm": 3.254377841949463,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.6108,
+      "step": 30
+    },
+    {
+      "epoch": 0.428694900605013,
+      "grad_norm": 2.024759292602539,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.4477,
+      "step": 31
+    },
+    {
+      "epoch": 0.442523768366465,
+      "grad_norm": 1.9464025497436523,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.5394,
+      "step": 32
+    },
+    {
+      "epoch": 0.45635263612791704,
+      "grad_norm": 1.8650126457214355,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.4821,
+      "step": 33
+    },
+    {
+      "epoch": 0.4701815038893691,
+      "grad_norm": 1.5287123918533325,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.4385,
+      "step": 34
+    },
+    {
+      "epoch": 0.4840103716508211,
+      "grad_norm": 1.276076078414917,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.4649,
+      "step": 35
+    },
+    {
+      "epoch": 0.4978392394122731,
+      "grad_norm": 1.4761910438537598,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.4801,
+      "step": 36
+    },
+    {
+      "epoch": 0.5116681071737251,
+      "grad_norm": 2.025033950805664,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.6552,
+      "step": 37
+    },
+    {
+      "epoch": 0.5254969749351772,
+      "grad_norm": 1.9071918725967407,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.5439,
+      "step": 38
+    },
+    {
+      "epoch": 0.5393258426966292,
+      "grad_norm": 3.013430118560791,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.4093,
+      "step": 39
+    },
+    {
+      "epoch": 0.5531547104580813,
+      "grad_norm": 2.1112544536590576,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.492,
+      "step": 40
+    },
+    {
+      "epoch": 0.5669835782195333,
+      "grad_norm": 1.9682427644729614,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.4969,
+      "step": 41
+    },
+    {
+      "epoch": 0.5808124459809854,
+      "grad_norm": 2.6426448822021484,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.4845,
+      "step": 42
+    },
+    {
+      "epoch": 0.5946413137424373,
+      "grad_norm": 2.1030192375183105,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.524,
+      "step": 43
+    },
+    {
+      "epoch": 0.6084701815038893,
+      "grad_norm": 1.8651204109191895,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.4401,
+      "step": 44
+    },
+    {
+      "epoch": 0.6222990492653414,
+      "grad_norm": 1.5484836101531982,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.4205,
+      "step": 45
+    },
+    {
+      "epoch": 0.6361279170267934,
+      "grad_norm": 1.8427436351776123,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.4307,
+      "step": 46
+    },
+    {
+      "epoch": 0.6499567847882455,
+      "grad_norm": 1.3399065732955933,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.3673,
+      "step": 47
+    },
+    {
+      "epoch": 0.6637856525496975,
+      "grad_norm": 2.0689697265625,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.5564,
+      "step": 48
+    },
+    {
+      "epoch": 0.6776145203111495,
+      "grad_norm": 1.9621024131774902,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.4653,
+      "step": 49
+    },
+    {
+      "epoch": 0.6914433880726015,
+      "grad_norm": 2.4232048988342285,
+      "learning_rate": 1e-05,
+      "loss": 0.7471,
+      "step": 50
+    },
+    {
+      "epoch": 0.6914433880726015,
+      "eval_loss": 0.6049863696098328,
+      "eval_runtime": 2.0809,
+      "eval_samples_per_second": 24.028,
+      "eval_steps_per_second": 6.247,
+      "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