Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e7ab1bd03057902d00497e6d96743cc05ea8532e4a7252b6508dd6da5b1f890
+oid sha256:cf1cb07dd91c37e1f44df0b4a8282570684678cadd1969f28d0ad45be25d29d1
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c7e896eb8c0034a543cdf874011284e8d086a05804e72d4709b670aec3ecb19
+oid sha256:3530652e6a3a4402779ba0c96a8e84b6c7aef46855f2c23d3d0345af1885270f
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd308249a57c0d6f4344a3870ce1dd0978df546565c0904a7176ff7b4e6cfaff
+oid sha256:664fae6eb8c1232844051f69861ba508c8e0ece5806fb44b43b10ec6b7b9a2dd
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:703b0e9eaf666dcc055ac26b17cfcd5d9b292a72d96dafd92d5f0e43b369e1e1
+oid sha256:21d711ce0173301c459bb84254bb1bdafd1f45e06a79acdcb11b05004b60ecb9
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4122ebc679b94e00543ee3829b404bff9c8cdb3c779e79ee40bc024f5ce6543
+oid sha256:5685264d45c7ae92b2480be5078984f9d2dfab0a9f59ec7f6b9c5305734c7a4a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9da85ffb38f6cea2da7d26e5761e3fc76c491b42c69596615720b283776ecbd
+oid sha256:3c332cfd5936929f316dbda6240830941934828277f13340e055193238ed7b78
 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": 2.039912396867294e-05,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.05650515609549371,
+  "best_metric": 1.4871836356178392e-05,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.11301031219098742,
   "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": 28.684,
       "eval_steps_per_second": 7.458,
       "step": 25
+    },
+    {
+      "epoch": 0.05876536233931346,
+      "grad_norm": 0.014457793906331062,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0008,
+      "step": 26
+    },
+    {
+      "epoch": 0.06102556858313321,
+      "grad_norm": 0.1443701684474945,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.0014,
+      "step": 27
+    },
+    {
+      "epoch": 0.06328577482695295,
+      "grad_norm": 0.0193707924336195,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0006,
+      "step": 28
+    },
+    {
+      "epoch": 0.06554598107077271,
+      "grad_norm": 0.15904578566551208,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.0015,
+      "step": 29
+    },
+    {
+      "epoch": 0.06780618731459245,
+      "grad_norm": 0.029126852750778198,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0007,
+      "step": 30
+    },
+    {
+      "epoch": 0.07006639355841221,
+      "grad_norm": 0.021486882120370865,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.0006,
+      "step": 31
+    },
+    {
+      "epoch": 0.07232659980223195,
+      "grad_norm": 0.02886809967458248,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0006,
+      "step": 32
+    },
+    {
+      "epoch": 0.0745868060460517,
+      "grad_norm": 0.024365216493606567,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.0008,
+      "step": 33
+    },
+    {
+      "epoch": 0.07684701228987145,
+      "grad_norm": 0.004941640887409449,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0003,
+      "step": 34
+    },
+    {
+      "epoch": 0.0791072185336912,
+      "grad_norm": 0.009240135550498962,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.0004,
+      "step": 35
+    },
+    {
+      "epoch": 0.08136742477751095,
+      "grad_norm": 0.014623638242483139,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.0003,
+      "step": 36
+    },
+    {
+      "epoch": 0.0836276310213307,
+      "grad_norm": 0.003545256331562996,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.0002,
+      "step": 37
+    },
+    {
+      "epoch": 0.08588783726515045,
+      "grad_norm": 0.3244648277759552,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.1677,
+      "step": 38
+    },
+    {
+      "epoch": 0.0881480435089702,
+      "grad_norm": 1.182705283164978,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0106,
+      "step": 39
+    },
+    {
+      "epoch": 0.09040824975278994,
+      "grad_norm": 1.5810155868530273,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0373,
+      "step": 40
+    },
+    {
+      "epoch": 0.0926684559966097,
+      "grad_norm": 1.5483887195587158,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.1527,
+      "step": 41
+    },
+    {
+      "epoch": 0.09492866224042944,
+      "grad_norm": 0.06926979124546051,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0006,
+      "step": 42
+    },
+    {
+      "epoch": 0.0971888684842492,
+      "grad_norm": 0.02940315008163452,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0005,
+      "step": 43
+    },
+    {
+      "epoch": 0.09944907472806894,
+      "grad_norm": 0.025981120765209198,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0008,
+      "step": 44
+    },
+    {
+      "epoch": 0.10170928097188868,
+      "grad_norm": 0.05548268184065819,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0006,
+      "step": 45
+    },
+    {
+      "epoch": 0.10396948721570844,
+      "grad_norm": 0.017940428107976913,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0003,
+      "step": 46
+    },
+    {
+      "epoch": 0.10622969345952818,
+      "grad_norm": 0.0061012692749500275,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0003,
+      "step": 47
+    },
+    {
+      "epoch": 0.10848989970334794,
+      "grad_norm": 0.0036830762401223183,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0002,
+      "step": 48
+    },
+    {
+      "epoch": 0.11075010594716768,
+      "grad_norm": 0.006693420931696892,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0002,
+      "step": 49
+    },
+    {
+      "epoch": 0.11301031219098742,
+      "grad_norm": 0.008400761522352695,
+      "learning_rate": 1e-05,
+      "loss": 0.0003,
+      "step": 50
+    },
+    {
+      "epoch": 0.11301031219098742,
+      "eval_loss": 1.4871836356178392e-05,
+      "eval_runtime": 1.7601,
+      "eval_samples_per_second": 28.407,
+      "eval_steps_per_second": 7.386,
+      "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": 2.629578157719552e+17,
+  "total_flos": 5.259156315439104e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null