Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f64ec1511b19d17226b80ba569807be85d2c24608aacbf58538f18bd0c051523
+oid sha256:2f2a0096e14a98aeb7f6ef2e758d32c02463c711919270f5579c1c5d46665bda
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3da6b9311ee779335be9752e6b93e853cce9870b947a723513a09811588a581
+oid sha256:4a39b06ff992f0aa2a5c76430966d2bee400de8fd88bf3f69c34a3c1f0d2ee56
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2f9a16272a3cf8b3f1cae03bfecd2ca0eecf3988b16f6a69c40e2c47b39a4fc
+oid sha256:af25ef66e3578b088787098691ff18f3d160f468c01678789a770159b408e9ff
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c8e96229eb8c5c66147bcf1025f2ac62ccb2fbf8cb8a140e4042a08295438b8
+oid sha256:b3cb1a771d842cefd502b9e7b043d798857a051d7ea04a1aca476720f6bce1e4
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1375358d9a695670af23e33bb8f1c2710512e5495e0f2736d0cee705784aeb1
+oid sha256:5c5fc06ca6e201f6cf92a9a131de3c7777a41831442b3ee77f257c6e125e5136
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ff1d0deeb41f4600ea1371b03f2a948b92e13a536aeeae1d92332cad54240ff
+oid sha256:ce1df0fc9a8b7b175429da9e9454ce253fb484f5186e19d58b68bb4f04eaed68
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:344fc18df9c84f214bc47e69d1bbde70d66cf3ec6caeac9cd529dfb5814c4b9a
+oid sha256:051dee7dfbeecb34b46e8409ffafec324501f465585234624669bc8c9e863ae4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7449390292167664,
-  "best_model_checkpoint": "miner_id_24/checkpoint-75",
-  "epoch": 0.02659044073655521,
+  "best_metric": 0.733076810836792,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.03545392098207361,
   "eval_steps": 25,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -564,6 +564,189 @@
       "eval_samples_per_second": 34.938,
       "eval_steps_per_second": 9.084,
       "step": 75
+    },
+    {
+      "epoch": 0.026944979946375944,
+      "grad_norm": 0.6937525272369385,
+      "learning_rate": 2.3444344707738015e-05,
+      "loss": 0.9399,
+      "step": 76
+    },
+    {
+      "epoch": 0.027299519156196682,
+      "grad_norm": 0.7247990965843201,
+      "learning_rate": 2.2400865784401e-05,
+      "loss": 0.8895,
+      "step": 77
+    },
+    {
+      "epoch": 0.027654058366017416,
+      "grad_norm": 0.6984252333641052,
+      "learning_rate": 2.1393033535713093e-05,
+      "loss": 0.7613,
+      "step": 78
+    },
+    {
+      "epoch": 0.02800859757583815,
+      "grad_norm": 0.6211410164833069,
+      "learning_rate": 2.0421950011441354e-05,
+      "loss": 0.6435,
+      "step": 79
+    },
+    {
+      "epoch": 0.02836313678565889,
+      "grad_norm": 0.7938443422317505,
+      "learning_rate": 1.9488677077162295e-05,
+      "loss": 0.5725,
+      "step": 80
+    },
+    {
+      "epoch": 0.028717675995479624,
+      "grad_norm": 0.6987906098365784,
+      "learning_rate": 1.8594235253127375e-05,
+      "loss": 0.69,
+      "step": 81
+    },
+    {
+      "epoch": 0.029072215205300362,
+      "grad_norm": 0.8338001370429993,
+      "learning_rate": 1.77396025983391e-05,
+      "loss": 0.7627,
+      "step": 82
+    },
+    {
+      "epoch": 0.029426754415121097,
+      "grad_norm": 0.6527311205863953,
+      "learning_rate": 1.6925713641057904e-05,
+      "loss": 0.5054,
+      "step": 83
+    },
+    {
+      "epoch": 0.029781293624941835,
+      "grad_norm": 0.7132216691970825,
+      "learning_rate": 1.6153458356909176e-05,
+      "loss": 0.5969,
+      "step": 84
+    },
+    {
+      "epoch": 0.03013583283476257,
+      "grad_norm": 0.7264847159385681,
+      "learning_rate": 1.5423681195707997e-05,
+      "loss": 0.5129,
+      "step": 85
+    },
+    {
+      "epoch": 0.030490372044583304,
+      "grad_norm": 0.7762057781219482,
+      "learning_rate": 1.4737180158065644e-05,
+      "loss": 0.4313,
+      "step": 86
+    },
+    {
+      "epoch": 0.030844911254404042,
+      "grad_norm": 0.6852719187736511,
+      "learning_rate": 1.4094705922787687e-05,
+      "loss": 0.4345,
+      "step": 87
+    },
+    {
+      "epoch": 0.031199450464224777,
+      "grad_norm": 0.7660951018333435,
+      "learning_rate": 1.3496961026017687e-05,
+      "loss": 0.724,
+      "step": 88
+    },
+    {
+      "epoch": 0.03155398967404551,
+      "grad_norm": 0.7194827198982239,
+      "learning_rate": 1.2944599093024267e-05,
+      "loss": 0.8667,
+      "step": 89
+    },
+    {
+      "epoch": 0.03190852888386625,
+      "grad_norm": 0.7124308943748474,
+      "learning_rate": 1.2438224123471442e-05,
+      "loss": 0.7907,
+      "step": 90
+    },
+    {
+      "epoch": 0.03226306809368699,
+      "grad_norm": 0.8714865446090698,
+      "learning_rate": 1.1978389830953907e-05,
+      "loss": 0.8492,
+      "step": 91
+    },
+    {
+      "epoch": 0.032617607303507726,
+      "grad_norm": 0.757225513458252,
+      "learning_rate": 1.1565599037519316e-05,
+      "loss": 0.742,
+      "step": 92
+    },
+    {
+      "epoch": 0.03297214651332846,
+      "grad_norm": 0.754546046257019,
+      "learning_rate": 1.1200303123839742e-05,
+      "loss": 0.6044,
+      "step": 93
+    },
+    {
+      "epoch": 0.033326685723149195,
+      "grad_norm": 0.770008385181427,
+      "learning_rate": 1.088290153563358e-05,
+      "loss": 0.6478,
+      "step": 94
+    },
+    {
+      "epoch": 0.03368122493296993,
+      "grad_norm": 0.8305578231811523,
+      "learning_rate": 1.0613741346877497e-05,
+      "loss": 0.647,
+      "step": 95
+    },
+    {
+      "epoch": 0.034035764142790664,
+      "grad_norm": 0.9594391584396362,
+      "learning_rate": 1.0393116880286118e-05,
+      "loss": 0.6551,
+      "step": 96
+    },
+    {
+      "epoch": 0.0343903033526114,
+      "grad_norm": 0.823460042476654,
+      "learning_rate": 1.0221269385474488e-05,
+      "loss": 0.5407,
+      "step": 97
+    },
+    {
+      "epoch": 0.03474484256243214,
+      "grad_norm": 0.8756825923919678,
+      "learning_rate": 1.0098386775155147e-05,
+      "loss": 0.4781,
+      "step": 98
+    },
+    {
+      "epoch": 0.03509938177225287,
+      "grad_norm": 0.7407690286636353,
+      "learning_rate": 1.0024603419658329e-05,
+      "loss": 0.4027,
+      "step": 99
+    },
+    {
+      "epoch": 0.03545392098207361,
+      "grad_norm": 0.6229119300842285,
+      "learning_rate": 1e-05,
+      "loss": 0.276,
+      "step": 100
+    },
+    {
+      "epoch": 0.03545392098207361,
+      "eval_loss": 0.733076810836792,
+      "eval_runtime": 1.4314,
+      "eval_samples_per_second": 34.932,
+      "eval_steps_per_second": 9.082,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -587,12 +770,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8.436965477019812e+17,
+  "total_flos": 1.1249873143390536e+18,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null