Training in progress, step 35, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77a6b96454de4850b867ed07156e5ad35e19987d0644f3e5605c16c1cdaa5e0b
+oid sha256:eeb756ad9543c942ccee853685806313a7458e964b89e6b76291396f47888bbf
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b91500b60d57a2ac18b8c39a96f813eadb4927cc17aa6b140592d19833e24f72
+oid sha256:33c96c5cee596f773ee704aa44808aca5f7704f975e805fd6549e746d2557eba
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55f420275005555115dc61c2e8c188670b6291e5a018d9a639b2f1eb082ecce4
+oid sha256:3f30b1a9f2f9dcf33e252cc1e54568bab7e45961cf67fc1d25ebe8a50aa0f6ba
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6b71fec2fe35f6b651be8a302d7480d5a61c3ea70171116b7361414453c9e86
+oid sha256:33841d63f2b79d8913e0f297a5a798cd3471b59811718d27e7ae78c8e74f5acc
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:105bfa9a5bf4bf4cb4f1a118e05fd0543018980a49e2913feb7814564ee7bf03
+oid sha256:6b2d275d83b9acfc3c3118bef8b91a20ebb6f62444214a9b15bcac644e89900b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06dae407277ea50434ec71c42e01bfa9936fda16ce40aac6667147cfb5e26701
+oid sha256:288cd09d6e31385d591a7d28dc534f5bcf6cb5610f2592fbf7acfc0e94ff576b
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42c052e81d046347be3074b07671b8743acfee2fa86afcaf4cf737a53f8e085c
+oid sha256:400690333b498d3c3ea4cd1446f834c1cb37202647b1e68e58a488ea7599ce2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 2.1148202419281006,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 2.172972972972973,
+  "epoch": 3.0432432432432432,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 35,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,76 @@
       "eval_samples_per_second": 17.621,
       "eval_steps_per_second": 2.259,
       "step": 25
+    },
+    {
+      "epoch": 2.2594594594594595,
+      "grad_norm": 0.08170148730278015,
+      "learning_rate": 1.725696330273575e-05,
+      "loss": 2.1414,
+      "step": 26
+    },
+    {
+      "epoch": 2.345945945945946,
+      "grad_norm": 0.06469491124153137,
+      "learning_rate": 1.3813298094746491e-05,
+      "loss": 2.2124,
+      "step": 27
+    },
+    {
+      "epoch": 2.4324324324324325,
+      "grad_norm": 0.08539947867393494,
+      "learning_rate": 1.0697345262860636e-05,
+      "loss": 2.0401,
+      "step": 28
+    },
+    {
+      "epoch": 2.518918918918919,
+      "grad_norm": 0.08035576343536377,
+      "learning_rate": 7.937323358440935e-06,
+      "loss": 2.1775,
+      "step": 29
+    },
+    {
+      "epoch": 2.6054054054054054,
+      "grad_norm": 0.06767440587282181,
+      "learning_rate": 5.558227567253832e-06,
+      "loss": 2.224,
+      "step": 30
+    },
+    {
+      "epoch": 2.691891891891892,
+      "grad_norm": 0.08720237016677856,
+      "learning_rate": 3.581603349196372e-06,
+      "loss": 2.1221,
+      "step": 31
+    },
+    {
+      "epoch": 2.7783783783783784,
+      "grad_norm": 0.06554112583398819,
+      "learning_rate": 2.0253513192751373e-06,
+      "loss": 2.1821,
+      "step": 32
+    },
+    {
+      "epoch": 2.864864864864865,
+      "grad_norm": 0.06643765419721603,
+      "learning_rate": 9.035651368646648e-07,
+      "loss": 2.1201,
+      "step": 33
+    },
+    {
+      "epoch": 2.9513513513513514,
+      "grad_norm": 0.10307445377111435,
+      "learning_rate": 2.2640387134577058e-07,
+      "loss": 2.0542,
+      "step": 34
+    },
+    {
+      "epoch": 3.0432432432432432,
+      "grad_norm": 0.13227105140686035,
+      "learning_rate": 0.0,
+      "loss": 3.2883,
+      "step": 35
     }
   ],
   "logging_steps": 1,
@@ -221,12 +291,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.185118621879501e+17,
+  "total_flos": 5.841261823000576e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null