Training in progress, step 35, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ffab7e1cb258a8173601436361b5a2d2721cb77d5f77c2572cb4e51cae53444
+oid sha256:0bba34187caab778beecca6e3e8ba092b9066012c6fe6d076f00dfe7b1791402
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25708fd9ddc3f0d49993bdc4f125cec1665ce6aa51bfca5223dbbfaf4a98239e
+oid sha256:87b254f9cfd98befe059577ca86bf091be30cca8b57751d330b6ac558791cbe2
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:115f3ae43bd1cccdf744378e1c0700123865f59182de6102505a85514ffb2ada
+oid sha256:a09292a498f9693015b4820c14e04d3a1ab4686eb8eb510e7848e581baacf429
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bf8839b0dfbcdd56de068ecc39fe0e4dc3fc410466b2b574132d48df4217149
+oid sha256:a11dbda2bcaeb9f8f5315fac146f94fc8d1d5bfe30715eadef4b12e222b2e2d9
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efe28a813ed0807ac209bd7b1bc3dac4069a6b16dcc783f1cb372407be0a2b38
+oid sha256:c39d31a69aac4efd1f7ce9283f9f93ffe67cc21872e605f498449b686382623a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:daafba58fc65cb8b160f0ee3aa6c9d52faba3b3dcf261d0152e0f7c741fe14f2
+oid sha256:4e84b8ed19a2393eb2c53153ea3aa0f29133154ca3628d589c20a90fca4a66d4
 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": 1.8321987390518188,
   "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": 15.453,
       "eval_steps_per_second": 1.981,
       "step": 25
+    },
+    {
+      "epoch": 2.2594594594594595,
+      "grad_norm": 3.1819040775299072,
+      "learning_rate": 1.725696330273575e-05,
+      "loss": 28.4675,
+      "step": 26
+    },
+    {
+      "epoch": 2.345945945945946,
+      "grad_norm": 2.3536086082458496,
+      "learning_rate": 1.3813298094746491e-05,
+      "loss": 29.8276,
+      "step": 27
+    },
+    {
+      "epoch": 2.4324324324324325,
+      "grad_norm": 2.923321008682251,
+      "learning_rate": 1.0697345262860636e-05,
+      "loss": 28.0126,
+      "step": 28
+    },
+    {
+      "epoch": 2.518918918918919,
+      "grad_norm": 3.1668083667755127,
+      "learning_rate": 7.937323358440935e-06,
+      "loss": 29.3021,
+      "step": 29
+    },
+    {
+      "epoch": 2.6054054054054054,
+      "grad_norm": 2.4113199710845947,
+      "learning_rate": 5.558227567253832e-06,
+      "loss": 29.5839,
+      "step": 30
+    },
+    {
+      "epoch": 2.691891891891892,
+      "grad_norm": 3.0063042640686035,
+      "learning_rate": 3.581603349196372e-06,
+      "loss": 29.1112,
+      "step": 31
+    },
+    {
+      "epoch": 2.7783783783783784,
+      "grad_norm": 2.736527919769287,
+      "learning_rate": 2.0253513192751373e-06,
+      "loss": 28.905,
+      "step": 32
+    },
+    {
+      "epoch": 2.864864864864865,
+      "grad_norm": 2.431605577468872,
+      "learning_rate": 9.035651368646648e-07,
+      "loss": 28.684,
+      "step": 33
+    },
+    {
+      "epoch": 2.9513513513513514,
+      "grad_norm": 3.4076993465423584,
+      "learning_rate": 2.2640387134577058e-07,
+      "loss": 28.1141,
+      "step": 34
+    },
+    {
+      "epoch": 3.0432432432432432,
+      "grad_norm": 2.473551034927368,
+      "learning_rate": 0.0,
+      "loss": 29.3945,
+      "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": 4.146268785113825e+17,
+  "total_flos": 5.774718047847711e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null