Training in progress, step 36, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9403fb908bc695cebdf82191db72c614e2bf14fa8a73110595b157f28f62b456
+oid sha256:473ea3e3d593b485955cb7bfbbed914a5d88e9a0bb5a5807b3399185ede724a9
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0912519459d961851b28aab54c29c223bdacdac16598731af2ceda83d407bdb
+oid sha256:a863c344e7323e8319d46d0b040c78edf6df3287d54d296838b37390c35b3fad
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7140e90d5cd57835971d48f905f3271e6a5c8cef2eca3e8524c1948f7c18e5e2
+oid sha256:cb24a807fc0c51bc8eae22da3ace2a152134835fe207f24f66aeb448558ada14
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80fbd81e4c0b089130777a152d2d7b6d9899a9b6508f54f19b5440b13d73e4a9
+oid sha256:7169452b3bd8c83ac883fbdddda2d02deac0b966334dc0ba8d64f38cda8a1ade
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee1d62d4395721bc7fac75c5dad4c799d75060ed93c796a27461cef43ab33034
+oid sha256:5d65ecbcc70c961762e72976b50b0d88898224c45afd62af48d0795749b92422
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e43815d123aacf4652ac39faf36bd18fe72329ffe8265b526e8677882c74ec7
+oid sha256:90d6b9a21f2476e669a0c031ad1a0498569beab5877a919a8734a74508acb73a
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80ee0e3a85744dc5ab7c697968a5f553547d0d3855c554f1051966905d4f4d69
+oid sha256:28651c349f447d90467a1ab072123a42ef3fcd558c7e8a7b853a87ba29324613
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.2677198052406311,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 2.1052631578947367,
+  "epoch": 3.031578947368421,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 36,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,83 @@
       "eval_samples_per_second": 19.046,
       "eval_steps_per_second": 2.381,
       "step": 25
+    },
+    {
+      "epoch": 2.1894736842105265,
+      "grad_norm": 0.04200873523950577,
+      "learning_rate": 1.9868268181037185e-05,
+      "loss": 0.0011,
+      "step": 26
+    },
+    {
+      "epoch": 2.2736842105263158,
+      "grad_norm": 2.74108624458313,
+      "learning_rate": 1.631521781767214e-05,
+      "loss": 0.0985,
+      "step": 27
+    },
+    {
+      "epoch": 2.3578947368421055,
+      "grad_norm": 2.8675966262817383,
+      "learning_rate": 1.3049554138967051e-05,
+      "loss": 0.4339,
+      "step": 28
+    },
+    {
+      "epoch": 2.442105263157895,
+      "grad_norm": 0.026142483577132225,
+      "learning_rate": 1.0099138635988026e-05,
+      "loss": 0.0007,
+      "step": 29
+    },
+    {
+      "epoch": 2.526315789473684,
+      "grad_norm": 4.404775619506836,
+      "learning_rate": 7.489143213519301e-06,
+      "loss": 0.1664,
+      "step": 30
+    },
+    {
+      "epoch": 2.610526315789474,
+      "grad_norm": 2.646777629852295,
+      "learning_rate": 5.241835432246889e-06,
+      "loss": 0.25,
+      "step": 31
+    },
+    {
+      "epoch": 2.694736842105263,
+      "grad_norm": 0.018841933459043503,
+      "learning_rate": 3.376388529782215e-06,
+      "loss": 0.0006,
+      "step": 32
+    },
+    {
+      "epoch": 2.7789473684210524,
+      "grad_norm": 4.183905601501465,
+      "learning_rate": 1.908717841359048e-06,
+      "loss": 0.2952,
+      "step": 33
+    },
+    {
+      "epoch": 2.863157894736842,
+      "grad_norm": 2.0903871059417725,
+      "learning_rate": 8.513450158049108e-07,
+      "loss": 0.2034,
+      "step": 34
+    },
+    {
+      "epoch": 2.9473684210526314,
+      "grad_norm": 2.281219959259033,
+      "learning_rate": 2.1329118524827662e-07,
+      "loss": 0.0681,
+      "step": 35
+    },
+    {
+      "epoch": 3.031578947368421,
+      "grad_norm": 1.8667627573013306,
+      "learning_rate": 0.0,
+      "loss": 0.1752,
+      "step": 36
     }
   ],
   "logging_steps": 1,
@@ -221,12 +298,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.949297687236444e+17,
+  "total_flos": 5.610862382625587e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null