Training in progress, step 36, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4baaeb2f7bc4c8e7b914a740085a24c46393a9168b6a9b0ad05f547ceea4c460
+oid sha256:313220a3d09e5ebce47a70491c495c8c9804dca1b526ae4f6be83e7842a4c9f1
 size 69527352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18020a5888de925053a30cc7d71384c1e9de64cfa0a06a06fb4e4fdd40921939
+oid sha256:09f4f93741fdc1b6020eeee3d6ba6c19e4045757f70f12a299e4f226d729a91b
 size 139313234

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8859992c8fce27dedb42f7cb90fc5243c2a604e54f2227bc1a6d7dbd93750a45
+oid sha256:82ab72d39363043353734178cb453747d9ade9dc92d465625b83d96c9e3aa87d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:845e5dc02684215b0876bca7fa7165b434db0ec8a6c680cb7bbd1a81beec7f58
+oid sha256:c5a37fe576bec7014bc2880a3a8418effd77ff81b2a33842bc09c09aca6dfbb0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:512f4f835c987c1f1a1acd697868a93c667cc03a82163d5164d9c97bc04cc99c
+oid sha256:63307387652bc837aa0f3c125f016d2fd3dbe96a4d8db0929c7af0fc9f201310
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:387b2e85b4c7e879118995f7b688c6181084dec5bdbfc2cff6c90acd23a67b24
+oid sha256:a7aa97eddaacdfbe2f89d2f87b1bd4a64faa4653f8a6b5a94cc9c2937a54defd
 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": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 2.171122994652406,
+  "epoch": 3.128342245989305,
   "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": 141.667,
       "eval_steps_per_second": 17.933,
       "step": 25
+    },
+    {
+      "epoch": 2.2566844919786098,
+      "grad_norm": 0.2852610945701599,
+      "learning_rate": 1.9868268181037185e-05,
+      "loss": 1.9419,
+      "step": 26
+    },
+    {
+      "epoch": 2.342245989304813,
+      "grad_norm": 0.3041047751903534,
+      "learning_rate": 1.631521781767214e-05,
+      "loss": 1.6465,
+      "step": 27
+    },
+    {
+      "epoch": 2.427807486631016,
+      "grad_norm": 0.4177848696708679,
+      "learning_rate": 1.3049554138967051e-05,
+      "loss": 1.4746,
+      "step": 28
+    },
+    {
+      "epoch": 2.5133689839572195,
+      "grad_norm": 0.30657851696014404,
+      "learning_rate": 1.0099138635988026e-05,
+      "loss": 1.7037,
+      "step": 29
+    },
+    {
+      "epoch": 2.598930481283422,
+      "grad_norm": 0.3365192115306854,
+      "learning_rate": 7.489143213519301e-06,
+      "loss": 1.484,
+      "step": 30
+    },
+    {
+      "epoch": 2.6844919786096257,
+      "grad_norm": 0.2342955768108368,
+      "learning_rate": 5.241835432246889e-06,
+      "loss": 0.6956,
+      "step": 31
+    },
+    {
+      "epoch": 2.770053475935829,
+      "grad_norm": 0.3052198588848114,
+      "learning_rate": 3.376388529782215e-06,
+      "loss": 1.6939,
+      "step": 32
+    },
+    {
+      "epoch": 2.855614973262032,
+      "grad_norm": 0.34793445467948914,
+      "learning_rate": 1.908717841359048e-06,
+      "loss": 1.4545,
+      "step": 33
+    },
+    {
+      "epoch": 2.9411764705882355,
+      "grad_norm": 0.0,
+      "learning_rate": 8.513450158049108e-07,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 3.0427807486631018,
+      "grad_norm": 0.5034242868423462,
+      "learning_rate": 2.1329118524827662e-07,
+      "loss": 2.7541,
+      "step": 35
+    },
+    {
+      "epoch": 3.128342245989305,
+      "grad_norm": 0.4670789837837219,
+      "learning_rate": 0.0,
+      "loss": 1.8256,
+      "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": 1.3054859280384e+16,
+  "total_flos": 1.879899736375296e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null