Training in progress, step 12800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d07ab31876ed38a86e666a664b1303d2fcb4e0257dee9b88bcded8b3910c6bbf
+oid sha256:e23c2a9854e6224292f6c1140aa1338288015cf24527251ba96328a73e720464
 size 1342238560

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:835c77b5f6e495aa0a74d60ee06f6d033318181078fb2179a698f655ff7d79fa
+oid sha256:632d622114bdc171e1099025bfaaca6134055bf6db6a774c72051adfb383f846
 size 682101844

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce42cff510ee2ada7e8024123ff5b1a6490f6c777983ec0806bd2fa16bc7fbab
+oid sha256:d5bee219f111021b2fbc53a14d566a2c4bc2dd8384ab30dfa694874d872de377
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b459673e17f29c783844eae669e36f012c5d2d3ef2899548881a926791da6e99
+oid sha256:6c044f46d7cbd2c6b18fe9486bbe71c07c8f95dc6fca7686029d8d23b2d00a4a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcf8554566d6b1b01b6eb5b81f07754979de13dd3c15a2611e74f257e416adca
+oid sha256:94370ddab630f8b173819037c71ef1e0278dc02dc63037506f952d1acb8aded4
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6b39caa183f939db5b3e9f0bc1720923bca770c3bcb61bde91f678e36ed8f9b
+oid sha256:bccfd5cad920ae844408873b0ebb428e3ce7a0eee56be8c4ab86bf51aba5c412
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b561b94227cf1c22fba64906aaf8c69e33f95eadfd805cd1c2b45ffe750a03cf
+oid sha256:8ed5b4a7dd74456c87add6046084c7ad8e7b0225576806efaa3c0abcd6575d23
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9095445149333523,
+  "epoch": 0.9123957516572814,
   "eval_steps": 1280,
-  "global_step": 12760,
+  "global_step": 12800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -9019,6 +9019,42 @@
       "learning_rate": 2.669861432463838e-09,
       "loss": 0.1381,
       "step": 12760
+    },
+    {
+      "epoch": 0.9102573241143346,
+      "grad_norm": 0.38785186409950256,
+      "learning_rate": 1.501802903153271e-09,
+      "loss": 0.1402,
+      "step": 12770
+    },
+    {
+      "epoch": 0.9109701332953168,
+      "grad_norm": 0.3392987549304962,
+      "learning_rate": 6.674698132758117e-10,
+      "loss": 0.1425,
+      "step": 12780
+    },
+    {
+      "epoch": 0.9116829424762991,
+      "grad_norm": 0.28917720913887024,
+      "learning_rate": 1.6686773176566306e-10,
+      "loss": 0.1372,
+      "step": 12790
+    },
+    {
+      "epoch": 0.9123957516572814,
+      "grad_norm": 0.3354244828224182,
+      "learning_rate": 0.0,
+      "loss": 0.1419,
+      "step": 12800
+    },
+    {
+      "epoch": 0.9123957516572814,
+      "eval_loss": 0.1430967152118683,
+      "eval_runtime": 202.4398,
+      "eval_samples_per_second": 19.487,
+      "eval_steps_per_second": 4.876,
+      "step": 12800
     }
   ],
   "logging_steps": 10,
@@ -9033,12 +9069,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.917381750239265e+18,
+  "total_flos": 4.932796740051927e+18,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null