Training in progress, step 1533, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f223caf7929ca318636f3ba59853e80da2c3442e58790b9aa9620469f077dcdd
+oid sha256:dd4d1e46df8ec68b6c9e6ef9bc5ecf5f0ad16089ded3c1805891caf30fbe6f72
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98b4fcee642581b59a7244a4e37836a0670b2039f4714e7c1ed25e132985dbe4
+oid sha256:893f018393ecbc033a95361d425c0b3602b2ffb2547981cb44eaeddaacbecdb4
 size 49846644

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84b646cf536e8227b66dc69f9a778486c8a7ac0b176b0a4c53112763ef66fe62
+oid sha256:896ad7dae661b5fa712333e29820e33b88ac3783953f98a388981dde046510a4
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b3cae7afbbeecf2d5eebabe029b4fc894e107994ebf862a1691926e2168a23e
+oid sha256:6e62d7598f5c49e3b437a4b23d93990537e226573e28bd010a4ea6395b0e2122
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6b60196473d01acca54f1bfaab7782b1e9e71ebfb49f472a000c757182eb4c1
+oid sha256:c0de816f9b02b9ee5a2b349ad6f5a137bba325ea03a2d153fce825bff92786e7
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f306602a5392b7b4f66c9140309f102c7fa749834c21b02d757113b9665853a7
+oid sha256:88c46b6808dd9d7ce1226ecee5a6e06c39c94514246c005c8173fb95caf7000e
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d7adbf4e044c8cb7edc3f270cc5c3a63ee883daa8cd11b2707b6bd0b9847b17
+oid sha256:c582b8eeaf5293cff12aebb879053ac0a11aad5efa379d7618133c7165704367
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9975550122249389,
+  "epoch": 0.9995110024449878,
   "eval_steps": 767,
-  "global_step": 1530,
+  "global_step": 1533,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -10733,6 +10733,27 @@
       "learning_rate": 9.830211892492003e-10,
       "loss": 1.1091,
       "step": 1530
+    },
+    {
+      "epoch": 0.9982070089649552,
+      "grad_norm": 0.3718799948692322,
+      "learning_rate": 4.368991016689972e-10,
+      "loss": 1.0742,
+      "step": 1531
+    },
+    {
+      "epoch": 0.9988590057049714,
+      "grad_norm": 0.47078269720077515,
+      "learning_rate": 1.0922489471765219e-10,
+      "loss": 1.0806,
+      "step": 1532
+    },
+    {
+      "epoch": 0.9995110024449878,
+      "grad_norm": 0.4701193571090698,
+      "learning_rate": 0.0,
+      "loss": 0.8084,
+      "step": 1533
     }
   ],
   "logging_steps": 1,
@@ -10747,12 +10768,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.420887745382318e+18,
+  "total_flos": 3.4275953684124795e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null