Training in progress, step 4000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7057efa04f84d06fb8967e215cd3ed4e982d7324a9964d6bbddac5f0e932d7f5
+oid sha256:9286827e09996aa12033872735e0de092fd721c4fe1f91e63b8050c811435776
 size 281587880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e1eb62a18526c2a140b51e8df453f354efe9fff401a06b4a4b58ee9618117dd
+oid sha256:353f67a4c0bb212617e4e1eb2fea3e745777ba393205008d24b356bb498ecc67
 size 143366164

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc3697b212f20146262137e7c1a969576663ccc4ae69304edc36288b1d18cfd1
+oid sha256:ea009eea43ba9165a25447a2ebeb5b3ce293fc229f86ecc8e82133799a169966
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b9e6d31c8b9ec88e33f75ea2e1485990411f6bd2ad3eadb72c07fb2ff77cc4a
+oid sha256:6dfb77a49f10367faf585826f2baa575617770456a06df6deae0b699b8cbfe55
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d078af19d6439842c947502bac22108599fc2ee9fcd36b51d3f5f8765f9e42c
+oid sha256:556f588ce3e53b2cd23465a5fe33a0f16e45fcf93add9e1c51ddd54944327598
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5982284510275852c78aa2d02bd147d4856df83b4bf467c5c077c2680e8271c0
+oid sha256:8445b826fcbaedb310f62e7bc99ed78babefe67e99b18bb93ecdf39f948cb8d3
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0a4ea943eff6a00a0d44284eab894bea8fb50f7f4cf9fce50a355f53053d12e
+oid sha256:ca8ec1dff7e8c1bbfb8a0a9f36b118f79da805799d7feb6fd3b3b5df69889adf
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae334b3ce7770bc0260e90dc8782002eb4f829e4a83cf87989a3bcab2ddad5aa
+oid sha256:038432af1ae4b33111e160b3375c93d2ca42e7f72b9e44ece5c683ff70210b50
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cec5f6de25d29de2f1bb3c4f3529450759465854bf2202d64d33659c58ee0a0e
+oid sha256:0d9b46724719c2f5295bd4180c934cad4763102ab04394464305bff7116c4581
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd393c8d7b7d37049aa33eaacfe9ea78417f491646acb1001289f2f04bc216ff
+oid sha256:b97c73dff8b858f452882698214d6c496e79029e7e4e7768425eabf4cf62410b
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e374cd16ce446630eb5de7b6aef11f861ca1227fccdd18be31c30ca89d07e197
+oid sha256:94a718f147a195eb428ec1cc98c1dc66af23c9088cc3fbd17bc99e8886d33266
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 99.5,
+  "epoch": 100.0,
   "eval_steps": 40,
-  "global_step": 3980,
+  "global_step": 4000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3593,6 +3593,28 @@
       "learning_rate": 1.2486132855826781e-08,
       "loss": 0.0,
       "step": 3980
+    },
+    {
+      "epoch": 99.75,
+      "grad_norm": 9.601525562175084e-06,
+      "learning_rate": 3.121581935328077e-09,
+      "loss": 0.0,
+      "step": 3990
+    },
+    {
+      "epoch": 100.0,
+      "grad_norm": 2.9180186174926348e-05,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 4000
+    },
+    {
+      "epoch": 100.0,
+      "eval_loss": 6.550197895194287e-07,
+      "eval_runtime": 0.3302,
+      "eval_samples_per_second": 109.012,
+      "eval_steps_per_second": 15.141,
+      "step": 4000
     }
   ],
   "logging_steps": 10,
@@ -3607,12 +3629,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.6756598975863194e+17,
+  "total_flos": 1.684080299081728e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null