Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e0a9c71cd47c0e98e4df8a7e78f4b523fcd607377b8ca17db6e416015c3207f
+oid sha256:1f20e8f6be8ed2a027ac1ac173ba7c8f1398af53659e9c490d959f3b83f6e4eb
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62ade698410c7671fb365897251dba414c6a38da64f7d2134b76611ae3967174
+oid sha256:bd8b2277cc8e4a8252c6aa6de8b222268999f3c54fc6ec0ff391a62041e28699
 size 25986148

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b21341e28491e7519aa247a7900dde9ffa5bc444ad819877747c1cba8a2f246
+oid sha256:d7a5475a895beefd8e88792279bc7b9824ecdee79a3346daf854c89ea9d51ba2
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69ae5e0ac083cbd6919e32143a287b06120b3d4d3cefddc87a84a5a2240ee75a
+oid sha256:ff1d8702bb6011415533922894e39f5667dd644c48a3e176012aad15745aeeb3
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e59a7c6fcdbe021eb09a9b26ec2b45b55030c986399c9694fff97c95b645c400
+oid sha256:47b94deb6488a8ea2970de89e038b0b413c39f429bdfe25e64a990f2bac72ad2
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c01e7d96866ffb2310854fcb4f079a0cd8597ced3b2cd3eb4cea82a53748202
+oid sha256:b3a2331dd8a80581bf12ca2c2221d19c51c14d59789f85fbb3c4e57fd806793d
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:789b5ac6a3d26da907edb51db958ba71233b76a160341b9ee57b430ce74531e6
+oid sha256:7eadb0c710a5dc30d6df8c49dcc0e753d1737144f4972cee4fe942e58cf212fb
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91edd18fb81e0ac338bab59cc220719cc869b33d86ada4ae9588d0548376122c
+oid sha256:2d578ccb511f4a759fe54a960f06d0c3a34e652db1c51c7cd0ba4ba68a96ae60
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f3c1c4cc28dd44ba1817dffea22d63df2cc40ceac5849d28972cf3ae287c3d4
+oid sha256:99d44679f089a93f2fac43fc1eda9e52f9a15a49d7c099fce2fbfe1ca76b7e6c
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f4d82c554fbc426dbdfa4a4ba0d2eda37c9813afb5b4534eea5b76764acddac
+oid sha256:a1927bd520aba17e0716a8a52fd79f8e24f9c9944a5db3f51284d8b4d78fd3cd
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff2736979009751c0c6b0ddcc5f6544d6f723aa752b4798eab0b70fb76cf0083
+oid sha256:532138a5ca880d8da393ae449e5715b2766def36b8838785ca08d07228b119b7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01862341894932878,
+  "epoch": 0.02483122526577171,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 90.047,
       "eval_steps_per_second": 11.268,
       "step": 15
+    },
+    {
+      "epoch": 0.019864980212617366,
+      "grad_norm": 0.2886999845504761,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.8474,
+      "step": 16
+    },
+    {
+      "epoch": 0.021106541475905953,
+      "grad_norm": 0.31647738814353943,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.7155,
+      "step": 17
+    },
+    {
+      "epoch": 0.022348102739194537,
+      "grad_norm": 1.7367758750915527,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.881,
+      "step": 18
+    },
+    {
+      "epoch": 0.02358966400248312,
+      "grad_norm": 0.30022862553596497,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.7167,
+      "step": 19
+    },
+    {
+      "epoch": 0.02483122526577171,
+      "grad_norm": 0.33463653922080994,
+      "learning_rate": 0.0,
+      "loss": 0.7163,
+      "step": 20
+    },
+    {
+      "epoch": 0.02483122526577171,
+      "eval_loss": NaN,
+      "eval_runtime": 60.2868,
+      "eval_samples_per_second": 90.003,
+      "eval_steps_per_second": 11.263,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -158,12 +201,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.940970105765888e+16,
+  "total_flos": 6.587960141021184e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null