Training in progress, step 17, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f34852b64327509c6719a0ba9c958e37d74df9a1a5223f3b4a772a7ffeab0b4
+oid sha256:c7c851e06731b0ecbaed25e4c2fb3fac377510945b256c52fb23e16128eff133
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91008858bc4f68950e73897c7142d989181b2126363548c3ab4bbceceef6b473
+oid sha256:50c62e17ff7a779b067f2e839a60f85e5220616b068329703b4afb8349f2fcbb
 size 25986148

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d208fc8ffc06a5de0e78a66250af5e4040febbcf16cdc254af2f5493300ac1c9
+oid sha256:52c25a94052779e54eb2ff5e9802cbfca09cefd84adaa1bc9ddc06d4e032cd8b
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:171729bc4986a9839636ee98592d71f8b00583a8eaabd1d63cf9d7610cef9d8e
+oid sha256:2a5fd4d1c60e38cc53dbc0d8c872a89b8dc601dc955555ed8af3b98f3a59f082
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e28a9e95efff5f4fdbdab6994e651e446586624a0f8b61ff953351f9ace2fd28
+oid sha256:1ee4472987825b5a3aa9ff4e10a00e5b3f5b492f3a84b3cca905282446f0b840
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a87f5e3936866d69d87c5ebfdc7bf0d96d0c6bd727c3a6dbd5f5cb4c98ccb1ee
+oid sha256:114a17c71aa68a99d88356dcda21ef219223ee4093c86fc7c6224f2e5c423f50
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99817fbab47484f57146aab5db5d1d20950343ead7ff360b6f6af4b55cb9d971
+oid sha256:a919a23e6215f96d02ffed7d2d944bf660cff5b83a019b5b420707794f63db8b
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd6d7b5374da01deb55707ef3ca400e859d43ff9196f00ccd1413b068442c0ac
+oid sha256:49b47025cd1aa2fad2f43267bfc10b85200961aa9c04bf2a3762a049568443bf
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c436452d7af3913a771cc03d673e6c05ed368a9b1cf6d0e23e1bfe1832a5e7c
+oid sha256:d29a6f1b626ebfc901f92cf6f704afd6a00ba416653ba725093467244b876197
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f09039d225663348fb992c94c210c08e9332bf92c2e8818ce5057bb9610639d
+oid sha256:314b04a252b4c00e6b3e5721f66c8d916ddb958e737116660ac389e2ee0667e0
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f193dee591957702c791ef1b0861987f5cc59c358aa6dd7c5c0054f6dbca1910
+oid sha256:4361bd413ec5a87c7dfd652089f4b23c8fabc62b257574cbf6fe71d1b80db5dc
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9230769230769231,
+  "epoch": 1.0461538461538462,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 17,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,20 @@
       "eval_samples_per_second": 93.513,
       "eval_steps_per_second": 5.978,
       "step": 15
+    },
+    {
+      "epoch": 0.9846153846153847,
+      "grad_norm": 11.402575492858887,
+      "learning_rate": 4.951556604879048e-06,
+      "loss": 1.5679,
+      "step": 16
+    },
+    {
+      "epoch": 1.0461538461538462,
+      "grad_norm": 26.45924949645996,
+      "learning_rate": 0.0,
+      "loss": 2.5677,
+      "step": 17
     }
   ],
   "logging_steps": 1,
@@ -158,12 +172,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 9.881940211531776e+16,
+  "total_flos": 1.1199532239736013e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null