Training in progress, step 100, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a845c37c43ad9337b2921423d609a972ceaae5b1912f8ef370db95fce81ed3e
+oid sha256:04c2e4755acfcc66aa21c36f660bab6e9c0522884c8dfc3e01bf29fb889dd2b2
 size 250490408

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2a69423bd2f85a3cb77effdb9583e4539e6b3e63bc98bd5f6bec4e02bc44df4
+oid sha256:cf855f526c2baeae61a5407f698fc194d44acb4c56958d91435bf8e3ec014180
 size 255265850

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22171af70cffee5f380e1336353e06904e40202cafcf0b44991e820c034f9a1d
+oid sha256:9d8ec3545b76ac71f41d21727701a3d87f460097098e8138aa16b13c3dd2fc3e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:814445e8c97a1d090f0500a145fa38cc3b150850d76a622c09dc8d7720d6070b
+oid sha256:96cd719805ad13610164e69f3ed856b75110c72d1c0d2a84ad11ade297409c85
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ceb997af1461f413df7026c0297eec218ef5efb08cee2d5237d66f270eb535e
+oid sha256:65e9460bf57e8621d5c8825f686824afc4baeffe3beb03ad34e254f7b85bccd7
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d88b7788659022a87572b128e431cdef971fa16742897741033f21525c1d5c8
+oid sha256:e1c7bd565c921255ceb6b55c4940901b726a42c50280268071e867e96f607b89
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c420644371984c0c279fff13e73e1c3067315dc564ce90ee02e2ca237d8a9e35
+oid sha256:3a60c7d771c1fd156acee762fba03c724cb41829a3f71df370ecd1d20b134982
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 13.333333333333334,
+  "epoch": 16.666666666666668,
   "eval_steps": 20,
-  "global_step": 80,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -103,6 +103,28 @@
       "eval_samples_per_second": 277.061,
       "eval_steps_per_second": 2.215,
       "step": 80
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 3.046875,
+      "learning_rate": 5.418275829936537e-06,
+      "loss": 4.4608,
+      "step": 90
+    },
+    {
+      "epoch": 16.666666666666668,
+      "grad_norm": 1.7734375,
+      "learning_rate": 0.0,
+      "loss": 4.4609,
+      "step": 100
+    },
+    {
+      "epoch": 16.666666666666668,
+      "eval_loss": 3.212986707687378,
+      "eval_runtime": 5.3548,
+      "eval_samples_per_second": 280.31,
+      "eval_steps_per_second": 2.241,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -117,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.0372248846204928e+16,
+  "total_flos": 1.2971582112661504e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null