Training in progress, step 1950, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bfdae32dcb0649e9b6181d28f56452309d6ccd5e9baa4277ab4f62d2c4d1d80
+oid sha256:e8442e92131e813ad779f2e5ae1738b36bb12dfa25c65cc43cd254c7aa1ebfb5
 size 457872944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b9fcea2908dd4a519879ba1fc9feed289c05701d2902b54237248ade2af5861
+oid sha256:54db9d4a05e37e1ffabfb46252585a89e74384915ec6e7f08b4aa6f212520050
 size 906655482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d8872471717f433968474073c4ebf4bc1b3a47efb0c26462b67fedcf37cefdb
+oid sha256:d028195f91f8f2da375afd5c8611226c3f441d4eab18dd3d9c58776f6e4ad297
 size 14180

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2760d17b439f8ea889c9a58cfe3005f72c6e199a9c6e96f0f7dd483d869f42ba
+oid sha256:a1fd2596562ccd88417cda1ce7310479ebb8edf0f8c5a343fa492c5fa64814ee
 size 1256

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.529088020324707,
   "best_model_checkpoint": "./output/checkpoint-1050",
-  "epoch": 5.09915014164306,
+  "epoch": 5.524079320113314,
   "eval_steps": 150,
-  "global_step": 1800,
+  "global_step": 1950,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1363,6 +1363,119 @@
       "eval_samples_per_second": 9.733,
       "eval_steps_per_second": 9.733,
       "step": 1800
+    },
+    {
+      "epoch": 5.127478753541077,
+      "grad_norm": 6.307571887969971,
+      "learning_rate": 3.094997749385071e-05,
+      "loss": 0.0484,
+      "step": 1810
+    },
+    {
+      "epoch": 5.1558073654390935,
+      "grad_norm": 4.0599684715271,
+      "learning_rate": 3.0828615953126175e-05,
+      "loss": 0.0364,
+      "step": 1820
+    },
+    {
+      "epoch": 5.18413597733711,
+      "grad_norm": 1.6084905862808228,
+      "learning_rate": 3.0706860448208514e-05,
+      "loss": 0.0375,
+      "step": 1830
+    },
+    {
+      "epoch": 5.212464589235127,
+      "grad_norm": 3.262603759765625,
+      "learning_rate": 3.058471598398967e-05,
+      "loss": 0.0508,
+      "step": 1840
+    },
+    {
+      "epoch": 5.240793201133145,
+      "grad_norm": 2.902472972869873,
+      "learning_rate": 3.0462187581350132e-05,
+      "loss": 0.0685,
+      "step": 1850
+    },
+    {
+      "epoch": 5.269121813031162,
+      "grad_norm": 1.6740124225616455,
+      "learning_rate": 3.033928027695265e-05,
+      "loss": 0.0568,
+      "step": 1860
+    },
+    {
+      "epoch": 5.2974504249291785,
+      "grad_norm": 5.76546573638916,
+      "learning_rate": 3.021599912303509e-05,
+      "loss": 0.0706,
+      "step": 1870
+    },
+    {
+      "epoch": 5.325779036827195,
+      "grad_norm": 4.644334316253662,
+      "learning_rate": 3.009234918720284e-05,
+      "loss": 0.062,
+      "step": 1880
+    },
+    {
+      "epoch": 5.354107648725212,
+      "grad_norm": 2.3427531719207764,
+      "learning_rate": 2.9968335552220465e-05,
+      "loss": 0.0529,
+      "step": 1890
+    },
+    {
+      "epoch": 5.38243626062323,
+      "grad_norm": 5.573881149291992,
+      "learning_rate": 2.9843963315802763e-05,
+      "loss": 0.065,
+      "step": 1900
+    },
+    {
+      "epoch": 5.410764872521247,
+      "grad_norm": 1.00111985206604,
+      "learning_rate": 2.9719237590405247e-05,
+      "loss": 0.0458,
+      "step": 1910
+    },
+    {
+      "epoch": 5.4390934844192635,
+      "grad_norm": 9.30931282043457,
+      "learning_rate": 2.959416350301396e-05,
+      "loss": 0.0665,
+      "step": 1920
+    },
+    {
+      "epoch": 5.46742209631728,
+      "grad_norm": 2.9437053203582764,
+      "learning_rate": 2.946874619493476e-05,
+      "loss": 0.0539,
+      "step": 1930
+    },
+    {
+      "epoch": 5.495750708215297,
+      "grad_norm": 6.750890254974365,
+      "learning_rate": 2.9342990821581955e-05,
+      "loss": 0.0574,
+      "step": 1940
+    },
+    {
+      "epoch": 5.524079320113314,
+      "grad_norm": 3.0086891651153564,
+      "learning_rate": 2.9216902552266397e-05,
+      "loss": 0.0515,
+      "step": 1950
+    },
+    {
+      "epoch": 5.524079320113314,
+      "eval_loss": 0.7158511281013489,
+      "eval_runtime": 31.532,
+      "eval_samples_per_second": 9.958,
+      "eval_steps_per_second": 9.958,
+      "step": 1950
     }
   ],
   "logging_steps": 10,
@@ -1382,7 +1495,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.689547059086029e+16,
+  "total_flos": 9.410666091714048e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null