Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fba258da8d17699e1921848723f46c99c943cd889cf70514c98d6efbe53abb69
+oid sha256:e627017a49bc4863d2d88041d6a4b346b1b510721a0d304c5904d10f4d3f5686
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e80b4a79a792f81accd6205b337f219be78befc6eba04182ff062997fa8c775
+oid sha256:b677c433fe39e753e53e39715b3ea732c8ca1361009cc36be340a875e348f0c1
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:def413155bb0129590bbc51f05743e4908c7b52782173d41ef46bfe863ef46d5
+oid sha256:16c7f7133cb41e4c7f58ad848fed2fb893c76880e5c42ef87bba992b08ea7012
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd18e5325bf99a4b662a5314e5f491b65903ffc83b0317f63835d8305a50591e
+oid sha256:4ec0bb6efeeb25000ef7426abb9d88265daa212fa2a170e1fb3f58996efa27f6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.003731473815548585,
+  "epoch": 0.004197908042492158,
   "eval_steps": 5,
-  "global_step": 40,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -170,6 +170,28 @@
       "eval_samples_per_second": 16.019,
       "eval_steps_per_second": 4.005,
       "step": 40
+    },
+    {
+      "epoch": 0.003918047506326014,
+      "grad_norm": 1.5312135219573975,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.8295,
+      "step": 42
+    },
+    {
+      "epoch": 0.004197908042492158,
+      "grad_norm": 1.5169057846069336,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.9098,
+      "step": 45
+    },
+    {
+      "epoch": 0.004197908042492158,
+      "eval_loss": 0.8880054950714111,
+      "eval_runtime": 1127.4078,
+      "eval_samples_per_second": 16.015,
+      "eval_steps_per_second": 4.004,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -189,7 +211,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.896629160148992e+16,
+  "total_flos": 5.50981865570304e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null