Training in progress, step 800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93c99d345c0bb6c0f21f62c3f6648742993640d5fe8198292d8cf36a639cb9bc
+oid sha256:cc8a717d7936bc5b8f311f71f62874984905d4d47f58fdda4f6aa5e4898edf85
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8967f7b452f21e53c2e9d636961f8bd59e4ca605765bbd738d7706fbe60a788
+oid sha256:e9f70ce29e1e782a7f4b7ff70d7274a0e5fbf58bb7c6997e990772cf3df7ad27
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32b417cb034f8363f099f00b2d6eae2103541ebb0f2806afcc68eb0fbd986563
+oid sha256:2c92b486b14f7a50cc9e7e571422ae87d331c417b0c0a958af23c536241b187d
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30423cc69a1c7d18caef4643847588d5884db012263cbe7b7224fa4719ca4156
+oid sha256:de7840bcb72f2f480fd301578d289cdfa174589e831b0d33e5772f3956b6beae
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.9850085973739624,
-  "best_model_checkpoint": "./outputs/checkpoint-700",
-  "epoch": 0.9943181818181818,
+  "best_metric": 1.9744948148727417,
+  "best_model_checkpoint": "./outputs/checkpoint-800",
+  "epoch": 1.1363636363636362,
   "eval_steps": 100,
-  "global_step": 700,
+  "global_step": 800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -105,6 +105,20 @@
       "eval_samples_per_second": 27.841,
       "eval_steps_per_second": 3.49,
       "step": 700
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.0002,
+      "loss": 2.1122,
+      "step": 800
+    },
+    {
+      "epoch": 1.14,
+      "eval_loss": 1.9744948148727417,
+      "eval_runtime": 53.6175,
+      "eval_samples_per_second": 27.827,
+      "eval_steps_per_second": 3.488,
+      "step": 800
     }
   ],
   "logging_steps": 100,
@@ -112,7 +126,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.11870781595648e+16,
+  "total_flos": 2.424565849208832e+16,
   "trial_name": null,
   "trial_params": null
 }