Training in progress, step 800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b363b1d8327f0083d70b911bbc386bded569428aca9aa74f00aa73cde23ec71
+oid sha256:52541ac2bf3ec9fc8ecf2d563913fe644dffe290994b699d58dc9269b1d1accc
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32a48f69204be59c1cac87a11a7af4b80efc60b9cc109ad7c7e98d130115fb5a
+oid sha256:2e713f1111b25bc9d0b57686bd301067dc2dc7b8db459df4165bdb18ec1158e7
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec86ceb8d74fcdb02c7a500faa95db56c309f6ef4f9b4535c3180da9cf2b8f32
+oid sha256:f988a87c292524c83b21ea4c41795c72510e2df27e6988755709c4cf8287a8ef
 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": 1.455640435218811,
-  "best_model_checkpoint": "./outputs/checkpoint-700",
-  "epoch": 0.9333333333333333,
+  "best_metric": 1.446093201637268,
+  "best_model_checkpoint": "./outputs/checkpoint-800",
+  "epoch": 1.0666666666666667,
   "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": 15.521,
       "eval_steps_per_second": 1.947,
       "step": 700
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0002,
+      "loss": 1.2091,
+      "step": 800
+    },
+    {
+      "epoch": 1.07,
+      "eval_loss": 1.446093201637268,
+      "eval_runtime": 93.3855,
+      "eval_samples_per_second": 15.538,
+      "eval_steps_per_second": 1.949,
+      "step": 800
     }
   ],
   "logging_steps": 100,
@@ -112,7 +126,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 4.094671702818816e+16,
+  "total_flos": 4.677188212150272e+16,
   "trial_name": null,
   "trial_params": null
 }