Training in progress, step 800, checkpoint

last-checkpoint/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c7175f9b939389b1ffe82369166f106741b940df6ba4f2292d4a8b850b56970
+oid sha256:fc3865a1483cde40a2aa4a7fe92ebf945342be8c269b06978098ccbcc744b16a
 size 50349441

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce81976d3d030f207b15a9236da70e693802271d1c914f8f0223a1a8100360d9
+oid sha256:397c36d5cc09dddb7c7c7df01c2ed02a751d70764be2a8adca2275043181b300
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:451a2106b4c24d69e8c55c73469acc51b69136bb9cd4cc4e5451d1be338a1eaf
+oid sha256:abaef124d8e265d68d5751114b7c7b99ba0eb280d27af45a9884fb7e66277ae9
 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": 1.7120596170425415,
-  "best_model_checkpoint": "./outputs/checkpoint-700",
-  "epoch": 0.5100182149362478,
+  "best_metric": 1.6833879947662354,
+  "best_model_checkpoint": "./outputs/checkpoint-800",
+  "epoch": 0.5828779599271403,
   "eval_steps": 100,
-  "global_step": 700,
+  "global_step": 800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -105,13 +105,27 @@
       "eval_samples_per_second": 43.525,
       "eval_steps_per_second": 5.446,
       "step": 700
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002,
+      "loss": 1.6973,
+      "step": 800
+    },
+    {
+      "epoch": 0.58,
+      "eval_loss": 1.6833879947662354,
+      "eval_runtime": 144.034,
+      "eval_samples_per_second": 43.559,
+      "eval_steps_per_second": 5.45,
+      "step": 800
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 4.174060032521011e+16,
+  "total_flos": 4.770964776085094e+16,
   "trial_name": null,
   "trial_params": null
 }