Training in progress, step 800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e40bdc465bd535c2783d83b251b11b8e98f4bcffb0e1344c3ae38edebee3157
+oid sha256:becce76969faf3f4e3718c070b9df777a2bd1d13106aad62e2f01b884d4991bf
 size 6304192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d15bff77fecf2dc44840050851feef036cd519494e0898cc0e60b1a49435590b
+oid sha256:5b2da5f561ff4a1116124cc807648f7a863100329832fa6b09e31d9b911adb28
 size 12639429

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd8dd7793a5701b64cff4ece571f2d331ce025868e37b09362177387e1ab6cc1
+oid sha256:a44e67e7afe750fe86df1f191491956aa5374ed00de2fe34a89e159730d72861
 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": 1.2776304483413696,
-  "best_model_checkpoint": "./outputs/checkpoint-700",
-  "epoch": 0.9333333333333333,
+  "best_metric": 1.2741276025772095,
+  "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": 15.189,
       "eval_steps_per_second": 1.905,
       "step": 700
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0002,
+      "loss": 1.0976,
+      "step": 800
+    },
+    {
+      "epoch": 1.07,
+      "eval_loss": 1.2741276025772095,
+      "eval_runtime": 127.4814,
+      "eval_samples_per_second": 15.139,
+      "eval_steps_per_second": 1.898,
+      "step": 800
     }
   ],
   "logging_steps": 100,
@@ -112,7 +126,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.482400846458061e+16,
+  "total_flos": 2.836263099222835e+16,
   "trial_name": null,
   "trial_params": null
 }