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:db32e050ad76c866b28528b01a82e917698b0c3bd139e7845cc8ce7e901bcd7a
+oid sha256:64fdbe98ea9ff1aaa3934406d079f6e9f6edfb8b0f995ab001a7a5996589a6a8
 size 12595704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37cf3999163e56b211cd8686ee5dcc09ee1c475bb1cd0cad992b7779e83f7ce9
+oid sha256:ef8f119f447683c354fd7c289dd1b1e4d72a72bc752770a750352926a8472a43
 size 25222341

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1be18b8e1675453c1ec73a72d48498d1f8a280178cb411b90876e8ee648f603a
+oid sha256:97f421960082621eb5d18a65ca61753285f8400dd4a46495b865c4b2f5f1806c
 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": 1.107673168182373,
-  "best_model_checkpoint": "./outputs/checkpoint-700",
-  "epoch": 0.9333333333333333,
+  "best_metric": 1.103180170059204,
+  "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": 8.08,
       "eval_steps_per_second": 1.013,
       "step": 700
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0002,
+      "loss": 0.9532,
+      "step": 800
+    },
+    {
+      "epoch": 1.07,
+      "eval_loss": 1.103180170059204,
+      "eval_runtime": 531.86,
+      "eval_samples_per_second": 3.629,
+      "eval_steps_per_second": 0.455,
+      "step": 800
     }
   ],
   "logging_steps": 100,
@@ -112,7 +126,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 9.898653051450163e+16,
+  "total_flos": 1.130969014206382e+17,
   "trial_name": null,
   "trial_params": null
 }