Training in progress, step 800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21a36c705e0f208c931506b65183bb9794b3e3f1c84edfc542435b64fda27e8d
+oid sha256:7f7a2c56811085a8befd160ec89fab677e453207d020e32f82920919cdd0c1e8
 size 12595704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca4c07fbe4f1b8ef8f0919fe2ef0968691f6aa757daf928240261b85febe1179
+oid sha256:98defc4369dc5ed5ef6150d824ec69a16d9c8bcff9d62719b0bfcf76183bfb91
 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": 1.1068408489227295,
-  "best_model_checkpoint": "./outputs/checkpoint-700",
-  "epoch": 0.9333333333333333,
+  "best_metric": 1.102936029434204,
+  "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": 10.358,
       "eval_steps_per_second": 1.299,
       "step": 700
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0002,
+      "loss": 0.9531,
+      "step": 800
+    },
+    {
+      "epoch": 1.07,
+      "eval_loss": 1.102936029434204,
+      "eval_runtime": 186.6863,
+      "eval_samples_per_second": 10.338,
+      "eval_steps_per_second": 1.296,
+      "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
 }