Training in progress, step 700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03eb44e9094128238da87898552bab191fc68ed5a4dceb0b3dbac97f84a66881
+oid sha256:21a36c705e0f208c931506b65183bb9794b3e3f1c84edfc542435b64fda27e8d
 size 12595704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9df58cf4ea3115d266c58f0aa7ca7719e3ec8db32c15979d69ff3a4ca1436732
+oid sha256:ca4c07fbe4f1b8ef8f0919fe2ef0968691f6aa757daf928240261b85febe1179
 size 25222341

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb71876f27f3a3887b197fb59dafcc8efc45a24e2f5dff6f12d568629a8f4919
+oid sha256:1be18b8e1675453c1ec73a72d48498d1f8a280178cb411b90876e8ee648f603a
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c1a2ac1c11599601eeac95feb1dbfd49ec5c625e61dcce18b3f094491f9cf2d
+oid sha256:30423cc69a1c7d18caef4643847588d5884db012263cbe7b7224fa4719ca4156
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.111202597618103,
-  "best_model_checkpoint": "./outputs/checkpoint-600",
-  "epoch": 0.8,
+  "best_metric": 1.1068408489227295,
+  "best_model_checkpoint": "./outputs/checkpoint-700",
+  "epoch": 0.9333333333333333,
   "eval_steps": 100,
-  "global_step": 600,
+  "global_step": 700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -91,6 +91,20 @@
       "eval_samples_per_second": 10.355,
       "eval_steps_per_second": 1.298,
       "step": 600
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0002,
+      "loss": 0.9638,
+      "step": 700
+    },
+    {
+      "epoch": 0.93,
+      "eval_loss": 1.1068408489227295,
+      "eval_runtime": 186.3328,
+      "eval_samples_per_second": 10.358,
+      "eval_steps_per_second": 1.299,
+      "step": 700
     }
   ],
   "logging_steps": 100,
@@ -98,7 +112,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 8.4807475288277e+16,
+  "total_flos": 9.898653051450163e+16,
   "trial_name": null,
   "trial_params": null
 }