Training in progress, step 700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e0f0f7d4c470e915eb2fafa01dff3de3771d0db50cf82273dc589da9bdd6d56
+oid sha256:0f0305d08d5cbbc629e59224a65cf405b777ea90413ed7fc95d7420d5f67da69
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:069e1e1d7d9896b15bfdcf354ae50c5e10727699cfca8c14f194fc1fd4d7bff7
+oid sha256:c2cea027fb58f2463a20aa97ae02012e9d4a1f7296e05f3aff80cbbc44b0e40f
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dd42064bd4fb4eec8036fb285c03c704810bfb9590c79f20aac0cfa140f4e28
+oid sha256:2a7aea1bef86b1056125513432a9481c64077b07ee990116c26b3bfaebd6be37
 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": 1.1658653020858765,
-  "best_model_checkpoint": "./outputs/checkpoint-600",
-  "epoch": 0.8,
+  "best_metric": 1.1600923538208008,
+  "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": 10.873,
       "eval_steps_per_second": 1.363,
       "step": 600
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0002,
+      "loss": 0.9654,
+      "step": 700
+    },
+    {
+      "epoch": 0.93,
+      "eval_loss": 1.1600923538208008,
+      "eval_runtime": 177.776,
+      "eval_samples_per_second": 10.856,
+      "eval_steps_per_second": 1.361,
+      "step": 700
     }
   ],
   "logging_steps": 100,
@@ -98,7 +112,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 4.481983825772544e+16,
+  "total_flos": 5.2320035432448e+16,
   "trial_name": null,
   "trial_params": null
 }