Training in progress, step 700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:418ae8a1056f82c7cb8c1f8d06fbd00d37e4d693eb0f84eddeeb12f931bd07b2
+oid sha256:b48d88d84faf01890db2155447ac959a5885868161d2be46584cc6de411e88dc
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e45f536f153b81db23498208022104ab4ab3fbd27e46839ebfcbe08b05b63a68
+oid sha256:6b9a6ce0cdf232b7504a6caca88c93917f9db12c54afd8275db3c49218493c0b
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bea72d7bc14392060552e2632922b1efac8f9292c9a40eab92222a0ce3dae64
+oid sha256:4933eabcc84eee1438f9d6f8169b5cecd886b53e4de0afe6e5bf4f525371b890
 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": 2.552586555480957,
-  "best_model_checkpoint": "./outputs/checkpoint-600",
-  "epoch": 0.4371584699453552,
+  "best_metric": 2.527393341064453,
+  "best_model_checkpoint": "./outputs/checkpoint-700",
+  "epoch": 0.5100182149362478,
   "eval_steps": 100,
-  "global_step": 600,
+  "global_step": 700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -91,13 +91,27 @@
       "eval_samples_per_second": 30.674,
       "eval_steps_per_second": 3.838,
       "step": 600
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0002,
+      "loss": 2.5368,
+      "step": 700
+    },
+    {
+      "epoch": 0.51,
+      "eval_loss": 2.527393341064453,
+      "eval_runtime": 204.8117,
+      "eval_samples_per_second": 30.633,
+      "eval_steps_per_second": 3.833,
+      "step": 700
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.710192402874368e+16,
+  "total_flos": 1.993348357668864e+16,
   "trial_name": null,
   "trial_params": null
 }