Training in progress, step 600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8be84b876b24033bd4becf2ef43e447b6c64b69a07961cda4354ecbad3d3d078
+oid sha256:45823c022c8f10ad3153bfe719c7ef94957374e2be3e949f4d648b4b8208cf90
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:988f82b8444f663906c2fd4312c9549060a28eeb1471d941f7aceb77bc3333cd
+oid sha256:be0b1269b8f705ba789c8af8a2b6b676975cfc5f543de3b007d70078fd538f17
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e0d167b9891e530dfce8ffa0ecb74bcb31b42ce9cddaf6bfc22d7ab81a514cd
+oid sha256:5bea72d7bc14392060552e2632922b1efac8f9292c9a40eab92222a0ce3dae64
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5efc416a6883409dd7ab6f5c779e107c7c2baa7af6e12ed9fbd9dd73b8b20784
+oid sha256:9c1a2ac1c11599601eeac95feb1dbfd49ec5c625e61dcce18b3f094491f9cf2d
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.5791709423065186,
-  "best_model_checkpoint": "./outputs/checkpoint-500",
-  "epoch": 0.36429872495446264,
+  "best_metric": 2.5526647567749023,
+  "best_model_checkpoint": "./outputs/checkpoint-600",
+  "epoch": 0.4371584699453552,
   "eval_steps": 100,
-  "global_step": 500,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -77,13 +77,27 @@
       "eval_samples_per_second": 30.608,
       "eval_steps_per_second": 3.83,
       "step": 500
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0002,
+      "loss": 2.5557,
+      "step": 600
+    },
+    {
+      "epoch": 0.44,
+      "eval_loss": 2.5526647567749023,
+      "eval_runtime": 208.5751,
+      "eval_samples_per_second": 30.08,
+      "eval_steps_per_second": 3.764,
+      "step": 600
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.424403231326208e+16,
+  "total_flos": 1.710192402874368e+16,
   "trial_name": null,
   "trial_params": null
 }