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:bd1e4d09eb2419c4b5c4d9da974d153ab051bebe15cd566b81c560f87258feda
+oid sha256:77b70d671075a6eb8f5d91717351d379473610431e93a8a92edc067ccd5da237
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:242f2dbca9744b0128482ac838b792502a16494ad677adea668a7c6898a30a07
+oid sha256:070d46375484b81e21c9182b9ae1c2f6b8b145cf4cea5e735e449e333ecf3790
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4267e22d8a64de946137e693a74aa29d7c65d83f9a227b17a42126683108c273
+oid sha256:11b4ab10147dbc1307ad06bf0937a764f0221849caa4b93328a8e07e14712e43
 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": 1.3869292736053467,
-  "best_model_checkpoint": "./outputs/checkpoint-500",
-  "epoch": 0.6666666666666666,
+  "best_metric": 1.3736246824264526,
+  "best_model_checkpoint": "./outputs/checkpoint-600",
+  "epoch": 0.8,
   "eval_steps": 100,
-  "global_step": 500,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -77,6 +77,20 @@
       "eval_samples_per_second": 12.906,
       "eval_steps_per_second": 1.619,
       "step": 500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0002,
+      "loss": 1.1389,
+      "step": 600
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 1.3736246824264526,
+      "eval_runtime": 112.3926,
+      "eval_samples_per_second": 12.91,
+      "eval_steps_per_second": 1.619,
+      "step": 600
     }
   ],
   "logging_steps": 100,
@@ -84,7 +98,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.186244674256896e+16,
+  "total_flos": 3.82117742641152e+16,
   "trial_name": null,
   "trial_params": null
 }