Training in progress, step 700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77b70d671075a6eb8f5d91717351d379473610431e93a8a92edc067ccd5da237
+oid sha256:38ecb0e7e871d247340910e9c43dc76ecf1f1f7fb9caab19a424362d56858048
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:070d46375484b81e21c9182b9ae1c2f6b8b145cf4cea5e735e449e333ecf3790
+oid sha256:da9e98f3e8018ef9402f8bed7bad02205b0d0d4167f1c684c350e8463b92c7bd
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11b4ab10147dbc1307ad06bf0937a764f0221849caa4b93328a8e07e14712e43
+oid sha256:43a6492d1b5c194543f2b211b57f9ad8cc03582b9b8fe48eb7a61392100f57c6
 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": 1.3736246824264526,
-  "best_model_checkpoint": "./outputs/checkpoint-600",
-  "epoch": 0.8,
+  "best_metric": 1.3629770278930664,
+  "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": 12.91,
       "eval_steps_per_second": 1.619,
       "step": 600
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0002,
+      "loss": 1.1305,
+      "step": 700
+    },
+    {
+      "epoch": 0.93,
+      "eval_loss": 1.3629770278930664,
+      "eval_runtime": 112.4413,
+      "eval_samples_per_second": 12.905,
+      "eval_steps_per_second": 1.619,
+      "step": 700
     }
   ],
   "logging_steps": 100,
@@ -98,7 +112,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.82117742641152e+16,
+  "total_flos": 4.455201325768704e+16,
   "trial_name": null,
   "trial_params": null
 }