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:a44d68c1949cbfa59abba3d2625ffd3f2dc2128805ada225747c9f01902b68b6
+oid sha256:03eb44e9094128238da87898552bab191fc68ed5a4dceb0b3dbac97f84a66881
 size 12595704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4339f6bb7269a28cdea90b720694f12d2231e01b41800a39f7f397cee6dd728
+oid sha256:9df58cf4ea3115d266c58f0aa7ca7719e3ec8db32c15979d69ff3a4ca1436732
 size 25222341

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa973b75275daf4d11c1e648510112ae79c2a7760fe20777b3adc73ea7118cb9
+oid sha256:eb71876f27f3a3887b197fb59dafcc8efc45a24e2f5dff6f12d568629a8f4919
 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": 1.1161261796951294,
-  "best_model_checkpoint": "./outputs/checkpoint-500",
-  "epoch": 0.6666666666666666,
+  "best_metric": 1.111202597618103,
+  "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": 10.335,
       "eval_steps_per_second": 1.296,
       "step": 500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0002,
+      "loss": 0.9675,
+      "step": 600
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 1.111202597618103,
+      "eval_runtime": 186.3885,
+      "eval_samples_per_second": 10.355,
+      "eval_steps_per_second": 1.298,
+      "step": 600
     }
   ],
   "logging_steps": 100,
@@ -84,7 +98,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 7.068751460568269e+16,
+  "total_flos": 8.4807475288277e+16,
   "trial_name": null,
   "trial_params": null
 }