Training in progress, step 700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e7e2e40e27050790b1c4e75f4c627fee80ef7597256773af76800687e1ce61c
+oid sha256:db32e050ad76c866b28528b01a82e917698b0c3bd139e7845cc8ce7e901bcd7a
 size 12595704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:194495552fd48659d5d22bbaee88398a59b7fc814d12748a03571f82b098415b
+oid sha256:37cf3999163e56b211cd8686ee5dcc09ee1c475bb1cd0cad992b7779e83f7ce9
 size 25222341

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb71876f27f3a3887b197fb59dafcc8efc45a24e2f5dff6f12d568629a8f4919
+oid sha256:1be18b8e1675453c1ec73a72d48498d1f8a280178cb411b90876e8ee648f603a
 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": 1.1117215156555176,
-  "best_model_checkpoint": "./outputs/checkpoint-600",
-  "epoch": 0.8,
+  "best_metric": 1.107673168182373,
+  "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": 10.31,
       "eval_steps_per_second": 1.293,
       "step": 600
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0002,
+      "loss": 0.9639,
+      "step": 700
+    },
+    {
+      "epoch": 0.93,
+      "eval_loss": 1.107673168182373,
+      "eval_runtime": 238.8707,
+      "eval_samples_per_second": 8.08,
+      "eval_steps_per_second": 1.013,
+      "step": 700
     }
   ],
   "logging_steps": 100,
@@ -98,7 +112,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 8.4807475288277e+16,
+  "total_flos": 9.898653051450163e+16,
   "trial_name": null,
   "trial_params": null
 }