Training in progress, step 1200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fc67d0b39f261767da8740cf81c62338043bd400a41e5d2dba4f79946e9aa2a
+oid sha256:a5227e6151cea8b3a502805637c2eec55a5caaa66dfa55b60c22d921e6dccd5c
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25335ec184d7e735e317fe31510db6c2a789be35a77830a65cb90c68e6650ff0
+oid sha256:312d388fdc45c70d5e646e092ec8e5e08d7c85aa2748d7b7d7fc97593de4089b
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e475523f80935f54ca9dc3a91dba918ff84a0ec6b0829d5b53e18f8d55891544
+oid sha256:cc812a9a0585c12499e2e04e0fa9dc706fcccd59e7fbc41a4c4c31a095960052
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f5f3a2d7191245a70e1410d8951fd2f5c94b0b91f13bf39c3f76fe8aaf57fd4
+oid sha256:3d8d6be7898f87772ccbc5c732e900fe63a643c4595ce6af3d6bc6f811ba4b65
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3308976888656616,
-  "best_model_checkpoint": "./outputs/checkpoint-1100",
-  "epoch": 1.4666666666666668,
+  "best_metric": 1.3270059823989868,
+  "best_model_checkpoint": "./outputs/checkpoint-1200",
+  "epoch": 1.6,
   "eval_steps": 100,
-  "global_step": 1100,
+  "global_step": 1200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -161,6 +161,20 @@
       "eval_samples_per_second": 12.919,
       "eval_steps_per_second": 1.62,
       "step": 1100
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.0002,
+      "loss": 1.0816,
+      "step": 1200
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 1.3270059823989868,
+      "eval_runtime": 112.5104,
+      "eval_samples_per_second": 12.897,
+      "eval_steps_per_second": 1.618,
+      "step": 1200
     }
   ],
   "logging_steps": 100,
@@ -168,7 +182,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 6.99522709745664e+16,
+  "total_flos": 7.628242252087296e+16,
   "trial_name": null,
   "trial_params": null
 }