Training in progress, step 1300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6b4157f2aea3bc9b9cabc443b31cdde0c6d2946d316cdd060d44eadb89f6056
+oid sha256:1f20a1448c3bbe23e17710008e2ab7dd87a78860043a1298bffde318d5880473
 size 6304192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63f182ba5fd94a974506ce0ab7766bf19dc6b19529737bc9bbea0e6eb9c1e226
+oid sha256:82437dee397761c24a5f8cb76a9d6a14d0434486dd10c6571592090abc979f1e
 size 12639429

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a96a582389e353e413577cf32a9dd9c3f569b7fd8a5bd42d698d00b47bfced1c
+oid sha256:10d88b02080a0ea2c4b84decc15320ceeac831f11b262b68b63536132f618e5a
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d8d6be7898f87772ccbc5c732e900fe63a643c4595ce6af3d6bc6f811ba4b65
+oid sha256:d52a4d67627993645e1cea71ef09276f4b0a2f5bba92959ce9a1a76893653978
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2579678297042847,
-  "best_model_checkpoint": "./outputs/checkpoint-1200",
-  "epoch": 1.6,
+  "best_metric": 1.2565162181854248,
+  "best_model_checkpoint": "./outputs/checkpoint-1300",
+  "epoch": 1.7333333333333334,
   "eval_steps": 100,
-  "global_step": 1200,
+  "global_step": 1300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -175,6 +175,20 @@
       "eval_samples_per_second": 15.274,
       "eval_steps_per_second": 1.915,
       "step": 1200
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.0002,
+      "loss": 1.0837,
+      "step": 1300
+    },
+    {
+      "epoch": 1.73,
+      "eval_loss": 1.2565162181854248,
+      "eval_runtime": 126.7636,
+      "eval_samples_per_second": 15.225,
+      "eval_steps_per_second": 1.909,
+      "step": 1300
     }
   ],
   "logging_steps": 100,
@@ -182,7 +196,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 4.253905911733862e+16,
+  "total_flos": 4.608775905574502e+16,
   "trial_name": null,
   "trial_params": null
 }