Training in progress, step 1200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:828d4a90a79926476ae1bc4aa6d764727385375199b4b2038fbb746b89774971
+oid sha256:e6b4157f2aea3bc9b9cabc443b31cdde0c6d2946d316cdd060d44eadb89f6056
 size 6304192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bd31f6a42e09c33577d0850b11db6765f299aa35c2fdf36ab9191122e21e7d5
+oid sha256:63f182ba5fd94a974506ce0ab7766bf19dc6b19529737bc9bbea0e6eb9c1e226
 size 12639429

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2479d85779f408734c43086390c11d46c003cabf0a9fda602c9204c5d6de6353
+oid sha256:a96a582389e353e413577cf32a9dd9c3f569b7fd8a5bd42d698d00b47bfced1c
 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": 1.2609761953353882,
-  "best_model_checkpoint": "./outputs/checkpoint-1100",
-  "epoch": 1.4666666666666668,
+  "best_metric": 1.2579678297042847,
+  "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": 15.223,
       "eval_steps_per_second": 1.909,
       "step": 1100
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.0002,
+      "loss": 1.0775,
+      "step": 1200
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 1.2579678297042847,
+      "eval_runtime": 126.3602,
+      "eval_samples_per_second": 15.274,
+      "eval_steps_per_second": 1.915,
+      "step": 1200
     }
   ],
   "logging_steps": 100,
@@ -168,7 +182,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.899783473241702e+16,
+  "total_flos": 4.253905911733862e+16,
   "trial_name": null,
   "trial_params": null
 }