Training in progress, step 1300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b98adbb6b3410bc2c57c920f9bbcd7a3ac28b282b30b139fffda0964c475269
+oid sha256:c43d17a0b6473ddf0c1ed312c5ee7d8274ece66ae8189e895d85d3a7735a8650
 size 6304192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c125db7b2fe970a833bc15fed3b33ab9955d790ae3bf05c3d600a43d97ac273
+oid sha256:afa39228be4f719cfe727599c80ea835aecea082d8739066d22f86bbaf841294
 size 12639429

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2479d85779f408734c43086390c11d46c003cabf0a9fda602c9204c5d6de6353
+oid sha256:10d88b02080a0ea2c4b84decc15320ceeac831f11b262b68b63536132f618e5a
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f5f3a2d7191245a70e1410d8951fd2f5c94b0b91f13bf39c3f76fe8aaf57fd4
+oid sha256:d52a4d67627993645e1cea71ef09276f4b0a2f5bba92959ce9a1a76893653978
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.260953664779663,
-  "best_model_checkpoint": "./outputs/checkpoint-1100",
-  "epoch": 1.4666666666666668,
+  "best_metric": 1.2555885314941406,
+  "best_model_checkpoint": "./outputs/checkpoint-1300",
+  "epoch": 1.7333333333333334,
   "eval_steps": 100,
-  "global_step": 1100,
+  "global_step": 1300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -161,6 +161,34 @@
       "eval_samples_per_second": 15.116,
       "eval_steps_per_second": 1.895,
       "step": 1100
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.0002,
+      "loss": 1.0776,
+      "step": 1200
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 1.2578165531158447,
+      "eval_runtime": 128.6774,
+      "eval_samples_per_second": 14.999,
+      "eval_steps_per_second": 1.881,
+      "step": 1200
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.0002,
+      "loss": 1.0839,
+      "step": 1300
+    },
+    {
+      "epoch": 1.73,
+      "eval_loss": 1.2555885314941406,
+      "eval_runtime": 127.1086,
+      "eval_samples_per_second": 15.184,
+      "eval_steps_per_second": 1.904,
+      "step": 1300
     }
   ],
   "logging_steps": 100,
@@ -168,7 +196,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.899783473241702e+16,
+  "total_flos": 4.608775905574502e+16,
   "trial_name": null,
   "trial_params": null
 }