Training in progress, step 1200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:328e511f2d707a3a5f2e4f3e13b8fca6d5787e0d4b456d94ca6fc144757dbf81
+oid sha256:57989e1fd10b56b2bab72708fbd6d79b6ecad73cf4f91cd5e396a74c212ec955
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7410f2b9e82a61e479380c683e0fe1f478b2937ab33f326d0703465bdee9c579
+oid sha256:a0835ff9d6fab8a0b2490c1330449db90f28256320f9b26781a1f514715699ff
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cdf360eed736a9a453b77189edcc26992b441f5547b33e72ad2bf313f6d61f2
+oid sha256:1aab6ee5ef938a85af4adff67c8efb0931b96509caa2c6ce3bd47b07a26ea0a3
 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": 0.9814682006835938,
-  "best_model_checkpoint": "./outputs/checkpoint-1100",
-  "epoch": 1.5625,
+  "best_metric": 0.9781661033630371,
+  "best_model_checkpoint": "./outputs/checkpoint-1200",
+  "epoch": 1.7045454545454546,
   "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": 12.003,
       "eval_steps_per_second": 1.504,
       "step": 1100
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 0.0002,
+      "loss": 1.1074,
+      "step": 1200
+    },
+    {
+      "epoch": 1.7,
+      "eval_loss": 0.9781661033630371,
+      "eval_runtime": 119.7103,
+      "eval_samples_per_second": 12.463,
+      "eval_steps_per_second": 1.562,
+      "step": 1200
     }
   ],
   "logging_steps": 100,
@@ -168,7 +182,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 6.182618126727168e+16,
+  "total_flos": 6.7446395960832e+16,
   "trial_name": null,
   "trial_params": null
 }