Training in progress, step 1200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:181d85e807b0b793a1dc2bb1ecd6f311ed37477246478ab7572f367f6d8eacab
+oid sha256:de8870e3d1844d63b1d1ccf6c212323aba6916a9403d58c3f906cfe0571362a1
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8651df2fec8e9e3bc369dd9f51ab3623b928fa3d1963e3a099359ec9cdc0933
+oid sha256:12555ca2545543abe6e163790234b25afbd4d55b67b282832079d80ef92c60c4
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84db2af589fa7f305136bb5605de5c7877cdb6c1ecdd979b15a8d593b1177841
+oid sha256:0648c05bcceba81aabdea1b34baac57c985681599db080ce43ad848e9f5bad60
 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": 1.9253034591674805,
-  "best_model_checkpoint": "./outputs/checkpoint-1100",
-  "epoch": 1.5625,
+  "best_metric": 1.9184151887893677,
+  "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": 19.892,
       "eval_steps_per_second": 2.493,
       "step": 1100
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 0.0002,
+      "loss": 2.0589,
+      "step": 1200
+    },
+    {
+      "epoch": 1.7,
+      "eval_loss": 1.9184151887893677,
+      "eval_runtime": 75.1429,
+      "eval_samples_per_second": 19.856,
+      "eval_steps_per_second": 2.489,
+      "step": 1200
     }
   ],
   "logging_steps": 100,
@@ -168,7 +182,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.347635642638336e+16,
+  "total_flos": 3.65226999975936e+16,
   "trial_name": null,
   "trial_params": null
 }