Training in progress, step 1800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59465a4a7d34793059adfe9a8416fd24c5b271a5ecdb3df0fb42c337ff706f11
+oid sha256:608489387daeb1a56e87ce498459fd7d98bfb06cf92c1bfc13d9d265e233bc5c
 size 6304192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:392009cd8ba887ce820a80707e0daff1f42dd31245c3b7bc8f20fd6911fb8c98
+oid sha256:986dfa4577c0b6ce3660a3836b3555a21f8e4e78e4b7986da916ad693d9dc2e1
 size 12639429

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ba57bccd1bc46c2196bf8529c8ed5ea5a8675c8c74e1de03263cf273e5cb709
+oid sha256:86ef024fdb50d2b5245e358e85c40ce33acc74b982ce82b2769eebe5c2cafd32
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0410ad60e6d0138b921a03b0a3e367fd27c6ab07cb9a5006fcb66ea8e5bbacc4
+oid sha256:c0e0a1736a46fd1627af3c246e44261aaac909256abbd413b5ee5c968f6b2d8e
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2424886226654053,
-  "best_model_checkpoint": "./outputs/checkpoint-1700",
-  "epoch": 2.2666666666666666,
+  "best_metric": 1.2424781322479248,
+  "best_model_checkpoint": "./outputs/checkpoint-1800",
+  "epoch": 2.4,
   "eval_steps": 100,
-  "global_step": 1700,
+  "global_step": 1800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -245,6 +245,20 @@
       "eval_samples_per_second": 15.194,
       "eval_steps_per_second": 1.905,
       "step": 1700
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 0.0002,
+      "loss": 1.0668,
+      "step": 1800
+    },
+    {
+      "epoch": 2.4,
+      "eval_loss": 1.2424781322479248,
+      "eval_runtime": 127.5992,
+      "eval_samples_per_second": 15.125,
+      "eval_steps_per_second": 1.897,
+      "step": 1800
     }
   ],
   "logging_steps": 100,
@@ -252,7 +266,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 6.027920028021965e+16,
+  "total_flos": 6.382682082163507e+16,
   "trial_name": null,
   "trial_params": null
 }