Training in progress, step 1000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fafa06afcfe8cb3f99cebccff70da442a3235613cee8e9d96f47868759eb184
+oid sha256:60946e37979145aa9a9e215ed9d7164b3fffae876a38c9bd5428998b9e46f967
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74f72b21cf44bc2db86b7d92bea717d4306def78cf0bd626a77c89a1d0bdf449
+oid sha256:aac72d3c9ffae1a41075109cb505cc228f79b1166b04ee4f0cb3149b4bc83712
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2badf77de5f001fb7a6ec008eb08fb5ff6e56a3cfa119aeed3b9e33cc1691aac
+oid sha256:94f62e9a3b242c8c8b9f4a8d4e73fc2bfa679b0c548fab0ee7b833ff28c97b01
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3c39113390004215769b6e7fbe73f1073dd2faa3ab8f9ff815b62e9c2f80c82
+oid sha256:3bb7339d1d2da342a44f3ba5e076fb6e5d93aee86f890c002703d2b3a0750820
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.9468154907226562,
-  "best_model_checkpoint": "./outputs/checkpoint-900",
-  "epoch": 1.2784090909090908,
+  "best_metric": 1.9387000799179077,
+  "best_model_checkpoint": "./outputs/checkpoint-1000",
+  "epoch": 1.4204545454545454,
   "eval_steps": 100,
-  "global_step": 900,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -133,6 +133,20 @@
       "eval_samples_per_second": 19.819,
       "eval_steps_per_second": 2.484,
       "step": 900
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.0002,
+      "loss": 2.0737,
+      "step": 1000
+    },
+    {
+      "epoch": 1.42,
+      "eval_loss": 1.9387000799179077,
+      "eval_runtime": 75.1482,
+      "eval_samples_per_second": 19.854,
+      "eval_steps_per_second": 2.488,
+      "step": 1000
     }
   ],
   "logging_steps": 100,
@@ -140,7 +154,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.739447726317568e+16,
+  "total_flos": 3.04398546665472e+16,
   "trial_name": null,
   "trial_params": null
 }