Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -21,9 +21,9 @@
   "revision": null,
   "target_modules": [
     "dense_h_to_4h",
+    "query_key_value",
     "dense",
-    "dense_4h_to_h",
-    "query_key_value"
+    "dense_4h_to_h"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:660a3237a09a3a144f6a848bcf59f3d9f773540979c541a8a0a2319714263717
+oid sha256:0f80570171eb4128ea94897b7fb339be1b8faaae7e455f6c482787a6bc8737ba
 size 25192496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04669e8640494907289e0e57255c375f0104bdac29adef3c332ea73429cbfbd3
+oid sha256:f49291774a46c7e4128f9f7f944b39ff8d38785b0d73805d223775fc7d27f41d
 size 13005178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a985867639007f961b208e0d4a01f2747fed7ed93d5be58f508870576f1b146
+oid sha256:48ff583cbed74ae345b2c71bfc9205b2dc7ab182aa8a1dc1b15179eaff92fb8a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.465451514613251e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0007105086968997226,
+  "eval_steps": 10,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,39 @@
     {
       "epoch": 5.465451514613251e-05,
       "eval_loss": 3.0376367568969727,
-      "eval_runtime": 691.7432,
-      "eval_samples_per_second": 11.137,
-      "eval_steps_per_second": 5.569,
+      "eval_runtime": 692.0351,
+      "eval_samples_per_second": 11.132,
+      "eval_steps_per_second": 5.566,
       "step": 1
+    },
+    {
+      "epoch": 0.00027327257573066255,
+      "grad_norm": 9.199381828308105,
+      "learning_rate": 5e-05,
+      "loss": 13.2748,
+      "step": 5
+    },
+    {
+      "epoch": 0.0005465451514613251,
+      "grad_norm": 10.021293640136719,
+      "learning_rate": 0.0001,
+      "loss": 12.8217,
+      "step": 10
+    },
+    {
+      "epoch": 0.0005465451514613251,
+      "eval_loss": 2.7879865169525146,
+      "eval_runtime": 693.1951,
+      "eval_samples_per_second": 11.114,
+      "eval_steps_per_second": 5.557,
+      "step": 10
     }
   ],
   "logging_steps": 5,
-  "max_steps": 1,
+  "max_steps": 50,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 1,
+  "save_steps": 13,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -29,12 +51,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 59714473820160.0,
+  "total_flos": 776288159662080.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1fd845bc5ed58da9503b25c5ccc5c2a9ea630eff1f2e5781c959601cd224b9a
+oid sha256:74f33fe8ac14ce5aba98871749768ff8716341934e6c742a947e5aa014a2c8fa
 size 6776