Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "q_proj",
     "k_proj",
-    "gate_proj",
-    "up_proj",
     "v_proj",
     "o_proj",
+    "up_proj",
     "down_proj",
-    "q_proj"
+    "gate_proj"
   ],
   "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 sha256:465ed80f4e41232bac32c905cdb5599447df074839446202b3b885469c5e8092
+oid sha256:f0ce46624dcc38339c8f71960c2aea25beeff28b35aa54e58cb5380a231aa415
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b21a98399f4a753ccc2d075d8652683e37eee1eb64014b914b5eb741ae803baf
+oid sha256:1af2c48b214f33c13714b4e6ae82b8269891bf4b3bb32536c1792238ddb0ee47
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce18d2d551de9284109c0e2530e5f04b91a8696554c7740e97ea2b7bdd6d1090
+oid sha256:baecc8988a2f594185c875288190c60274795754df975adfaa0c8b19740a1a71
 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": 5.714612263557917e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0007428995942625293,
+  "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": 5.714612263557917e-05,
       "eval_loss": 5.322761535644531,
-      "eval_runtime": 1111.1779,
-      "eval_samples_per_second": 6.631,
-      "eval_steps_per_second": 3.315,
+      "eval_runtime": 1113.0929,
+      "eval_samples_per_second": 6.619,
+      "eval_steps_per_second": 3.31,
       "step": 1
+    },
+    {
+      "epoch": 0.00028573061317789587,
+      "grad_norm": 99.31301879882812,
+      "learning_rate": 5e-05,
+      "loss": 20.6401,
+      "step": 5
+    },
+    {
+      "epoch": 0.0005714612263557917,
+      "grad_norm": 150.89935302734375,
+      "learning_rate": 0.0001,
+      "loss": 20.1525,
+      "step": 10
+    },
+    {
+      "epoch": 0.0005714612263557917,
+      "eval_loss": 3.5502824783325195,
+      "eval_runtime": 1113.2257,
+      "eval_samples_per_second": 6.619,
+      "eval_steps_per_second": 3.309,
+      "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": 350533957189632.0,
+  "total_flos": 4513124698816512.0,
   "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 sha256:5b8242127a8ebb761d9b9930aaa8acbcca7aba80114abb8349235bfa93948623
+oid sha256:d3998a8a68e8bcbb3bd9178aa49c385a10c89fa50a262369450a5ef7a6fd2f3c
 size 6776