Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
     "up_proj",
-    "gate_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj",
     "down_proj",
     "q_proj",
-    "o_proj",
-    "k_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:a1c681701ae2571c4fecf021735437215b8edb6f8a7b3eb49777099087ae35cb
+oid sha256:78a8d6299f246aa90a461cba5e7cdd6098b3fdeb35d24f73226753f1ad5c6a04
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1238b4cb375c3903520f123588d51ca13eee3446a9bc2989cd234ab7bb9ca2e
+oid sha256:ae40c352e7abdb5203e6d0efe5760b9eb18bf9a66ea47066d87fb259b9af9c1a
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e96084db0d88b3f6f054fd8e1ee389d8068f68911086b40d9534c6441e1738ec
+oid sha256:35b6a158c84ac6a2bb295366e2caae4dfc38a123e092d320dc9f8152b74bc96f
 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": 0.000526592943654555,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.006845708267509215,
+  "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": 0.000526592943654555,
       "eval_loss": 10.178997039794922,
-      "eval_runtime": 21.2998,
-      "eval_samples_per_second": 37.559,
-      "eval_steps_per_second": 18.78,
+      "eval_runtime": 21.4891,
+      "eval_samples_per_second": 37.228,
+      "eval_steps_per_second": 18.614,
       "step": 1
+    },
+    {
+      "epoch": 0.0026329647182727752,
+      "grad_norm": 22.557941436767578,
+      "learning_rate": 5e-05,
+      "loss": 10.0299,
+      "step": 5
+    },
+    {
+      "epoch": 0.0052659294365455505,
+      "grad_norm": 24.156038284301758,
+      "learning_rate": 0.0001,
+      "loss": 7.5164,
+      "step": 10
+    },
+    {
+      "epoch": 0.0052659294365455505,
+      "eval_loss": 3.2705798149108887,
+      "eval_runtime": 21.3836,
+      "eval_samples_per_second": 37.412,
+      "eval_steps_per_second": 18.706,
+      "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": 24054551543808.0,
+  "total_flos": 312709170069504.0,
   "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:da66e35473b3ca9737d070eddcc176bb99cd6787e8e267092a14002485ceba79
+oid sha256:b60c045490c2b02d041777766560bc96f7454144f33654805d7e142dd3d5280a
 size 6776