Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "dense",
-    "k_proj",
+    "fc2",
+    "q_proj",
     "v_proj",
     "fc1",
-    "fc2",
-    "q_proj"
+    "k_proj",
+    "dense"
   ],
   "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 sha256:27408c34a426666326cdca7eadd371c4c2786e8507f049f8cd53a1747d950780
+oid sha256:153354adb18d148a24e3cfa56dfa84176f93d1fd9e29770488db5fbdff5db339
 size 28348936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fc13ee9ec5b5a45de643e1a9dd356e4c46c94f45d78bda5885456751278b175
+oid sha256:066a8e173a125d800e76f9b9af86930d261fdb3ce0ffaaf8d74cc367182f165e
 size 14714068

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d1a79639e12b8889f2b311dbfd6d3fd05a8ab3c09e9da62375e8eb00ecb18bd
+oid sha256:9236e63cf9cb8afba0ea778b5222e99707adb9172e18130ef8d6fc2ffd066843
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:5adea6def46a60dd5782726d51a89bdf0f30226cd791e511d8af09a5644f99e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0011554015020219526,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.015020219526285385,
+  "eval_steps": 10,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,32 @@
     {
       "epoch": 0.0011554015020219526,
       "eval_loss": 6.479506969451904,
-      "eval_runtime": 205.6487,
-      "eval_samples_per_second": 28.354,
-      "eval_steps_per_second": 3.545,
+      "eval_runtime": 205.9246,
+      "eval_samples_per_second": 28.316,
+      "eval_steps_per_second": 3.54,
       "step": 1
+    },
+    {
+      "epoch": 0.011554015020219527,
+      "grad_norm": 2.6358954906463623,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 5.4872,
+      "step": 10
+    },
+    {
+      "epoch": 0.011554015020219527,
+      "eval_loss": 4.352705955505371,
+      "eval_runtime": 204.1824,
+      "eval_samples_per_second": 28.558,
+      "eval_steps_per_second": 3.57,
+      "step": 10
     }
   ],
   "logging_steps": 10,
-  "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 +44,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 941119223365632.0,
+  "total_flos": 1.233190706479104e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36f5f013749d3fa1916409104d7a10ddb76af73ff9efdc513bc6f9b9a61e88bb
+oid sha256:3c56e726ab7d75db132e22bc209ed4b3869c3dae42e1e33427a2073eb12a14b1
 size 6776