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",
     "up_proj",
+    "k_proj",
+    "q_proj",
+    "gate_proj",
     "o_proj",
     "v_proj",
-    "down_proj",
-    "gate_proj"
+    "down_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:bf3459951b76d0f17f731c298fd3e5e141973711b5219b3589aba53d5309ab71
+oid sha256:3bd0cb7914fbc1839d3cc4e902819cb5e0cf880edba65eb6b1ace257f70a098c
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad08b986d1c76d765c6a507a039771d6f7e11e32f5aacba5f54cadab31252a40
+oid sha256:308f21aecd78dafaebc40c259098e8e4b55b8dbe0f44531d0de6e946fa5ece28
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3e24e5a4848112015906f3af8fac3e7620b85d2495d2a8ad5b1d541e67d1036
+oid sha256:6b0d7d803be24f959b116e68b8ea14894849bd60bc99076174569f43dd2e27b2
 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": 0.0005636184303226716,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.00732703959419473,
+  "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": 0.0005636184303226716,
       "eval_loss": 11.894136428833008,
-      "eval_runtime": 47.4667,
-      "eval_samples_per_second": 15.737,
-      "eval_steps_per_second": 7.879,
+      "eval_runtime": 47.443,
+      "eval_samples_per_second": 15.745,
+      "eval_steps_per_second": 7.883,
       "step": 1
+    },
+    {
+      "epoch": 0.0028180921516133576,
+      "grad_norm": 22.021039962768555,
+      "learning_rate": 5e-05,
+      "loss": 12.5352,
+      "step": 5
+    },
+    {
+      "epoch": 0.005636184303226715,
+      "grad_norm": 19.067848205566406,
+      "learning_rate": 0.0001,
+      "loss": 9.8637,
+      "step": 10
+    },
+    {
+      "epoch": 0.005636184303226715,
+      "eval_loss": 5.757726192474365,
+      "eval_runtime": 47.5479,
+      "eval_samples_per_second": 15.71,
+      "eval_steps_per_second": 7.866,
+      "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": 75014599606272.0,
+  "total_flos": 1000194661416960.0,
   "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:d8033239e26a6ed9f5499c19b5ae07030b5096b2c38f1362ce1e2cee39492ea8
+oid sha256:d53238db5efe79f1abeab238c83d70d389182543369653dc62ac805c70601e3f
 size 6776