Training in progress, step 5, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
     "q_proj",
-    "o_proj",
+    "down_proj",
     "gate_proj",
-    "v_proj",
+    "up_proj",
     "k_proj",
-    "up_proj"
+    "v_proj",
+    "o_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:e7aadff02eb8558c9740beadd5a8515e6a692bec62185c57715dc74eb516e3e8
+oid sha256:5cbf093472fb7af1bc859b0a382bf27ed46078b5aad5cd80c7eb38bc31473baa
 size 1770585648

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f22fda284fe8c75934d03ac77ff1560b4a2fcc4bc20b3580a6483453cc4bcdf
+oid sha256:13e99c884c8f2ec890eaa1d7c7de288c54598d77362cd8118226eb6ebc0e8762
 size 99235764

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bea54d2c350a4b2f8ad7efc6a9086ec6f77e8edbe147b48c2a3617b9ad41af6c
+oid sha256:d6a216e76306077697fce369babc722d934631ceab06c507d0d26aa9b1335b22
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2972d8cacb091bd0e98bfff54b2e4933301753087ce149a9bf9a205a5e2d795
+oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,48 +1,69 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.6,
-  "eval_steps": 1,
-  "global_step": 2,
+  "epoch": 0.021052631578947368,
+  "eval_steps": 3,
+  "global_step": 5,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.8,
-      "grad_norm": 11.588508605957031,
+      "epoch": 0.004210526315789474,
+      "grad_norm": 4.598019123077393,
       "learning_rate": 2e-05,
-      "loss": 13.3042,
+      "loss": 6.9188,
       "step": 1
     },
     {
-      "epoch": 0.8,
-      "eval_loss": 11.52426815032959,
-      "eval_runtime": 0.39,
-      "eval_samples_per_second": 2.564,
-      "eval_steps_per_second": 2.564,
+      "epoch": 0.004210526315789474,
+      "eval_loss": 6.859975814819336,
+      "eval_runtime": 33.5224,
+      "eval_samples_per_second": 2.983,
+      "eval_steps_per_second": 1.492,
       "step": 1
     },
     {
-      "epoch": 1.6,
-      "grad_norm": 11.549392700195312,
+      "epoch": 0.008421052631578947,
+      "grad_norm": 4.9840407371521,
       "learning_rate": 4e-05,
-      "loss": 13.1934,
+      "loss": 6.9548,
       "step": 2
     },
     {
-      "epoch": 1.6,
-      "eval_loss": 11.268893241882324,
-      "eval_runtime": 0.3904,
-      "eval_samples_per_second": 2.562,
-      "eval_steps_per_second": 2.562,
-      "step": 2
+      "epoch": 0.01263157894736842,
+      "grad_norm": 4.931889533996582,
+      "learning_rate": 6e-05,
+      "loss": 7.0142,
+      "step": 3
+    },
+    {
+      "epoch": 0.01263157894736842,
+      "eval_loss": 6.778191566467285,
+      "eval_runtime": 33.692,
+      "eval_samples_per_second": 2.968,
+      "eval_steps_per_second": 1.484,
+      "step": 3
+    },
+    {
+      "epoch": 0.016842105263157894,
+      "grad_norm": 5.493557453155518,
+      "learning_rate": 8e-05,
+      "loss": 6.6227,
+      "step": 4
+    },
+    {
+      "epoch": 0.021052631578947368,
+      "grad_norm": 5.254875659942627,
+      "learning_rate": 0.0001,
+      "loss": 6.3977,
+      "step": 5
     }
   ],
   "logging_steps": 1,
-  "max_steps": 2,
+  "max_steps": 10,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 2,
+  "num_train_epochs": 1,
   "save_steps": 5,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -51,12 +72,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 1057029158338560.0,
+  "total_flos": 2818744422236160.0,
   "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:af853a67b3854fa26b67dfae731715dfd1e79725227c471b95b403f47394d08e
+oid sha256:3adc47e4c8037ea0a9eac467b0ef0580d17689437606d47d386217d90a1d11ec
 size 6136