Training in progress, epoch 0, checkpoint

last-checkpoint/adapter_config.json

@@ -10,23 +10,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
-  "lora_dropout": 0.05,
+  "lora_alpha": 8,
+  "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 4,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
     "gate_proj",
     "q_proj",
-    "up_proj",
+    "down_proj",
     "v_proj",
+    "o_proj",
     "k_proj",
-    "down_proj"
+    "up_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:b533b7117bc0e3c81f20822c894195616054d12b9a0cdcfb40e420186d215d2a
-size 14696
+oid sha256:1d88b1e51271dd31989fdcb683c1f1b908065dbdaece123315139618413ff168
+size 9048

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f42ed2f7db2eb0efb886fd0c06f7bbded3dbda320f1d1b8a30c808868f264a9
-size 39398
+oid sha256:a22ece71d8000ff8dfbaa944694fb3173f5083ccc053d6dc045708f8cc7d2754
+size 28134

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3e7f581cbfcc9ee011f6906f74fe1cae71cebb72a9de5faedb960a4a724a10b
+oid sha256:89dbad7a5f4eb47d4580585d91b020d1a7f5dc2fd4d54175561c1eb48d2175e4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebe0540ed6e94d693724d0fd61916b0efd9dc6adbac83c0b0a2d35823214a0a5
+oid sha256:e6da16eefab22daee3fb0999c7651be192feb36b73810bf419e9165c7023ec02
 size 1064

last-checkpoint/trainer_state.json

@@ -1,7 +1,7 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.727664155005382e-05,
+  "epoch": 0.0002666666666666667,
   "eval_steps": 500,
   "global_step": 1,
   "is_hyper_param_search": false,
@@ -9,18 +9,18 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 6.727664155005382e-05,
-      "grad_norm": 0.1577831506729126,
-      "learning_rate": 0.0001,
-      "loss": 11.9692,
+      "epoch": 0.0002666666666666667,
+      "grad_norm": 0.013278936967253685,
+      "learning_rate": 0.0,
+      "loss": 11.9308,
       "step": 1
     },
     {
-      "epoch": 6.727664155005382e-05,
-      "eval_loss": 11.932138442993164,
-      "eval_runtime": 0.7745,
-      "eval_samples_per_second": 194.959,
-      "eval_steps_per_second": 194.959,
+      "epoch": 0.0002666666666666667,
+      "eval_loss": 11.933883666992188,
+      "eval_runtime": 0.0604,
+      "eval_samples_per_second": 265.052,
+      "eval_steps_per_second": 66.263,
       "step": 1
     }
   ],
@@ -41,8 +41,8 @@
       "attributes": {}
     }
   },
-  "total_flos": 3692544.0,
-  "train_batch_size": 1,
+  "total_flos": 10444800.0,
+  "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:746519a0d96e6801b9e01fd3392d353e8f9467d5d8a337d4d558559fbbc2a9f0
+oid sha256:c263e05fe207b407c6cd11bb652d63a63732b2d1b47dcaa717b61ddd3b2908e5
 size 6776