Training in progress, step 1, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "q_proj",
-    "down_proj",
-    "up_proj",
     "v_proj",
-    "k_proj",
-    "o_proj"
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj",
+    "gate_proj",
+    "k_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 sha256:18dc6060de8c128e117c5ce24d9e4da4ad79d23eba34dafe403d1ed7226cb8f8
+oid sha256:d2085e5e5ae4a4b2c9c1f78678fa0169ff9ec6401218dd485bd08f1b49bce871
 size 48679352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45cbb3b0323cae4e143143f477d8c2646acbf186987abd9e7c48a313fd419fde
+oid sha256:9b80f324b974d53679e20af62fcdd2c88a00e37fe9bfc25346b347a97885da47
 size 25152500

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ae91c81bb1bda2bfa96330f9b07ba8a071665d1b8c7a5fc225f5ea9c74fbbc2
+oid sha256:db583067794f20b01832d4ddabaad594d5a607a594a6f04f852e2b423222180d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
+oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.008454872120059184,
-  "eval_steps": 10,
-  "global_step": 50,
+  "epoch": 0.0001690974424011837,
+  "eval_steps": 1,
+  "global_step": 1,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,127 +11,17 @@
     {
       "epoch": 0.0001690974424011837,
       "eval_loss": 0.6357499361038208,
-      "eval_runtime": 140.594,
-      "eval_samples_per_second": 17.711,
-      "eval_steps_per_second": 8.855,
+      "eval_runtime": 141.0554,
+      "eval_samples_per_second": 17.653,
+      "eval_steps_per_second": 8.826,
       "step": 1
-    },
-    {
-      "epoch": 0.0008454872120059184,
-      "grad_norm": 0.23109857738018036,
-      "learning_rate": 5e-05,
-      "loss": 0.5982,
-      "step": 5
-    },
-    {
-      "epoch": 0.0016909744240118367,
-      "grad_norm": 0.32216212153434753,
-      "learning_rate": 0.0001,
-      "loss": 0.6734,
-      "step": 10
-    },
-    {
-      "epoch": 0.0016909744240118367,
-      "eval_loss": 0.6111032962799072,
-      "eval_runtime": 141.3399,
-      "eval_samples_per_second": 17.617,
-      "eval_steps_per_second": 8.809,
-      "step": 10
-    },
-    {
-      "epoch": 0.0025364616360177552,
-      "grad_norm": 0.2761354446411133,
-      "learning_rate": 9.619397662556435e-05,
-      "loss": 0.5525,
-      "step": 15
-    },
-    {
-      "epoch": 0.0033819488480236735,
-      "grad_norm": 0.3936506509780884,
-      "learning_rate": 8.535533905932738e-05,
-      "loss": 0.5134,
-      "step": 20
-    },
-    {
-      "epoch": 0.0033819488480236735,
-      "eval_loss": 0.5297576189041138,
-      "eval_runtime": 142.7855,
-      "eval_samples_per_second": 17.439,
-      "eval_steps_per_second": 8.719,
-      "step": 20
-    },
-    {
-      "epoch": 0.004227436060029592,
-      "grad_norm": 0.4028269946575165,
-      "learning_rate": 6.91341716182545e-05,
-      "loss": 0.4533,
-      "step": 25
-    },
-    {
-      "epoch": 0.0050729232720355105,
-      "grad_norm": 0.3197304308414459,
-      "learning_rate": 5e-05,
-      "loss": 0.4767,
-      "step": 30
-    },
-    {
-      "epoch": 0.0050729232720355105,
-      "eval_loss": 0.5105544328689575,
-      "eval_runtime": 142.8654,
-      "eval_samples_per_second": 17.429,
-      "eval_steps_per_second": 8.714,
-      "step": 30
-    },
-    {
-      "epoch": 0.005918410484041429,
-      "grad_norm": 0.33733314275741577,
-      "learning_rate": 3.086582838174551e-05,
-      "loss": 0.4694,
-      "step": 35
-    },
-    {
-      "epoch": 0.006763897696047347,
-      "grad_norm": 0.4488641023635864,
-      "learning_rate": 1.4644660940672627e-05,
-      "loss": 0.4668,
-      "step": 40
-    },
-    {
-      "epoch": 0.006763897696047347,
-      "eval_loss": 0.50519859790802,
-      "eval_runtime": 142.7619,
-      "eval_samples_per_second": 17.442,
-      "eval_steps_per_second": 8.721,
-      "step": 40
-    },
-    {
-      "epoch": 0.007609384908053266,
-      "grad_norm": 0.3778371512889862,
-      "learning_rate": 3.8060233744356633e-06,
-      "loss": 0.5074,
-      "step": 45
-    },
-    {
-      "epoch": 0.008454872120059184,
-      "grad_norm": 0.33311334252357483,
-      "learning_rate": 0.0,
-      "loss": 0.4794,
-      "step": 50
-    },
-    {
-      "epoch": 0.008454872120059184,
-      "eval_loss": 0.5040430426597595,
-      "eval_runtime": 141.9754,
-      "eval_samples_per_second": 17.538,
-      "eval_steps_per_second": 8.769,
-      "step": 50
     }
   ],
   "logging_steps": 5,
-  "max_steps": 50,
+  "max_steps": 1,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 13,
+  "save_steps": 1,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -144,7 +34,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5600570517749760.0,
+  "total_flos": 139144609136640.0,
   "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 sha256:970945d17a881d17fb4642a2a489c21c9954e4d9455c343ef04721e859e26bea
+oid sha256:9e292bbdfbba24381a1ea0d6ed53af4f98514ac1370e030678b164a4ba7f0588
 size 6776