Training in progress, step 1, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
     "q_proj",
-    "o_proj",
-    "v_proj",
+    "k_proj",
     "gate_proj",
+    "up_proj",
     "down_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 sha256:0b8945e878be151ddfc7063de49857eebc91cdd16a483d4ecc18fa43d06fefdc
+oid sha256:bdcfea411f8cd15e45d4c83c900a5b0c5f3f75802234e6d0038f641d8d820c63
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddd06a1d51d594964d2231d0a9f1dcd7ce979116db8da9b5de5ff823411dcb44
+oid sha256:1360b214dc305ce0c7fca0fdb3feecc9d03ca3af798b10af45b117b0f4bff123
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41789f3af3a2f230c866a76817aa8d07b0351b38fb4936d34dc66478fbaf0cb3
+oid sha256:a2eae9201856a338feeba0ff4bf7474692709b21fd9c0fc9f43cf11e5b83198f
 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": 0.001505253334136135,
-  "eval_steps": 10,
-  "global_step": 50,
+  "epoch": 3.0105066682722702e-05,
+  "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": 3.0105066682722702e-05,
       "eval_loss": NaN,
-      "eval_runtime": 1587.2582,
-      "eval_samples_per_second": 8.812,
-      "eval_steps_per_second": 4.406,
+      "eval_runtime": 1576.8338,
+      "eval_samples_per_second": 8.87,
+      "eval_steps_per_second": 4.435,
       "step": 1
-    },
-    {
-      "epoch": 0.00015052533341361352,
-      "grad_norm": NaN,
-      "learning_rate": 5e-05,
-      "loss": 0.0,
-      "step": 5
-    },
-    {
-      "epoch": 0.00030105066682722703,
-      "grad_norm": NaN,
-      "learning_rate": 0.0001,
-      "loss": 0.0,
-      "step": 10
-    },
-    {
-      "epoch": 0.00030105066682722703,
-      "eval_loss": NaN,
-      "eval_runtime": 1589.757,
-      "eval_samples_per_second": 8.798,
-      "eval_steps_per_second": 4.399,
-      "step": 10
-    },
-    {
-      "epoch": 0.0004515760002408405,
-      "grad_norm": NaN,
-      "learning_rate": 9.619397662556435e-05,
-      "loss": 0.0,
-      "step": 15
-    },
-    {
-      "epoch": 0.0006021013336544541,
-      "grad_norm": NaN,
-      "learning_rate": 8.535533905932738e-05,
-      "loss": 0.0,
-      "step": 20
-    },
-    {
-      "epoch": 0.0006021013336544541,
-      "eval_loss": NaN,
-      "eval_runtime": 1590.0558,
-      "eval_samples_per_second": 8.797,
-      "eval_steps_per_second": 4.399,
-      "step": 20
-    },
-    {
-      "epoch": 0.0007526266670680675,
-      "grad_norm": NaN,
-      "learning_rate": 6.91341716182545e-05,
-      "loss": 0.0,
-      "step": 25
-    },
-    {
-      "epoch": 0.000903152000481681,
-      "grad_norm": NaN,
-      "learning_rate": 5e-05,
-      "loss": 0.0,
-      "step": 30
-    },
-    {
-      "epoch": 0.000903152000481681,
-      "eval_loss": NaN,
-      "eval_runtime": 1588.543,
-      "eval_samples_per_second": 8.805,
-      "eval_steps_per_second": 4.403,
-      "step": 30
-    },
-    {
-      "epoch": 0.0010536773338952945,
-      "grad_norm": NaN,
-      "learning_rate": 3.086582838174551e-05,
-      "loss": 0.0,
-      "step": 35
-    },
-    {
-      "epoch": 0.0012042026673089081,
-      "grad_norm": NaN,
-      "learning_rate": 1.4644660940672627e-05,
-      "loss": 0.0,
-      "step": 40
-    },
-    {
-      "epoch": 0.0012042026673089081,
-      "eval_loss": NaN,
-      "eval_runtime": 1584.1629,
-      "eval_samples_per_second": 8.829,
-      "eval_steps_per_second": 4.415,
-      "step": 40
-    },
-    {
-      "epoch": 0.0013547280007225216,
-      "grad_norm": NaN,
-      "learning_rate": 3.8060233744356633e-06,
-      "loss": 0.0,
-      "step": 45
-    },
-    {
-      "epoch": 0.001505253334136135,
-      "grad_norm": NaN,
-      "learning_rate": 0.0,
-      "loss": 0.0,
-      "step": 50
-    },
-    {
-      "epoch": 0.001505253334136135,
-      "eval_loss": NaN,
-      "eval_runtime": 1583.3342,
-      "eval_samples_per_second": 8.834,
-      "eval_steps_per_second": 4.417,
-      "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": 1.7077833251684352e+16,
+  "total_flos": 348527209218048.0,
   "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 sha256:390ec137b1e2130ba7739530f8650fb24920a69891994edd4b47e004e4ac20e1
+oid sha256:838f3b607b7a7439f00f34167bb5f50daf2f16906641ce65654aa977b314d19e
 size 6776