Training in progress, step 1, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
+    "down_proj",
     "k_proj",
     "gate_proj",
-    "down_proj",
-    "q_proj",
+    "up_proj",
     "v_proj",
-    "up_proj"
+    "o_proj",
+    "q_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:b59ae0c65fd66d333a6afa6a3e0eb355737767312007a55a6e7f7a51aaecf029
+oid sha256:ec6cbd1c2938d07aee1a5389dfc30d49c460718667389cc09d75a1fb980d99e6
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57aa5093bb35041d5edb05277f65db2ae0cf0daed8d75ddfdbc54b9b4f44896b
+oid sha256:73c12d7d662e76a16d514a7c3bd62182817c5116d85f26a94007520cdb8c1a17
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7da9f1139f61cc766662dec9be1a789e9af6ce81829e82037fdc4fc6fe2c5c18
+oid sha256:2c1bdcd7448219e600293d53ff73c83853ae0c339196e90ddb1d496056270a7f
 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": 0.0015519154516461943,
-  "eval_steps": 10,
-  "global_step": 50,
+  "epoch": 3.103830903292389e-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": 3.103830903292389e-05,
       "eval_loss": 3.7120916843414307,
-      "eval_runtime": 1355.8503,
-      "eval_samples_per_second": 10.006,
-      "eval_steps_per_second": 5.003,
+      "eval_runtime": 1361.7732,
+      "eval_samples_per_second": 9.962,
+      "eval_steps_per_second": 4.981,
       "step": 1
-    },
-    {
-      "epoch": 0.00015519154516461942,
-      "grad_norm": 2.1552507877349854,
-      "learning_rate": 5e-05,
-      "loss": 3.9595,
-      "step": 5
-    },
-    {
-      "epoch": 0.00031038309032923884,
-      "grad_norm": 3.6430537700653076,
-      "learning_rate": 0.0001,
-      "loss": 3.5018,
-      "step": 10
-    },
-    {
-      "epoch": 0.00031038309032923884,
-      "eval_loss": 3.1252193450927734,
-      "eval_runtime": 1356.105,
-      "eval_samples_per_second": 10.004,
-      "eval_steps_per_second": 5.002,
-      "step": 10
-    },
-    {
-      "epoch": 0.0004655746354938583,
-      "grad_norm": 2.4750373363494873,
-      "learning_rate": 9.619397662556435e-05,
-      "loss": 2.5722,
-      "step": 15
-    },
-    {
-      "epoch": 0.0006207661806584777,
-      "grad_norm": 1.5241283178329468,
-      "learning_rate": 8.535533905932738e-05,
-      "loss": 1.5678,
-      "step": 20
-    },
-    {
-      "epoch": 0.0006207661806584777,
-      "eval_loss": 1.1251658201217651,
-      "eval_runtime": 1355.943,
-      "eval_samples_per_second": 10.005,
-      "eval_steps_per_second": 5.002,
-      "step": 20
-    },
-    {
-      "epoch": 0.0007759577258230971,
-      "grad_norm": 1.527565360069275,
-      "learning_rate": 6.91341716182545e-05,
-      "loss": 1.1063,
-      "step": 25
-    },
-    {
-      "epoch": 0.0009311492709877166,
-      "grad_norm": 1.7839757204055786,
-      "learning_rate": 5e-05,
-      "loss": 0.799,
-      "step": 30
-    },
-    {
-      "epoch": 0.0009311492709877166,
-      "eval_loss": 0.6185202598571777,
-      "eval_runtime": 1357.0146,
-      "eval_samples_per_second": 9.997,
-      "eval_steps_per_second": 4.998,
-      "step": 30
-    },
-    {
-      "epoch": 0.0010863408161523361,
-      "grad_norm": 1.172727346420288,
-      "learning_rate": 3.086582838174551e-05,
-      "loss": 0.4837,
-      "step": 35
-    },
-    {
-      "epoch": 0.0012415323613169554,
-      "grad_norm": 1.2722738981246948,
-      "learning_rate": 1.4644660940672627e-05,
-      "loss": 0.4368,
-      "step": 40
-    },
-    {
-      "epoch": 0.0012415323613169554,
-      "eval_loss": 0.4388025104999542,
-      "eval_runtime": 1356.999,
-      "eval_samples_per_second": 9.997,
-      "eval_steps_per_second": 4.999,
-      "step": 40
-    },
-    {
-      "epoch": 0.0013967239064815748,
-      "grad_norm": 1.1449508666992188,
-      "learning_rate": 3.8060233744356633e-06,
-      "loss": 0.3963,
-      "step": 45
-    },
-    {
-      "epoch": 0.0015519154516461943,
-      "grad_norm": 0.7516467571258545,
-      "learning_rate": 0.0,
-      "loss": 0.403,
-      "step": 50
-    },
-    {
-      "epoch": 0.0015519154516461943,
-      "eval_loss": 0.41470852494239807,
-      "eval_runtime": 1355.9699,
-      "eval_samples_per_second": 10.005,
-      "eval_steps_per_second": 5.002,
-      "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": 1.547311779938304e+16,
+  "total_flos": 325749848408064.0,
   "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:af0fc664b0f78b5edce403061af19e752e893c93796aa5a2da8ae2299e61a712
+oid sha256:f5e76f48b7fe2632a7d86e0199b2f33c9d5f9c8750a05025001349fc1c945098
 size 6776