Training in progress, step 1, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "v_proj",
-    "down_proj",
-    "gate_proj",
+    "o_proj",
     "k_proj",
     "up_proj",
     "q_proj",
-    "o_proj"
+    "down_proj",
+    "gate_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 sha256:2d66e126d8cd12655145df85246f7d483721d29cc46661448e3d27b13ac63d9d
+oid sha256:d240ae4748e5694e07e09aeda6c8aa4d62e5ab8534b71238ee64282647d97985
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33f42712618c2b228b510c4a0a3b1d275897113b913d32e4cc9f509998f3b788
+oid sha256:530a3c6fab8ca4ac6cf3ebc5f5e27222b48ca4ff60fad427dc03e762226bc6c5
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f04944917c15f265951392f0ad036c49b2e1d3572ae924179abc0eb1dc0ce1c
+oid sha256:4bb5535922cb1f8053375cf4f0b5607ee0a1812e8ed130523ebe0c6cd11317ef
 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": 0.03537944454272068,
-  "eval_steps": 10,
-  "global_step": 50,
+  "epoch": 0.0007075888908544136,
+  "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": 0.0007075888908544136,
       "eval_loss": 10.552796363830566,
-      "eval_runtime": 47.9588,
-      "eval_samples_per_second": 12.406,
-      "eval_steps_per_second": 6.214,
+      "eval_runtime": 47.7122,
+      "eval_samples_per_second": 12.471,
+      "eval_steps_per_second": 6.246,
       "step": 1
-    },
-    {
-      "epoch": 0.0035379444542720678,
-      "grad_norm": 26.071264266967773,
-      "learning_rate": 5e-05,
-      "loss": 10.6088,
-      "step": 5
-    },
-    {
-      "epoch": 0.0070758889085441356,
-      "grad_norm": 25.356914520263672,
-      "learning_rate": 0.0001,
-      "loss": 7.7488,
-      "step": 10
-    },
-    {
-      "epoch": 0.0070758889085441356,
-      "eval_loss": 4.3914079666137695,
-      "eval_runtime": 48.3524,
-      "eval_samples_per_second": 12.305,
-      "eval_steps_per_second": 6.163,
-      "step": 10
-    },
-    {
-      "epoch": 0.010613833362816204,
-      "grad_norm": 28.135635375976562,
-      "learning_rate": 9.619397662556435e-05,
-      "loss": 2.8647,
-      "step": 15
-    },
-    {
-      "epoch": 0.014151777817088271,
-      "grad_norm": 10.654553413391113,
-      "learning_rate": 8.535533905932738e-05,
-      "loss": 0.5001,
-      "step": 20
-    },
-    {
-      "epoch": 0.014151777817088271,
-      "eval_loss": 0.41789498925209045,
-      "eval_runtime": 48.3132,
-      "eval_samples_per_second": 12.315,
-      "eval_steps_per_second": 6.168,
-      "step": 20
-    },
-    {
-      "epoch": 0.01768972227136034,
-      "grad_norm": 6.251014232635498,
-      "learning_rate": 6.91341716182545e-05,
-      "loss": 0.3643,
-      "step": 25
-    },
-    {
-      "epoch": 0.021227666725632408,
-      "grad_norm": 11.83096694946289,
-      "learning_rate": 5e-05,
-      "loss": 0.3107,
-      "step": 30
-    },
-    {
-      "epoch": 0.021227666725632408,
-      "eval_loss": 0.21780718863010406,
-      "eval_runtime": 48.4603,
-      "eval_samples_per_second": 12.278,
-      "eval_steps_per_second": 6.149,
-      "step": 30
-    },
-    {
-      "epoch": 0.024765611179904477,
-      "grad_norm": 0.5458418726921082,
-      "learning_rate": 3.086582838174551e-05,
-      "loss": 0.2974,
-      "step": 35
-    },
-    {
-      "epoch": 0.028303555634176542,
-      "grad_norm": 7.429529190063477,
-      "learning_rate": 1.4644660940672627e-05,
-      "loss": 0.1783,
-      "step": 40
-    },
-    {
-      "epoch": 0.028303555634176542,
-      "eval_loss": 0.1497228592634201,
-      "eval_runtime": 48.4086,
-      "eval_samples_per_second": 12.291,
-      "eval_steps_per_second": 6.156,
-      "step": 40
-    },
-    {
-      "epoch": 0.03184150008844861,
-      "grad_norm": 7.319284439086914,
-      "learning_rate": 3.8060233744356633e-06,
-      "loss": 0.1818,
-      "step": 45
-    },
-    {
-      "epoch": 0.03537944454272068,
-      "grad_norm": 7.400360584259033,
-      "learning_rate": 0.0,
-      "loss": 0.3288,
-      "step": 50
-    },
-    {
-      "epoch": 0.03537944454272068,
-      "eval_loss": 0.14456623792648315,
-      "eval_runtime": 48.4799,
-      "eval_samples_per_second": 12.273,
-      "eval_steps_per_second": 6.147,
-      "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": 9555457081344000.0,
+  "total_flos": 191109141626880.0,
   "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:df7f26cf6d43d598f9b1364179ecd4079035ad9734fbe4015e87dbcee4d693bd
+oid sha256:e860434176efc6a708b005f903cb9015512d5a7065fbcd103d026e56154dcde9
 size 6776