Training in progress, step 1, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "v_proj",
-    "down_proj",
-    "o_proj",
+    "gate_proj",
     "q_proj",
+    "o_proj",
     "up_proj",
-    "gate_proj"
+    "v_proj",
+    "down_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 sha256:2f34b85fa1e719916212998c01e25fdcbdb6c6f49e275a456a0dac8edcb90c7e
+oid sha256:c0944fef5d9870908a850416e9370f6a1307eb62e8cf1a8605e843f126e778ac
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5a2d669783a612fd0afa501c5300dab4569147e9eff1f7710478b3894c2fe31
+oid sha256:07ded3bd2e251596c3af756e3b091a642adc3ad1d9a46d9e6c4d023f465a5dee
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbeb344358c5b2fc3427ec40a46912a0f05a8b64159d1e85af690dec1f30ebc6
+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": 0.0015492226775215535,
-  "eval_steps": 10,
-  "global_step": 50,
+  "epoch": 3.098445355043107e-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": 3.098445355043107e-05,
       "eval_loss": 1.195532202720642,
-      "eval_runtime": 1454.9398,
-      "eval_samples_per_second": 9.341,
-      "eval_steps_per_second": 4.67,
+      "eval_runtime": 1671.7428,
+      "eval_samples_per_second": 8.129,
+      "eval_steps_per_second": 4.065,
       "step": 1
-    },
-    {
-      "epoch": 0.00015492226775215535,
-      "grad_norm": 0.22048205137252808,
-      "learning_rate": 5e-05,
-      "loss": 1.2744,
-      "step": 5
-    },
-    {
-      "epoch": 0.0003098445355043107,
-      "grad_norm": 0.2948167622089386,
-      "learning_rate": 0.0001,
-      "loss": 1.1851,
-      "step": 10
-    },
-    {
-      "epoch": 0.0003098445355043107,
-      "eval_loss": 1.146066427230835,
-      "eval_runtime": 1458.2994,
-      "eval_samples_per_second": 9.319,
-      "eval_steps_per_second": 4.66,
-      "step": 10
-    },
-    {
-      "epoch": 0.0004647668032564661,
-      "grad_norm": 0.29153722524642944,
-      "learning_rate": 9.619397662556435e-05,
-      "loss": 1.1034,
-      "step": 15
-    },
-    {
-      "epoch": 0.0006196890710086214,
-      "grad_norm": 0.31050845980644226,
-      "learning_rate": 8.535533905932738e-05,
-      "loss": 1.0061,
-      "step": 20
-    },
-    {
-      "epoch": 0.0006196890710086214,
-      "eval_loss": 1.0127846002578735,
-      "eval_runtime": 1456.8345,
-      "eval_samples_per_second": 9.328,
-      "eval_steps_per_second": 4.664,
-      "step": 20
-    },
-    {
-      "epoch": 0.0007746113387607767,
-      "grad_norm": 0.338260293006897,
-      "learning_rate": 6.91341716182545e-05,
-      "loss": 1.0445,
-      "step": 25
-    },
-    {
-      "epoch": 0.0009295336065129322,
-      "grad_norm": 0.33603912591934204,
-      "learning_rate": 5e-05,
-      "loss": 0.9271,
-      "step": 30
-    },
-    {
-      "epoch": 0.0009295336065129322,
-      "eval_loss": 0.9617733359336853,
-      "eval_runtime": 1465.4277,
-      "eval_samples_per_second": 9.274,
-      "eval_steps_per_second": 4.637,
-      "step": 30
-    },
-    {
-      "epoch": 0.0010844558742650874,
-      "grad_norm": 0.29064711928367615,
-      "learning_rate": 3.086582838174551e-05,
-      "loss": 0.9954,
-      "step": 35
-    },
-    {
-      "epoch": 0.0012393781420172428,
-      "grad_norm": 0.26686355471611023,
-      "learning_rate": 1.4644660940672627e-05,
-      "loss": 0.8849,
-      "step": 40
-    },
-    {
-      "epoch": 0.0012393781420172428,
-      "eval_loss": 0.9477787017822266,
-      "eval_runtime": 1466.3979,
-      "eval_samples_per_second": 9.268,
-      "eval_steps_per_second": 4.634,
-      "step": 40
-    },
-    {
-      "epoch": 0.0013943004097693981,
-      "grad_norm": 0.26942411065101624,
-      "learning_rate": 3.8060233744356633e-06,
-      "loss": 0.9229,
-      "step": 45
-    },
-    {
-      "epoch": 0.0015492226775215535,
-      "grad_norm": 0.3074963688850403,
-      "learning_rate": 0.0,
-      "loss": 0.9729,
-      "step": 50
-    },
-    {
-      "epoch": 0.0015492226775215535,
-      "eval_loss": 0.9452804327011108,
-      "eval_runtime": 1463.3929,
-      "eval_samples_per_second": 9.287,
-      "eval_steps_per_second": 4.643,
-      "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": 1.631344694132736e+16,
+  "total_flos": 329564584673280.0,
   "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 sha256:64fc1663dcc857414e974ca64c0fc60401310189ca79d1a766620a0b6f1353c0
+oid sha256:1282862ef4cd6e946a53bd460b8859ab7b30bff3bd3a88e8322fd83fd26ecbe1
 size 6776