Training in progress, step 1, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "up_proj",
+    "gate_proj",
     "k_proj",
     "v_proj",
-    "gate_proj",
-    "down_proj",
-    "q_proj"
+    "o_proj",
+    "q_proj",
+    "up_proj",
+    "down_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 sha256:688d778838c55b0578479a317a55a3164fc060bea7260ceed5113818f3eb2334
+oid sha256:2ebaa2d23c4f5ac3c4b2691293f0fb44c66581e11fd5d4c467a513a4daa2285d
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cd5838276fee287e998f0948daaf0f90781259d36f701615c5b9c1710eeb322
+oid sha256:213916e69d2d0d7fd5f1a09235451c856b4df38cc270c4e751e8e114def9f7d5
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04ba654ff3bebec0b8c057295e60da4148f65602bb406a4a9d7e1e31b13a4f7a
+oid sha256:792d1546ebf93af6d5f2808ada23d245a92ec7ea7130b1c43c380eba2e821f58
 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

@@ -1,102 +1,27 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1523809523809524,
-  "eval_steps": 10,
-  "global_step": 50,
+  "epoch": 0.00019047619047619048,
+  "eval_steps": 1,
+  "global_step": 1,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.0030476190476190477,
-      "eval_loss": 4.400742053985596,
-      "eval_runtime": 114.9592,
-      "eval_samples_per_second": 19.233,
-      "eval_steps_per_second": 2.41,
+      "epoch": 0.00019047619047619048,
+      "eval_loss": 4.401525974273682,
+      "eval_runtime": 130.1992,
+      "eval_samples_per_second": 16.982,
+      "eval_steps_per_second": 8.495,
       "step": 1
-    },
-    {
-      "epoch": 0.030476190476190476,
-      "grad_norm": 1.0924090147018433,
-      "learning_rate": 9.330127018922194e-05,
-      "loss": 2.463,
-      "step": 10
-    },
-    {
-      "epoch": 0.030476190476190476,
-      "eval_loss": 0.06426526606082916,
-      "eval_runtime": 114.7248,
-      "eval_samples_per_second": 19.272,
-      "eval_steps_per_second": 2.414,
-      "step": 10
-    },
-    {
-      "epoch": 0.06095238095238095,
-      "grad_norm": 0.2648712992668152,
-      "learning_rate": 6.91341716182545e-05,
-      "loss": 0.0275,
-      "step": 20
-    },
-    {
-      "epoch": 0.06095238095238095,
-      "eval_loss": 0.034637633711099625,
-      "eval_runtime": 115.3696,
-      "eval_samples_per_second": 19.164,
-      "eval_steps_per_second": 2.401,
-      "step": 20
-    },
-    {
-      "epoch": 0.09142857142857143,
-      "grad_norm": 0.0003379475383553654,
-      "learning_rate": 3.705904774487396e-05,
-      "loss": 0.013,
-      "step": 30
-    },
-    {
-      "epoch": 0.09142857142857143,
-      "eval_loss": 0.026944607496261597,
-      "eval_runtime": 114.9927,
-      "eval_samples_per_second": 19.227,
-      "eval_steps_per_second": 2.409,
-      "step": 30
-    },
-    {
-      "epoch": 0.1219047619047619,
-      "grad_norm": 0.0002899740939028561,
-      "learning_rate": 1.0332332985438248e-05,
-      "loss": 0.0084,
-      "step": 40
-    },
-    {
-      "epoch": 0.1219047619047619,
-      "eval_loss": 0.02513935975730419,
-      "eval_runtime": 114.8647,
-      "eval_samples_per_second": 19.249,
-      "eval_steps_per_second": 2.412,
-      "step": 40
-    },
-    {
-      "epoch": 0.1523809523809524,
-      "grad_norm": 0.12068207561969757,
-      "learning_rate": 0.0,
-      "loss": 0.0324,
-      "step": 50
-    },
-    {
-      "epoch": 0.1523809523809524,
-      "eval_loss": 0.024778621271252632,
-      "eval_runtime": 114.7796,
-      "eval_samples_per_second": 19.263,
-      "eval_steps_per_second": 2.413,
-      "step": 50
     }
   ],
-  "logging_steps": 10,
-  "max_steps": 50,
+  "logging_steps": 5,
+  "max_steps": 1,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 13,
+  "save_steps": 1,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -109,8 +34,8 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3502197696718438e+17,
-  "train_batch_size": 8,
+  "total_flos": 162873313591296.0,
+  "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 sha256:90400da332347c8d725a7ef78db68f6ff850850a139dbe8f54a45b559a5bb162
+oid sha256:66ed145fc5c15a154dc155bb28a58ac6da9cf4c11fb5ffef93d21fd82027add0
 size 6776