Training in progress, step 1, checkpoint

last-checkpoint/adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
     "q_proj",
-    "o_proj",
     "down_proj",
+    "v_proj",
+    "o_proj",
     "up_proj",
     "gate_proj",
     "k_proj"

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aedb7851d99090f11bbb9b725dc4bc3c9c95f78016e6bf69d67126e0e0dbef22
+oid sha256:203301e3b5526978243e8d89a98274ab08a8d557bcccc7959cd2c65ea0584274
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7441bd72a8ab80be22f71af324b422d12ab914e62dd40255b7c372817037b6db
+oid sha256:3d331d02e035ffcd50bdaf7e7840cbcbe61fe17c36b89e934acbecf0df61700e
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af2202558662bca10e0fe13d768ab39eb3cf9190e25153973e536077ff3dcd4b
+oid sha256:6e7b432d4c1390a80984e093813a079e02823704a7187bbae0ecafb3a9eb8384
 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": 0.11990407673860912,
-  "eval_steps": 10,
-  "global_step": 50,
+  "epoch": 0.00014989132878662968,
+  "eval_steps": 1,
+  "global_step": 1,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.002398081534772182,
-      "eval_loss": 10.374227523803711,
-      "eval_runtime": 4.7315,
-      "eval_samples_per_second": 593.897,
-      "eval_steps_per_second": 74.396,
+      "epoch": 0.00014989132878662968,
+      "eval_loss": 10.374155044555664,
+      "eval_runtime": 12.7746,
+      "eval_samples_per_second": 219.968,
+      "eval_steps_per_second": 109.984,
       "step": 1
-    },
-    {
-      "epoch": 0.023980815347721823,
-      "grad_norm": 0.027691999450325966,
-      "learning_rate": 9.330127018922194e-05,
-      "loss": 10.3744,
-      "step": 10
-    },
-    {
-      "epoch": 0.023980815347721823,
-      "eval_loss": 10.373770713806152,
-      "eval_runtime": 4.4671,
-      "eval_samples_per_second": 629.048,
-      "eval_steps_per_second": 78.799,
-      "step": 10
-    },
-    {
-      "epoch": 0.047961630695443645,
-      "grad_norm": 0.027547860518097878,
-      "learning_rate": 6.91341716182545e-05,
-      "loss": 10.3738,
-      "step": 20
-    },
-    {
-      "epoch": 0.047961630695443645,
-      "eval_loss": 10.37330150604248,
-      "eval_runtime": 4.558,
-      "eval_samples_per_second": 616.503,
-      "eval_steps_per_second": 77.227,
-      "step": 20
-    },
-    {
-      "epoch": 0.07194244604316546,
-      "grad_norm": 0.030619895085692406,
-      "learning_rate": 3.705904774487396e-05,
-      "loss": 10.3732,
-      "step": 30
-    },
-    {
-      "epoch": 0.07194244604316546,
-      "eval_loss": 10.372995376586914,
-      "eval_runtime": 4.6099,
-      "eval_samples_per_second": 609.561,
-      "eval_steps_per_second": 76.358,
-      "step": 30
-    },
-    {
-      "epoch": 0.09592326139088729,
-      "grad_norm": 0.029737740755081177,
-      "learning_rate": 1.0332332985438248e-05,
-      "loss": 10.373,
-      "step": 40
-    },
-    {
-      "epoch": 0.09592326139088729,
-      "eval_loss": 10.37285327911377,
-      "eval_runtime": 4.5931,
-      "eval_samples_per_second": 611.788,
-      "eval_steps_per_second": 76.637,
-      "step": 40
-    },
-    {
-      "epoch": 0.11990407673860912,
-      "grad_norm": 0.02912091463804245,
-      "learning_rate": 0.0,
-      "loss": 10.3727,
-      "step": 50
-    },
-    {
-      "epoch": 0.11990407673860912,
-      "eval_loss": 10.372833251953125,
-      "eval_runtime": 4.5186,
-      "eval_samples_per_second": 621.881,
-      "eval_steps_per_second": 77.901,
-      "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": 10344726528000.0,
-  "train_batch_size": 8,
+  "total_flos": 12930908160.0,
+  "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 sha256:85d13ad1de46976a07e81f340cc79426d8dc81765cc5c16ca7e6bbc33f1d04eb
+oid sha256:4751813afb0b25b65d294f8cc036bd2587f8a48509699200113820d13af8a14e
 size 6776