Training in progress, step 1, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "gate_proj",
-    "up_proj",
+    "down_proj",
     "k_proj",
-    "o_proj",
+    "gate_proj",
+    "q_proj",
     "v_proj",
-    "down_proj"
+    "up_proj",
+    "o_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 sha256:4f6b60fcae97ff3254a518b14da04f37124bdf1ae476f1994c2a8cd7567e14be
+oid sha256:0add5290396cf0ac4f59ce067dd503a5f8ea88edf4037194f9da4dfe8655af63
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddd06a1d51d594964d2231d0a9f1dcd7ce979116db8da9b5de5ff823411dcb44
+oid sha256:1360b214dc305ce0c7fca0fdb3feecc9d03ca3af798b10af45b117b0f4bff123
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dec5fe9a4e7d0b0d0b5890a54362458d63f1aa0cd3805572b7c904b144470602
+oid sha256:d9673d22f265ed23c9ac8fe3534732259b5ca12d0692ce0ea4ceef5963b1b4fd
 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": 0.052144440099074436,
-  "eval_steps": 10,
-  "global_step": 50,
+  "epoch": 6.518267444513249e-05,
+  "eval_steps": 1,
+  "global_step": 1,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.0010428888019814887,
+      "epoch": 6.518267444513249e-05,
       "eval_loss": NaN,
-      "eval_runtime": 330.4614,
-      "eval_samples_per_second": 19.548,
-      "eval_steps_per_second": 2.445,
+      "eval_runtime": 378.354,
+      "eval_samples_per_second": 17.074,
+      "eval_steps_per_second": 8.537,
       "step": 1
-    },
-    {
-      "epoch": 0.010428888019814887,
-      "grad_norm": NaN,
-      "learning_rate": 9.330127018922194e-05,
-      "loss": 0.0,
-      "step": 10
-    },
-    {
-      "epoch": 0.010428888019814887,
-      "eval_loss": NaN,
-      "eval_runtime": 329.3613,
-      "eval_samples_per_second": 19.614,
-      "eval_steps_per_second": 2.453,
-      "step": 10
-    },
-    {
-      "epoch": 0.020857776039629773,
-      "grad_norm": NaN,
-      "learning_rate": 6.91341716182545e-05,
-      "loss": 0.0,
-      "step": 20
-    },
-    {
-      "epoch": 0.020857776039629773,
-      "eval_loss": NaN,
-      "eval_runtime": 329.7608,
-      "eval_samples_per_second": 19.59,
-      "eval_steps_per_second": 2.45,
-      "step": 20
-    },
-    {
-      "epoch": 0.03128666405944466,
-      "grad_norm": NaN,
-      "learning_rate": 3.705904774487396e-05,
-      "loss": 0.0,
-      "step": 30
-    },
-    {
-      "epoch": 0.03128666405944466,
-      "eval_loss": NaN,
-      "eval_runtime": 330.0198,
-      "eval_samples_per_second": 19.575,
-      "eval_steps_per_second": 2.448,
-      "step": 30
-    },
-    {
-      "epoch": 0.041715552079259546,
-      "grad_norm": NaN,
-      "learning_rate": 1.0332332985438248e-05,
-      "loss": 0.0,
-      "step": 40
-    },
-    {
-      "epoch": 0.041715552079259546,
-      "eval_loss": NaN,
-      "eval_runtime": 329.6182,
-      "eval_samples_per_second": 19.598,
-      "eval_steps_per_second": 2.451,
-      "step": 40
-    },
-    {
-      "epoch": 0.052144440099074436,
-      "grad_norm": NaN,
-      "learning_rate": 0.0,
-      "loss": 0.0,
-      "step": 50
-    },
-    {
-      "epoch": 0.052144440099074436,
-      "eval_loss": NaN,
-      "eval_runtime": 329.6408,
-      "eval_samples_per_second": 19.597,
-      "eval_steps_per_second": 2.451,
-      "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": 1.394108836872192e+17,
-  "train_batch_size": 8,
+  "total_flos": 174263604609024.0,
+  "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 sha256:8d9a9dea8f331f584c9b487728133ae2af0263e1b2a48a913b461eaa2ca9767b
+oid sha256:5f79eac3c3becad6b6342c9f355b4383f31ede640da5992da13e3b93ef21b914
 size 6776