Training in progress, step 1, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
+    "k_proj",
     "o_proj",
     "v_proj",
     "up_proj",
     "down_proj",
-    "q_proj",
-    "k_proj"
+    "gate_proj",
+    "q_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:c667f3158c7121051f8f080210a32def773221021715d632a9623fd6c8931b02
+oid sha256:ba2b7fddd7e8c5757c9c3ffe5dbebdbb3b09c4bcfe0868335e8e3cbd60781410
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6b25c752847b616122f69c31210833d88a139298d792a264acf326e4f7f32f6
+oid sha256:b1c840391a21fbb35ce4846a625e1f63917d6d5d754442f8daed3465d346a0e7
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f9237e9f8977bb0c6e516068d1da6bc029d8f114c421df2881a3b72905e53cc
+oid sha256:772c12aea0055e16597749ef8f0cf5d107fb6f555f61b38319bdf80a27064f18
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
+oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03757225433526012,
-  "eval_steps": 10,
-  "global_step": 13,
+  "epoch": 0.002890173410404624,
+  "eval_steps": 1,
+  "global_step": 1,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,39 +11,17 @@
     {
       "epoch": 0.002890173410404624,
       "eval_loss": NaN,
-      "eval_runtime": 33.0624,
-      "eval_samples_per_second": 4.416,
-      "eval_steps_per_second": 2.208,
+      "eval_runtime": 26.9332,
+      "eval_samples_per_second": 5.421,
+      "eval_steps_per_second": 2.71,
       "step": 1
-    },
-    {
-      "epoch": 0.014450867052023121,
-      "grad_norm": NaN,
-      "learning_rate": 5e-05,
-      "loss": 0.0,
-      "step": 5
-    },
-    {
-      "epoch": 0.028901734104046242,
-      "grad_norm": NaN,
-      "learning_rate": 0.0001,
-      "loss": 0.0,
-      "step": 10
-    },
-    {
-      "epoch": 0.028901734104046242,
-      "eval_loss": NaN,
-      "eval_runtime": 19.3605,
-      "eval_samples_per_second": 7.541,
-      "eval_steps_per_second": 3.771,
-      "step": 10
     }
   ],
   "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": {
@@ -51,12 +29,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 835068015673344.0,
+  "total_flos": 64859651702784.0,
   "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 sha256:3c5965fd082c86171b43b37ef2304ff45259d8950c596e22c65b26ea28d27a2c
+oid sha256:3d6b472af211d5dd4c48af73191b80f9c09570a04d2a3b56d1139f6261a9019a
 size 6776