Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -21,11 +21,11 @@
   "revision": null,
   "target_modules": [
     "gate_proj",
+    "down_proj",
     "o_proj",
     "v_proj",
-    "up_proj",
-    "down_proj",
     "q_proj",
+    "up_proj",
     "k_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c667f3158c7121051f8f080210a32def773221021715d632a9623fd6c8931b02
+oid sha256:9d2aa0ee5eaa8f65a06718277d762a4bfb0338f5148362141e6b8977e2d73cc4
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a25356f1d4da875880fb13346a4087d097ad469aced44a354bf5582f0c250ed7
+oid sha256:d6b25c752847b616122f69c31210833d88a139298d792a264acf326e4f7f32f6
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc465ce5bd3952187c57f4d107eff6e29f0951dae6123b0dc8cb299f37bf12ca
+oid sha256:7f9237e9f8977bb0c6e516068d1da6bc029d8f114c421df2881a3b72905e53cc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
+oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.14450867052023122,
+  "epoch": 0.03757225433526012,
   "eval_steps": 10,
-  "global_step": 50,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,9 +11,9 @@
     {
       "epoch": 0.002890173410404624,
       "eval_loss": NaN,
-      "eval_runtime": 33.0624,
-      "eval_samples_per_second": 4.416,
-      "eval_steps_per_second": 2.208,
+      "eval_runtime": 21.3252,
+      "eval_samples_per_second": 6.846,
+      "eval_steps_per_second": 3.423,
       "step": 1
     },
     {
@@ -33,98 +33,10 @@
     {
       "epoch": 0.028901734104046242,
       "eval_loss": NaN,
-      "eval_runtime": 19.3605,
-      "eval_samples_per_second": 7.541,
-      "eval_steps_per_second": 3.771,
+      "eval_runtime": 19.2525,
+      "eval_samples_per_second": 7.583,
+      "eval_steps_per_second": 3.792,
       "step": 10
-    },
-    {
-      "epoch": 0.04335260115606936,
-      "grad_norm": NaN,
-      "learning_rate": 9.619397662556435e-05,
-      "loss": 0.0,
-      "step": 15
-    },
-    {
-      "epoch": 0.057803468208092484,
-      "grad_norm": NaN,
-      "learning_rate": 8.535533905932738e-05,
-      "loss": 0.0,
-      "step": 20
-    },
-    {
-      "epoch": 0.057803468208092484,
-      "eval_loss": NaN,
-      "eval_runtime": 19.6331,
-      "eval_samples_per_second": 7.436,
-      "eval_steps_per_second": 3.718,
-      "step": 20
-    },
-    {
-      "epoch": 0.07225433526011561,
-      "grad_norm": NaN,
-      "learning_rate": 6.91341716182545e-05,
-      "loss": 0.0,
-      "step": 25
-    },
-    {
-      "epoch": 0.08670520231213873,
-      "grad_norm": NaN,
-      "learning_rate": 5e-05,
-      "loss": 0.0,
-      "step": 30
-    },
-    {
-      "epoch": 0.08670520231213873,
-      "eval_loss": NaN,
-      "eval_runtime": 22.7434,
-      "eval_samples_per_second": 6.419,
-      "eval_steps_per_second": 3.21,
-      "step": 30
-    },
-    {
-      "epoch": 0.10115606936416185,
-      "grad_norm": NaN,
-      "learning_rate": 3.086582838174551e-05,
-      "loss": 0.0,
-      "step": 35
-    },
-    {
-      "epoch": 0.11560693641618497,
-      "grad_norm": NaN,
-      "learning_rate": 1.4644660940672627e-05,
-      "loss": 0.0,
-      "step": 40
-    },
-    {
-      "epoch": 0.11560693641618497,
-      "eval_loss": NaN,
-      "eval_runtime": 18.4744,
-      "eval_samples_per_second": 7.903,
-      "eval_steps_per_second": 3.951,
-      "step": 40
-    },
-    {
-      "epoch": 0.13005780346820808,
-      "grad_norm": NaN,
-      "learning_rate": 3.8060233744356633e-06,
-      "loss": 0.0,
-      "step": 45
-    },
-    {
-      "epoch": 0.14450867052023122,
-      "grad_norm": NaN,
-      "learning_rate": 0.0,
-      "loss": 0.0,
-      "step": 50
-    },
-    {
-      "epoch": 0.14450867052023122,
-      "eval_loss": NaN,
-      "eval_runtime": 20.8873,
-      "eval_samples_per_second": 6.99,
-      "eval_steps_per_second": 3.495,
-      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -139,12 +51,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 3234875128676352.0,
+  "total_flos": 835068015673344.0,
   "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 sha256:285b7299698f125be3fc24951caddf4a06473df4e80b51e536b101a157790775
 size 6776