Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "q_proj",
+    "up_proj",
     "v_proj",
+    "down_proj",
     "gate_proj",
-    "k_proj",
-    "up_proj",
     "o_proj",
-    "q_proj",
-    "down_proj"
+    "k_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:bd226552c5ba44ee75684055770a11e05f618a8b33b781067caccc7ad0c64acd
+oid sha256:d673bcce9668c03bbabea9a3fa17c92416591c32381a7de345b90a4f892f025c
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bb069877b1663570707a75a0fc4e9a9ab0291546e73f835a6499ba9986a47cc
+oid sha256:8e34d379e29d7b98436fcf351652257a9166fd126c4f831808bc7eb90f01c617
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:529c9e51cf346c9538de8a198d0e350de38ac30f5061dd3c6b0f0716ac464501
+oid sha256:d04ce38a4b1ebe155394d1cb2e43ba46dcd389805a0df7f2671ac2a395b23d6c
 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": 0.1784121320249777,
+  "epoch": 0.0463871543264942,
   "eval_steps": 10,
-  "global_step": 50,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,120 +11,32 @@
     {
       "epoch": 0.003568242640499554,
       "eval_loss": 7.846585750579834,
-      "eval_runtime": 58.1489,
-      "eval_samples_per_second": 2.029,
-      "eval_steps_per_second": 1.015,
+      "eval_runtime": 31.965,
+      "eval_samples_per_second": 3.692,
+      "eval_steps_per_second": 1.846,
       "step": 1
     },
     {
       "epoch": 0.01784121320249777,
-      "grad_norm": 41.419822692871094,
+      "grad_norm": 36.881221771240234,
       "learning_rate": 5e-05,
-      "loss": 30.7878,
+      "loss": 30.8244,
       "step": 5
     },
     {
       "epoch": 0.03568242640499554,
-      "grad_norm": 59.32698059082031,
+      "grad_norm": 57.29407501220703,
       "learning_rate": 0.0001,
-      "loss": 27.0405,
+      "loss": 27.1875,
       "step": 10
     },
     {
       "epoch": 0.03568242640499554,
-      "eval_loss": 3.822364568710327,
-      "eval_runtime": 56.4726,
-      "eval_samples_per_second": 2.09,
-      "eval_steps_per_second": 1.045,
+      "eval_loss": 3.8446438312530518,
+      "eval_runtime": 32.0307,
+      "eval_samples_per_second": 3.684,
+      "eval_steps_per_second": 1.842,
       "step": 10
-    },
-    {
-      "epoch": 0.05352363960749331,
-      "grad_norm": 22.128131866455078,
-      "learning_rate": 9.619397662556435e-05,
-      "loss": 9.0197,
-      "step": 15
-    },
-    {
-      "epoch": 0.07136485280999108,
-      "grad_norm": 18.33565902709961,
-      "learning_rate": 8.535533905932738e-05,
-      "loss": 3.4617,
-      "step": 20
-    },
-    {
-      "epoch": 0.07136485280999108,
-      "eval_loss": 0.7452569603919983,
-      "eval_runtime": 79.1279,
-      "eval_samples_per_second": 1.491,
-      "eval_steps_per_second": 0.746,
-      "step": 20
-    },
-    {
-      "epoch": 0.08920606601248884,
-      "grad_norm": 5.567965030670166,
-      "learning_rate": 6.91341716182545e-05,
-      "loss": 2.9074,
-      "step": 25
-    },
-    {
-      "epoch": 0.10704727921498662,
-      "grad_norm": 13.315966606140137,
-      "learning_rate": 5e-05,
-      "loss": 2.7719,
-      "step": 30
-    },
-    {
-      "epoch": 0.10704727921498662,
-      "eval_loss": 0.7875707745552063,
-      "eval_runtime": 25.4368,
-      "eval_samples_per_second": 4.639,
-      "eval_steps_per_second": 2.319,
-      "step": 30
-    },
-    {
-      "epoch": 0.12488849241748438,
-      "grad_norm": 6.743807792663574,
-      "learning_rate": 3.086582838174551e-05,
-      "loss": 2.9019,
-      "step": 35
-    },
-    {
-      "epoch": 0.14272970561998216,
-      "grad_norm": 8.351219177246094,
-      "learning_rate": 1.4644660940672627e-05,
-      "loss": 2.6862,
-      "step": 40
-    },
-    {
-      "epoch": 0.14272970561998216,
-      "eval_loss": 0.709270715713501,
-      "eval_runtime": 25.8895,
-      "eval_samples_per_second": 4.558,
-      "eval_steps_per_second": 2.279,
-      "step": 40
-    },
-    {
-      "epoch": 0.16057091882247992,
-      "grad_norm": 14.457117080688477,
-      "learning_rate": 3.8060233744356633e-06,
-      "loss": 2.9802,
-      "step": 45
-    },
-    {
-      "epoch": 0.1784121320249777,
-      "grad_norm": 9.18240737915039,
-      "learning_rate": 0.0,
-      "loss": 2.8617,
-      "step": 50
-    },
-    {
-      "epoch": 0.1784121320249777,
-      "eval_loss": 0.7003238201141357,
-      "eval_runtime": 7.8711,
-      "eval_samples_per_second": 14.992,
-      "eval_steps_per_second": 7.496,
-      "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": 8143665679564800.0,
+  "total_flos": 2117353076686848.0,
   "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:bda2fa5ff426cbe3a121b0b49d1d4745df50ba1a7f481a38b7b039302e4be115
+oid sha256:2fdcb486b0b23121d11e50208dd22f5e08b20161ee5910ad969eab61c97967b3
 size 6776