Training in progress, step 3, checkpoint

last-checkpoint/adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "gate_proj",
-    "up_proj",
     "k_proj",
     "q_proj",
+    "up_proj",
+    "v_proj",
     "o_proj",
+    "gate_proj",
     "down_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79b3f28efd4fb6fac213216e392f9aa9c76e859a658868551e576aa09b480129
+oid sha256:3baa951bbbfdd1188f382c335ea49151b29b4c1fb18142935ab6cba433da0dc0
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:932eef22d386a206fbe0de2ddc8060fbd47b6f25ea52487a4a3716a9c8d40221
+oid sha256:3fdecc7bce3383d3a5b220e46876f4004ad2ace0aa89554c31ac6a6f13b9323b
 size 43122580

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3dfd3c3f31e5cb1ac7738aec767337a40d13bfb22b8b1f1f4ac9ea45caa5c45
+oid sha256:2cf68e26f94a54bb8ae5cbe12765de6bac6a1ccb174b66646786b68d44d57d0a
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bce9471f3eb84d4671d04353c3ce29e32a53340decf25bb098801e695f41548f
+oid sha256:3c8fe3c71a39000d4197cc8405349be99d4e3eb178b1ed84fbd89bec27620702
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:984862ca3e225b5a4f559e8cc3ae15d46f21c5d2c5baeb13d595e5855d391e75
+oid sha256:70a1a52aa6601b66cd14aa6c2ab353f19e95d8c430b1673f818f682e2acf6abc
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b1e5a3ac85757db89814139cfc8f3eef753e74d7ac5c5491479733b749b72b9
+oid sha256:ef25f629f6c4240e649191e5537010a60073d3455d6b59ae07a421ecdf15669f
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
 size 1064

last-checkpoint/trainer_state.json

@@ -1,16 +1,16 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.18691588785046728,
+  "epoch": 0.056074766355140186,
   "eval_steps": 3,
-  "global_step": 10,
+  "global_step": 3,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.018691588785046728,
-      "grad_norm": 1.2704600095748901,
+      "grad_norm": 1.2734662294387817,
       "learning_rate": 2e-05,
       "loss": 2.2598,
       "step": 1
@@ -18,97 +18,32 @@
     {
       "epoch": 0.018691588785046728,
       "eval_loss": 2.2257795333862305,
-      "eval_runtime": 0.9227,
-      "eval_samples_per_second": 98.625,
-      "eval_steps_per_second": 13.005,
+      "eval_runtime": 0.9183,
+      "eval_samples_per_second": 99.093,
+      "eval_steps_per_second": 13.067,
       "step": 1
     },
     {
       "epoch": 0.037383177570093455,
-      "grad_norm": 1.3961941003799438,
+      "grad_norm": 1.3796645402908325,
       "learning_rate": 4e-05,
       "loss": 2.262,
       "step": 2
     },
     {
       "epoch": 0.056074766355140186,
-      "grad_norm": 1.301194429397583,
+      "grad_norm": 1.3051254749298096,
       "learning_rate": 6e-05,
-      "loss": 2.2203,
+      "loss": 2.2198,
       "step": 3
     },
     {
       "epoch": 0.056074766355140186,
-      "eval_loss": 2.207164764404297,
-      "eval_runtime": 0.9897,
-      "eval_samples_per_second": 91.95,
-      "eval_steps_per_second": 12.125,
+      "eval_loss": 2.2063558101654053,
+      "eval_runtime": 0.9821,
+      "eval_samples_per_second": 92.663,
+      "eval_steps_per_second": 12.219,
       "step": 3
-    },
-    {
-      "epoch": 0.07476635514018691,
-      "grad_norm": 1.3056365251541138,
-      "learning_rate": 8e-05,
-      "loss": 2.1908,
-      "step": 4
-    },
-    {
-      "epoch": 0.09345794392523364,
-      "grad_norm": 1.2624163627624512,
-      "learning_rate": 0.0001,
-      "loss": 2.1388,
-      "step": 5
-    },
-    {
-      "epoch": 0.11214953271028037,
-      "grad_norm": 1.3537291288375854,
-      "learning_rate": 0.00012,
-      "loss": 2.1188,
-      "step": 6
-    },
-    {
-      "epoch": 0.11214953271028037,
-      "eval_loss": 1.8779184818267822,
-      "eval_runtime": 0.9893,
-      "eval_samples_per_second": 91.989,
-      "eval_steps_per_second": 12.13,
-      "step": 6
-    },
-    {
-      "epoch": 0.1308411214953271,
-      "grad_norm": 1.3764944076538086,
-      "learning_rate": 0.00014,
-      "loss": 1.8747,
-      "step": 7
-    },
-    {
-      "epoch": 0.14953271028037382,
-      "grad_norm": 1.407188892364502,
-      "learning_rate": 0.00016,
-      "loss": 1.637,
-      "step": 8
-    },
-    {
-      "epoch": 0.16822429906542055,
-      "grad_norm": 1.341946005821228,
-      "learning_rate": 0.00018,
-      "loss": 1.718,
-      "step": 9
-    },
-    {
-      "epoch": 0.16822429906542055,
-      "eval_loss": 1.5427663326263428,
-      "eval_runtime": 0.987,
-      "eval_samples_per_second": 92.195,
-      "eval_steps_per_second": 12.158,
-      "step": 9
-    },
-    {
-      "epoch": 0.18691588785046728,
-      "grad_norm": 1.5312464237213135,
-      "learning_rate": 0.0002,
-      "loss": 1.5626,
-      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -123,12 +58,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 7398256992583680.0,
+  "total_flos": 2219477097775104.0,
   "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:f3d3679db69ceef058498181bca7397508073e6fb52128a62b7e2c29a12b87cd
+oid sha256:209d8d7a29703f1d9662a917c50a08f1a61c19405f30552f5bbeddfb953db7e5
 size 6712