Training in progress, step 3, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "o_proj",
     "q_proj",
+    "down_proj",
+    "k_proj",
     "v_proj",
     "up_proj",
     "gate_proj",
-    "k_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:fbec12649f3cdbaec09276681b965c237a51c9d269b2e7832280cd287fa3a43d
+oid sha256:a8a206fd6fc82dc47865ca6972a848f653d5bb4c2cc530c6dc040a0487086171
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:601f86c559232f4e87233f8ef4de3229c8221c5900d0a94eb84232851e178144
+oid sha256:1904d8aee5cd393e6742756d030dadbcc2a508b70f966870e41930044f0afabe
 size 39398

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d72d7ea22c77570d9f0b88ee6c374873539a76f4bdfadda50933cc65992b9c8
-size 14512
+oid sha256:49d56c6fd229b79724ed3dcdb4b672517c1648204c72ac049f2492d414e60de1
+size 15920

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8acd44aea89adc155a830cbfb990e7f2a2f3c98d29366996401b6b1b0b798b77
-size 14512
+oid sha256:ce7631bd4ab517ce695982f0c187210a288656770e5c42ef4faa0f4c7edd7a3b
+size 15984

last-checkpoint/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82b85acc8eedcc692a4ea50ce2ab6c5db7c647c8c83776e141cce4bb67023ceb
+size 15984

last-checkpoint/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44e5a47f6caf446465a431fdda949366f3e32ce41cb8af2309a1630b254ebe18
+size 15984

last-checkpoint/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d17c75edd95d4e6d6a49098208613a584190e481ff384794811ac9f97688a1f4
+size 15984

last-checkpoint/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55f9a29d74bc179bd8107b8481e9c3e9e5582d1833bda5a5f55c2b0024f64b20
+size 15984

last-checkpoint/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d1c4d9a201fe2b5cd47cdb7e914822e96d14ce765e17bad5e47ded0b3392b99
+size 15984

last-checkpoint/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7969b1d053e2a68474c1dcbcff3192620975ee90d4433cd6a1c7abbad15fa205
+size 15984

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

@@ -1,114 +1,49 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005608524957936063,
+  "epoch": 0.013452914798206279,
   "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": 0.0005608524957936063,
-      "grad_norm": 0.014601945877075195,
+      "epoch": 0.004484304932735426,
+      "grad_norm": 0.006755814887583256,
       "learning_rate": 2e-05,
-      "loss": 11.9315,
+      "loss": 11.9309,
       "step": 1
     },
     {
-      "epoch": 0.0005608524957936063,
-      "eval_loss": 11.931306838989258,
-      "eval_runtime": 2.705,
-      "eval_samples_per_second": 277.638,
-      "eval_steps_per_second": 139.004,
+      "epoch": 0.004484304932735426,
+      "eval_loss": 11.931302070617676,
+      "eval_runtime": 0.5278,
+      "eval_samples_per_second": 1422.827,
+      "eval_steps_per_second": 89.045,
       "step": 1
     },
     {
-      "epoch": 0.0011217049915872126,
-      "grad_norm": 0.0080253342166543,
+      "epoch": 0.008968609865470852,
+      "grad_norm": 0.008150096982717514,
       "learning_rate": 4e-05,
-      "loss": 11.9304,
+      "loss": 11.9311,
       "step": 2
     },
     {
-      "epoch": 0.0016825574873808188,
-      "grad_norm": 0.01091256458312273,
+      "epoch": 0.013452914798206279,
+      "grad_norm": 0.00839826837182045,
       "learning_rate": 6e-05,
-      "loss": 11.9319,
+      "loss": 11.9313,
       "step": 3
     },
     {
-      "epoch": 0.0016825574873808188,
-      "eval_loss": 11.931302070617676,
-      "eval_runtime": 2.7389,
-      "eval_samples_per_second": 274.202,
-      "eval_steps_per_second": 137.284,
+      "epoch": 0.013452914798206279,
+      "eval_loss": 11.931297302246094,
+      "eval_runtime": 0.521,
+      "eval_samples_per_second": 1441.543,
+      "eval_steps_per_second": 90.216,
       "step": 3
-    },
-    {
-      "epoch": 0.002243409983174425,
-      "grad_norm": 0.01584225706756115,
-      "learning_rate": 8e-05,
-      "loss": 11.9328,
-      "step": 4
-    },
-    {
-      "epoch": 0.0028042624789680315,
-      "grad_norm": 0.01661496050655842,
-      "learning_rate": 0.0001,
-      "loss": 11.9248,
-      "step": 5
-    },
-    {
-      "epoch": 0.0033651149747616375,
-      "grad_norm": 0.008873275481164455,
-      "learning_rate": 0.00012,
-      "loss": 11.926,
-      "step": 6
-    },
-    {
-      "epoch": 0.0033651149747616375,
-      "eval_loss": 11.931286811828613,
-      "eval_runtime": 2.8054,
-      "eval_samples_per_second": 267.701,
-      "eval_steps_per_second": 134.029,
-      "step": 6
-    },
-    {
-      "epoch": 0.003925967470555244,
-      "grad_norm": 0.011052712798118591,
-      "learning_rate": 0.00014,
-      "loss": 11.9324,
-      "step": 7
-    },
-    {
-      "epoch": 0.00448681996634885,
-      "grad_norm": 0.005740743596106768,
-      "learning_rate": 0.00016,
-      "loss": 11.935,
-      "step": 8
-    },
-    {
-      "epoch": 0.005047672462142457,
-      "grad_norm": 0.011872372590005398,
-      "learning_rate": 0.00018,
-      "loss": 11.9287,
-      "step": 9
-    },
-    {
-      "epoch": 0.005047672462142457,
-      "eval_loss": 11.93126392364502,
-      "eval_runtime": 2.7223,
-      "eval_samples_per_second": 275.873,
-      "eval_steps_per_second": 138.12,
-      "step": 9
-    },
-    {
-      "epoch": 0.005608524957936063,
-      "grad_norm": 0.007526675704866648,
-      "learning_rate": 0.0002,
-      "loss": 11.9335,
-      "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": 1211154432.0,
+  "total_flos": 2894954496.0,
   "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:d6c93858d1c3a74aac008c11d81cfafe05e09f8d5379f18aebd6f8c9fd21194a
+oid sha256:b480b5981b44b1a685dac017205977827e4a56934f64c3c150725d74276fd6fb
 size 6776