Training in progress, step 10, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
     "gate_proj",
     "v_proj",
+    "down_proj",
     "o_proj",
-    "k_proj",
     "q_proj",
-    "up_proj"
+    "up_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:a0aef1fa7dbdb45e82489134af6d8602e4bf0936ca8b735c2aaa40351d8cf690
+oid sha256:8fd3b6737e9b1bdd1d6ea497fd79cde02fc17565139323cfcc10ff04f3fffc82
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f82b2fac4c287073493532f0e8d909683405ff219ebae791e130f8f6fc2023cd
+oid sha256:b7d410f5582950b1434cc019aaffae7f4c1c4278fb5dd7122c1d9b46f255f186
 size 160172858

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:200897803867d9476163ce84baa477ea4bfc2d20fbca1d606afa2d969206fa8c
+oid sha256:a3efe221c4a0adf497082884c488f9d91c42d1d873e72d47409fbf104eb83048
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,16 +1,16 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0021554304873667826,
+  "epoch": 0.0023949227637408694,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.00023949227637408692,
-      "grad_norm": 5.190128803253174,
+      "grad_norm": 5.223796367645264,
       "learning_rate": 2e-05,
       "loss": 2.4864,
       "step": 1
@@ -18,90 +18,97 @@
     {
       "epoch": 0.00023949227637408692,
       "eval_loss": 3.196671962738037,
-      "eval_runtime": 163.6418,
-      "eval_samples_per_second": 5.378,
-      "eval_steps_per_second": 5.378,
+      "eval_runtime": 163.78,
+      "eval_samples_per_second": 5.373,
+      "eval_steps_per_second": 5.373,
       "step": 1
     },
     {
       "epoch": 0.00047898455274817384,
-      "grad_norm": 3.8827998638153076,
+      "grad_norm": 3.92407488822937,
       "learning_rate": 4e-05,
       "loss": 3.3358,
       "step": 2
     },
     {
       "epoch": 0.0007184768291222608,
-      "grad_norm": 3.203981876373291,
+      "grad_norm": 3.1619839668273926,
       "learning_rate": 6e-05,
-      "loss": 3.3946,
+      "loss": 3.3959,
       "step": 3
     },
     {
       "epoch": 0.0007184768291222608,
-      "eval_loss": 3.0946106910705566,
-      "eval_runtime": 162.7901,
-      "eval_samples_per_second": 5.406,
-      "eval_steps_per_second": 5.406,
+      "eval_loss": 3.0963945388793945,
+      "eval_runtime": 163.8871,
+      "eval_samples_per_second": 5.37,
+      "eval_steps_per_second": 5.37,
       "step": 3
     },
     {
       "epoch": 0.0009579691054963477,
-      "grad_norm": 3.0879592895507812,
+      "grad_norm": 3.1326329708099365,
       "learning_rate": 8e-05,
-      "loss": 2.7666,
+      "loss": 2.768,
       "step": 4
     },
     {
       "epoch": 0.0011974613818704347,
-      "grad_norm": 3.3717029094696045,
+      "grad_norm": 3.3326337337493896,
       "learning_rate": 0.0001,
-      "loss": 2.7991,
+      "loss": 2.8028,
       "step": 5
     },
     {
       "epoch": 0.0014369536582445215,
-      "grad_norm": 2.83575439453125,
+      "grad_norm": 2.820315361022949,
       "learning_rate": 0.00012,
-      "loss": 1.8184,
+      "loss": 1.8255,
       "step": 6
     },
     {
       "epoch": 0.0014369536582445215,
-      "eval_loss": 2.6198861598968506,
-      "eval_runtime": 162.8545,
-      "eval_samples_per_second": 5.404,
-      "eval_steps_per_second": 5.404,
+      "eval_loss": 2.628291368484497,
+      "eval_runtime": 163.4655,
+      "eval_samples_per_second": 5.383,
+      "eval_steps_per_second": 5.383,
       "step": 6
     },
     {
       "epoch": 0.0016764459346186086,
-      "grad_norm": 2.426558256149292,
+      "grad_norm": 2.3316752910614014,
       "learning_rate": 0.00014,
-      "loss": 2.6655,
+      "loss": 2.6749,
       "step": 7
     },
     {
       "epoch": 0.0019159382109926954,
-      "grad_norm": 1.7445547580718994,
+      "grad_norm": 1.7211425304412842,
       "learning_rate": 0.00016,
-      "loss": 1.9561,
+      "loss": 1.9641,
       "step": 8
     },
     {
       "epoch": 0.0021554304873667826,
-      "grad_norm": 1.1460472345352173,
+      "grad_norm": 1.1501375436782837,
       "learning_rate": 0.00018,
-      "loss": 1.7204,
+      "loss": 1.7288,
       "step": 9
     },
     {
       "epoch": 0.0021554304873667826,
-      "eval_loss": 2.171725034713745,
-      "eval_runtime": 163.204,
-      "eval_samples_per_second": 5.392,
-      "eval_steps_per_second": 5.392,
+      "eval_loss": 2.1707475185394287,
+      "eval_runtime": 163.4934,
+      "eval_samples_per_second": 5.382,
+      "eval_steps_per_second": 5.382,
       "step": 9
+    },
+    {
+      "epoch": 0.0023949227637408694,
+      "grad_norm": 1.843157410621643,
+      "learning_rate": 0.0002,
+      "loss": 1.5776,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -116,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1478847803424768.0,
+  "total_flos": 1643164226027520.0,
   "train_batch_size": 1,
   "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:d9c99d0e2f5b8cc5e216c0a981ae420dfd0fdc085832d4176287c753653f2960
+oid sha256:06b93c27182e910c542b1e5fa166e9014b0895cb2f985ab3ed11d7d2d2b13627
 size 6776