Training in progress, step 10, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "o_proj",
+    "up_proj",
     "gate_proj",
-    "down_proj",
+    "o_proj",
+    "q_proj",
     "k_proj",
-    "v_proj",
-    "up_proj"
+    "down_proj",
+    "v_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 sha256:2cabc5f81db3af2437bbfc2194f5c9bdbea1405c35a0297f99882781ca8cbaca
+oid sha256:c52d9e387c8871db8e6320785b47284eb7bb61158eac9e6b7cbbe6c659894e8c
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c91934a6d59c98e2741ed2afcb0c220f8ca504c42e1d99fe7be0210b50575f2
+oid sha256:895f657468f854cb20a87cbb895182fd5db0f60e4fda9ae13c3e6d204cab5038
 size 168037178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:631dfb2aa9ae256eca5748a1b2ab04547dfc14e5e8346db748407ed5d049499d
+oid sha256:574c700717b33f47ad8a70b47083271e5db120d9e87ae1c83258d7702c5eeb81
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2972d8cacb091bd0e98bfff54b2e4933301753087ce149a9bf9a205a5e2d795
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.25,
+  "epoch": 0.8333333333333334,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -18,32 +18,97 @@
     {
       "epoch": 0.08333333333333333,
       "eval_loss": 1.4977792501449585,
-      "eval_runtime": 0.2209,
-      "eval_samples_per_second": 13.579,
-      "eval_steps_per_second": 13.579,
+      "eval_runtime": 0.3019,
+      "eval_samples_per_second": 9.937,
+      "eval_steps_per_second": 9.937,
       "step": 1
     },
     {
       "epoch": 0.16666666666666666,
-      "grad_norm": 4.962691783905029,
+      "grad_norm": 4.949731349945068,
       "learning_rate": 2e-05,
       "loss": 1.307,
       "step": 2
     },
     {
       "epoch": 0.25,
-      "grad_norm": 5.919677734375,
+      "grad_norm": 5.8763322830200195,
       "learning_rate": 4e-05,
       "loss": 1.5735,
       "step": 3
     },
     {
       "epoch": 0.25,
-      "eval_loss": 1.4450377225875854,
-      "eval_runtime": 0.2257,
-      "eval_samples_per_second": 13.291,
-      "eval_steps_per_second": 13.291,
+      "eval_loss": 1.4451128244400024,
+      "eval_runtime": 0.4158,
+      "eval_samples_per_second": 7.215,
+      "eval_steps_per_second": 7.215,
       "step": 3
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 4.730646133422852,
+      "learning_rate": 6e-05,
+      "loss": 1.2767,
+      "step": 4
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 3.4440248012542725,
+      "learning_rate": 8e-05,
+      "loss": 1.3011,
+      "step": 5
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 2.8259096145629883,
+      "learning_rate": 0.0001,
+      "loss": 1.0815,
+      "step": 6
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 0.816199779510498,
+      "eval_runtime": 0.4516,
+      "eval_samples_per_second": 6.643,
+      "eval_steps_per_second": 6.643,
+      "step": 6
+    },
+    {
+      "epoch": 0.5833333333333334,
+      "grad_norm": 2.387253522872925,
+      "learning_rate": 0.00012,
+      "loss": 0.8264,
+      "step": 7
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 2.6841723918914795,
+      "learning_rate": 0.00014,
+      "loss": 0.5359,
+      "step": 8
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 2.8740291595458984,
+      "learning_rate": 0.00016,
+      "loss": 0.229,
+      "step": 9
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 0.04347331449389458,
+      "eval_runtime": 0.4018,
+      "eval_samples_per_second": 7.467,
+      "eval_steps_per_second": 7.467,
+      "step": 9
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 2.354649782180786,
+      "learning_rate": 0.00018,
+      "loss": 0.1454,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -58,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 554869274443776.0,
+  "total_flos": 1849564248145920.0,
   "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 sha256:33ee77f9946e0ddfbac6f0c8ae58cf2871b3fdcb3ea1247868cf8374e044a7bd
+oid sha256:1dfa5dd032e4a03f440be49b93d0489893f415e88c3769ffa1903e5787dfef9f
 size 6776