Training in progress, step 10, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "gate_proj",
-    "v_proj",
-    "q_proj",
+    "o_proj",
     "up_proj",
+    "v_proj",
     "down_proj",
-    "o_proj"
+    "gate_proj",
+    "q_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 sha256:649737bef523858266e489ecb7a9ae8c584cbd11006dafee36be2fef8781bce4
+oid sha256:33343daee1ee6a6dc33af650613c9a7aecae25d982b09a8d3967d27eaa324c19
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11fde3094c1a2e3501de92eeb58134af21a5fcbc19b97f49f503ae9e0efbf79b
+oid sha256:1e8fa0d65874b89f3e9215ff9af2bec65b01e72410e4b6d53fd8c4c8cb5cabf1
 size 18810036

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8e8ccd03ceafdc89562e6c964f3a5653634131e26d07ce59dc6bdd4d1eded84
+oid sha256:19450a7f1f81f4b8381e6b4499d583d2beae56e265c1a11c35f7f6ed8254f893
 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": 0.01337295690936107,
+  "epoch": 0.014858841010401188,
   "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": 0.0014858841010401188,
-      "grad_norm": 23.471858978271484,
+      "grad_norm": 23.501811981201172,
       "learning_rate": 2e-05,
       "loss": 10.0714,
       "step": 1
@@ -18,90 +18,97 @@
     {
       "epoch": 0.0014858841010401188,
       "eval_loss": 9.684135437011719,
-      "eval_runtime": 31.905,
-      "eval_samples_per_second": 8.901,
-      "eval_steps_per_second": 4.451,
+      "eval_runtime": 28.856,
+      "eval_samples_per_second": 9.842,
+      "eval_steps_per_second": 4.921,
       "step": 1
     },
     {
       "epoch": 0.0029717682020802376,
-      "grad_norm": 24.766386032104492,
+      "grad_norm": 24.45585823059082,
       "learning_rate": 4e-05,
       "loss": 9.0429,
       "step": 2
     },
     {
       "epoch": 0.004457652303120356,
-      "grad_norm": 21.197526931762695,
+      "grad_norm": 21.319435119628906,
       "learning_rate": 6e-05,
-      "loss": 9.8085,
+      "loss": 9.82,
       "step": 3
     },
     {
       "epoch": 0.004457652303120356,
-      "eval_loss": 9.287724494934082,
-      "eval_runtime": 30.5477,
-      "eval_samples_per_second": 9.297,
-      "eval_steps_per_second": 4.648,
+      "eval_loss": 9.280440330505371,
+      "eval_runtime": 31.5724,
+      "eval_samples_per_second": 8.995,
+      "eval_steps_per_second": 4.498,
       "step": 3
     },
     {
       "epoch": 0.005943536404160475,
-      "grad_norm": 24.982576370239258,
+      "grad_norm": 24.67139434814453,
       "learning_rate": 8e-05,
-      "loss": 9.791,
+      "loss": 9.792,
       "step": 4
     },
     {
       "epoch": 0.007429420505200594,
-      "grad_norm": 21.579788208007812,
+      "grad_norm": 21.461652755737305,
       "learning_rate": 0.0001,
-      "loss": 8.7649,
+      "loss": 8.7251,
       "step": 5
     },
     {
       "epoch": 0.008915304606240713,
-      "grad_norm": 20.995973587036133,
+      "grad_norm": 20.924564361572266,
       "learning_rate": 0.00012,
-      "loss": 8.723,
+      "loss": 8.7056,
       "step": 6
     },
     {
       "epoch": 0.008915304606240713,
-      "eval_loss": 6.387414932250977,
-      "eval_runtime": 29.634,
-      "eval_samples_per_second": 9.584,
-      "eval_steps_per_second": 4.792,
+      "eval_loss": 6.362033843994141,
+      "eval_runtime": 29.6806,
+      "eval_samples_per_second": 9.569,
+      "eval_steps_per_second": 4.784,
       "step": 6
     },
     {
       "epoch": 0.010401188707280832,
-      "grad_norm": 36.22989273071289,
+      "grad_norm": 33.954002380371094,
       "learning_rate": 0.00014,
-      "loss": 6.0263,
+      "loss": 5.947,
       "step": 7
     },
     {
       "epoch": 0.01188707280832095,
-      "grad_norm": 17.54269790649414,
+      "grad_norm": 16.948091506958008,
       "learning_rate": 0.00016,
-      "loss": 5.0566,
+      "loss": 5.0426,
       "step": 8
     },
     {
       "epoch": 0.01337295690936107,
-      "grad_norm": 24.35970115661621,
+      "grad_norm": 24.004894256591797,
       "learning_rate": 0.00018,
-      "loss": 4.6364,
+      "loss": 4.6051,
       "step": 9
     },
     {
       "epoch": 0.01337295690936107,
-      "eval_loss": 3.430145025253296,
-      "eval_runtime": 28.208,
-      "eval_samples_per_second": 10.068,
-      "eval_steps_per_second": 5.034,
+      "eval_loss": 3.463918447494507,
+      "eval_runtime": 30.3769,
+      "eval_samples_per_second": 9.349,
+      "eval_steps_per_second": 4.675,
       "step": 9
+    },
+    {
+      "epoch": 0.014858841010401188,
+      "grad_norm": 15.860657691955566,
+      "learning_rate": 0.0002,
+      "loss": 3.0136,
+      "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": 648858870743040.0,
+  "total_flos": 720954300825600.0,
   "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 sha256:8910c913daa72aa2ee1f187619a3777cdd3adf003c43811644b4605775f3d33a
+oid sha256:a5235a99abae682b5b1490f6a9df0a8861b8e91f3470797e2fef11dca025dbf7
 size 6776