Training in progress, step 9, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "up_proj",
-    "v_proj",
+    "gate_proj",
+    "o_proj",
     "k_proj",
+    "v_proj",
+    "q_proj",
     "down_proj",
-    "gate_proj",
-    "o_proj"
+    "up_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:dfc76e68eb2eea32a4b5a45319da1f62de0cad86e3dfa674fa790d6e3e8420e7
+oid sha256:0e040314da350808ad16b7a5df1d334eddec92464e45c1ee61b68dd5cd82d8f7
 size 30322120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd1c939360354bc1039dafa258cb7065ecd9ef0a083d0b31a3dd370b927ce6fe
+oid sha256:023c610d7d9a89c9b50e551da44d1fedde5088b156a3bfeb824c17537862fb0f
 size 15768084

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c3490f66f3193c19d960a03b365425045c9218364a7eba1fbfdba254d9a4965
+oid sha256:d84a5cf2454179937316496e4212e2e56502a7858df2afe7855b38d36059da33
 size 14244

last-checkpoint/scheduler.pt

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

last-checkpoint/trainer_state.json

@@ -1,16 +1,16 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.011379800853485065,
+  "epoch": 0.010241820768136558,
   "eval_steps": 3,
-  "global_step": 10,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.0011379800853485065,
-      "grad_norm": 11.469493865966797,
+      "grad_norm": 11.28669261932373,
       "learning_rate": 2e-05,
       "loss": 4.9874,
       "step": 1
@@ -18,97 +18,90 @@
     {
       "epoch": 0.0011379800853485065,
       "eval_loss": 5.444311618804932,
-      "eval_runtime": 215.365,
-      "eval_samples_per_second": 1.718,
-      "eval_steps_per_second": 0.859,
+      "eval_runtime": 263.497,
+      "eval_samples_per_second": 1.404,
+      "eval_steps_per_second": 0.702,
       "step": 1
     },
     {
       "epoch": 0.002275960170697013,
-      "grad_norm": 10.285298347473145,
+      "grad_norm": 10.132047653198242,
       "learning_rate": 4e-05,
       "loss": 4.0493,
       "step": 2
     },
     {
       "epoch": 0.0034139402560455193,
-      "grad_norm": 14.50537109375,
+      "grad_norm": 13.788056373596191,
       "learning_rate": 6e-05,
-      "loss": 5.1435,
+      "loss": 5.1544,
       "step": 3
     },
     {
       "epoch": 0.0034139402560455193,
-      "eval_loss": 5.317582130432129,
-      "eval_runtime": 262.8446,
-      "eval_samples_per_second": 1.408,
-      "eval_steps_per_second": 0.704,
+      "eval_loss": 5.3216962814331055,
+      "eval_runtime": 263.6528,
+      "eval_samples_per_second": 1.403,
+      "eval_steps_per_second": 0.702,
       "step": 3
     },
     {
       "epoch": 0.004551920341394026,
-      "grad_norm": 9.632436752319336,
+      "grad_norm": 9.466752052307129,
       "learning_rate": 8e-05,
-      "loss": 4.2553,
+      "loss": 4.2767,
       "step": 4
     },
     {
       "epoch": 0.005689900426742532,
-      "grad_norm": 21.725357055664062,
+      "grad_norm": 21.691171646118164,
       "learning_rate": 0.0001,
-      "loss": 6.9753,
+      "loss": 6.9685,
       "step": 5
     },
     {
       "epoch": 0.0068278805120910386,
-      "grad_norm": 16.968942642211914,
+      "grad_norm": 16.943603515625,
       "learning_rate": 0.00012,
-      "loss": 4.5616,
+      "loss": 4.566,
       "step": 6
     },
     {
       "epoch": 0.0068278805120910386,
-      "eval_loss": 4.071743488311768,
-      "eval_runtime": 263.7024,
-      "eval_samples_per_second": 1.403,
-      "eval_steps_per_second": 0.702,
+      "eval_loss": 4.045292854309082,
+      "eval_runtime": 264.6413,
+      "eval_samples_per_second": 1.398,
+      "eval_steps_per_second": 0.699,
       "step": 6
     },
     {
       "epoch": 0.007965860597439544,
-      "grad_norm": 9.20816707611084,
+      "grad_norm": 9.648813247680664,
       "learning_rate": 0.00014,
-      "loss": 3.403,
+      "loss": 3.3786,
       "step": 7
     },
     {
       "epoch": 0.009103840682788052,
-      "grad_norm": 8.23747730255127,
+      "grad_norm": 8.042987823486328,
       "learning_rate": 0.00016,
-      "loss": 2.8285,
+      "loss": 2.8221,
       "step": 8
     },
     {
       "epoch": 0.010241820768136558,
-      "grad_norm": 7.336373329162598,
+      "grad_norm": 7.113251686096191,
       "learning_rate": 0.00018,
-      "loss": 2.8244,
+      "loss": 2.8156,
       "step": 9
     },
     {
       "epoch": 0.010241820768136558,
-      "eval_loss": 2.3922410011291504,
-      "eval_runtime": 247.1108,
-      "eval_samples_per_second": 1.497,
-      "eval_steps_per_second": 0.749,
+      "eval_loss": 2.4009945392608643,
+      "eval_runtime": 144.3345,
+      "eval_samples_per_second": 2.563,
+      "eval_steps_per_second": 1.282,
       "step": 9
-    },
-    {
-      "epoch": 0.011379800853485065,
-      "grad_norm": 4.929776668548584,
-      "learning_rate": 0.0002,
-      "loss": 1.8502,
-      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -123,12 +116,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 621231451668480.0,
+  "total_flos": 559108306501632.0,
   "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 sha256:119ef8fb7b1277eae8902d9416a71adad7d6ea0a771ac9ee38007e852b26f5bd
+oid sha256:5d0dbccc047e96de455f894a33a9e5fda5af77f6374c72803528d53dd977b166
 size 6712