Training in progress, step 10, checkpoint

last-checkpoint/adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
     "gate_proj",
     "v_proj",
-    "q_proj",
     "up_proj",
+    "o_proj",
     "down_proj",
+    "q_proj",
     "k_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac3498a57ffe26bc52ca1e493121354fa53a86c9591ae6a35635b8779ab03c74
+oid sha256:3efbcb775b1720262a9729aa89b4e2a7f33ef935101a533ff4f86c517bc197ff
 size 30322120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:330c2178862285d0ff254ea768d8b59f187bf803f67933b3a860444427a15929
+oid sha256:1d1c393a6cb2fcecb86f3329142ff43fa3f65823455884e3a22c595e6f721bc6
 size 15768084

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d84a5cf2454179937316496e4212e2e56502a7858df2afe7855b38d36059da33
+oid sha256:3c3490f66f3193c19d960a03b365425045c9218364a7eba1fbfdba254d9a4965
 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": 0.09022556390977443,
+  "epoch": 0.10025062656641603,
   "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": 0.010025062656641603,
-      "grad_norm": 21.28019142150879,
+      "grad_norm": 20.062788009643555,
       "learning_rate": 2e-05,
       "loss": 6.1371,
       "step": 1
@@ -18,90 +18,97 @@
     {
       "epoch": 0.010025062656641603,
       "eval_loss": 6.394162178039551,
-      "eval_runtime": 9.5693,
-      "eval_samples_per_second": 4.494,
-      "eval_steps_per_second": 2.299,
+      "eval_runtime": 9.5073,
+      "eval_samples_per_second": 4.523,
+      "eval_steps_per_second": 2.314,
       "step": 1
     },
     {
       "epoch": 0.020050125313283207,
-      "grad_norm": 24.765010833740234,
+      "grad_norm": 23.640897750854492,
       "learning_rate": 4e-05,
       "loss": 6.6622,
       "step": 2
     },
     {
       "epoch": 0.03007518796992481,
-      "grad_norm": 19.849573135375977,
+      "grad_norm": 18.601524353027344,
       "learning_rate": 6e-05,
-      "loss": 6.6966,
+      "loss": 6.6642,
       "step": 3
     },
     {
       "epoch": 0.03007518796992481,
-      "eval_loss": 6.185020446777344,
-      "eval_runtime": 8.2531,
-      "eval_samples_per_second": 5.21,
-      "eval_steps_per_second": 2.666,
+      "eval_loss": 6.188879013061523,
+      "eval_runtime": 8.1646,
+      "eval_samples_per_second": 5.267,
+      "eval_steps_per_second": 2.695,
       "step": 3
     },
     {
       "epoch": 0.040100250626566414,
-      "grad_norm": 18.815658569335938,
+      "grad_norm": 17.62156105041504,
       "learning_rate": 8e-05,
-      "loss": 5.9323,
+      "loss": 5.9167,
       "step": 4
     },
     {
       "epoch": 0.05012531328320802,
-      "grad_norm": 19.071056365966797,
+      "grad_norm": 17.715669631958008,
       "learning_rate": 0.0001,
-      "loss": 5.4602,
+      "loss": 5.3858,
       "step": 5
     },
     {
       "epoch": 0.06015037593984962,
-      "grad_norm": 26.607534408569336,
+      "grad_norm": 27.59926986694336,
       "learning_rate": 0.00012,
-      "loss": 5.8849,
+      "loss": 5.8808,
       "step": 6
     },
     {
       "epoch": 0.06015037593984962,
-      "eval_loss": 5.290524482727051,
-      "eval_runtime": 8.3367,
-      "eval_samples_per_second": 5.158,
-      "eval_steps_per_second": 2.639,
+      "eval_loss": 5.289012432098389,
+      "eval_runtime": 8.2512,
+      "eval_samples_per_second": 5.211,
+      "eval_steps_per_second": 2.666,
       "step": 6
     },
     {
       "epoch": 0.07017543859649122,
-      "grad_norm": 19.01709747314453,
+      "grad_norm": 18.069259643554688,
       "learning_rate": 0.00014,
-      "loss": 4.9242,
+      "loss": 4.9484,
       "step": 7
     },
     {
       "epoch": 0.08020050125313283,
-      "grad_norm": 24.233760833740234,
+      "grad_norm": 23.07379722595215,
       "learning_rate": 0.00016,
-      "loss": 4.2854,
+      "loss": 4.2756,
       "step": 8
     },
     {
       "epoch": 0.09022556390977443,
-      "grad_norm": 24.025436401367188,
+      "grad_norm": 23.45814323425293,
       "learning_rate": 0.00018,
-      "loss": 4.359,
+      "loss": 4.4603,
       "step": 9
     },
     {
       "epoch": 0.09022556390977443,
-      "eval_loss": 2.969768524169922,
-      "eval_runtime": 8.296,
-      "eval_samples_per_second": 5.183,
-      "eval_steps_per_second": 2.652,
+      "eval_loss": 3.1214287281036377,
+      "eval_runtime": 8.192,
+      "eval_samples_per_second": 5.249,
+      "eval_steps_per_second": 2.686,
       "step": 9
+    },
+    {
+      "epoch": 0.10025062656641603,
+      "grad_norm": 26.12590217590332,
+      "learning_rate": 0.0002,
+      "loss": 3.0215,
+      "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": 559108306501632.0,
+  "total_flos": 621231451668480.0,
   "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 sha256:7388f3e7b07c8c879afb44613463aaecf2dc880d04e9c93c89b5d5ebe5b7c8c8
+oid sha256:9477e1527e6ebd8764da7c6352084cb17361334c458bc27fbb9f06b94a455cce
 size 6776