Training in progress, step 9, checkpoint

last-checkpoint/adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "dense_h_to_4h",
-    "query_key_value",
     "dense",
-    "dense_4h_to_h"
+    "query_key_value",
+    "dense_4h_to_h",
+    "dense_h_to_4h"
   ],
   "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 sha256:6465b0e2f785246fba367e5d6e13428427c959a4a196f8343337934a404fe369
+oid sha256:314ad9225a3f614d44c968651caec9bfdf68294130e38469dad747c426d81625
 size 33572288

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3144c8f54a6b0cc48cc960939c5a7a198e7d506247c50b1949978cb7cb195740
+oid sha256:1d46560164c0582af94064e6059dbbb1cf31f32a78166909a083e597d274678b
 size 17190970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7cec7fa95fb16b09232bf47470bd56c852288bce7d205fc837860a8a1d8db12
+oid sha256:b1ae6309517a2108e6bd10ea1fd8da0edc71a65cb14916086f3915020657220a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,16 +1,16 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.013036393264530146,
+  "epoch": 0.01955458989679522,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.0021727322107550242,
-      "grad_norm": 38.3082275390625,
+      "grad_norm": 37.16297912597656,
       "learning_rate": 2e-05,
       "loss": 26.2925,
       "step": 1
@@ -18,61 +18,90 @@
     {
       "epoch": 0.0021727322107550242,
       "eval_loss": 6.362123489379883,
-      "eval_runtime": 69.9182,
-      "eval_samples_per_second": 2.775,
-      "eval_steps_per_second": 1.387,
+      "eval_runtime": 69.8308,
+      "eval_samples_per_second": 2.778,
+      "eval_steps_per_second": 1.389,
       "step": 1
     },
     {
       "epoch": 0.0043454644215100485,
-      "grad_norm": 34.35226821899414,
+      "grad_norm": 32.820220947265625,
       "learning_rate": 4e-05,
       "loss": 23.3629,
       "step": 2
     },
     {
       "epoch": 0.006518196632265073,
-      "grad_norm": 46.58251953125,
+      "grad_norm": 45.58674621582031,
       "learning_rate": 6e-05,
-      "loss": 31.458,
+      "loss": 31.4505,
       "step": 3
     },
     {
       "epoch": 0.006518196632265073,
-      "eval_loss": 6.052692413330078,
-      "eval_runtime": 69.8071,
-      "eval_samples_per_second": 2.779,
-      "eval_steps_per_second": 1.39,
+      "eval_loss": 6.055120944976807,
+      "eval_runtime": 68.8054,
+      "eval_samples_per_second": 2.82,
+      "eval_steps_per_second": 1.41,
       "step": 3
     },
     {
       "epoch": 0.008690928843020097,
-      "grad_norm": 34.892906188964844,
+      "grad_norm": 33.71705627441406,
       "learning_rate": 8e-05,
-      "loss": 22.7088,
+      "loss": 22.7458,
       "step": 4
     },
     {
       "epoch": 0.010863661053775122,
-      "grad_norm": 27.14177703857422,
+      "grad_norm": 26.417665481567383,
       "learning_rate": 0.0001,
-      "loss": 19.6406,
+      "loss": 19.5417,
       "step": 5
     },
     {
       "epoch": 0.013036393264530146,
-      "grad_norm": 33.119747161865234,
+      "grad_norm": 31.988718032836914,
       "learning_rate": 0.00012,
-      "loss": 24.4518,
+      "loss": 24.3794,
       "step": 6
     },
     {
       "epoch": 0.013036393264530146,
-      "eval_loss": 4.772887706756592,
-      "eval_runtime": 70.422,
-      "eval_samples_per_second": 2.755,
-      "eval_steps_per_second": 1.377,
+      "eval_loss": 4.7808332443237305,
+      "eval_runtime": 67.3901,
+      "eval_samples_per_second": 2.879,
+      "eval_steps_per_second": 1.439,
       "step": 6
+    },
+    {
+      "epoch": 0.015209125475285171,
+      "grad_norm": 29.322267532348633,
+      "learning_rate": 0.00014,
+      "loss": 19.7093,
+      "step": 7
+    },
+    {
+      "epoch": 0.017381857686040194,
+      "grad_norm": 27.37926483154297,
+      "learning_rate": 0.00016,
+      "loss": 18.7525,
+      "step": 8
+    },
+    {
+      "epoch": 0.01955458989679522,
+      "grad_norm": 28.797134399414062,
+      "learning_rate": 0.00018,
+      "loss": 17.7134,
+      "step": 9
+    },
+    {
+      "epoch": 0.01955458989679522,
+      "eval_loss": 3.6513190269470215,
+      "eval_runtime": 68.1618,
+      "eval_samples_per_second": 2.846,
+      "eval_steps_per_second": 1.423,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1081911388667904.0,
+  "total_flos": 1622867083001856.0,
   "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:b5626cd2613597d38b016ac503b35d867aeed1b5b31a1151465dc38b87f3fc7b
+oid sha256:7039ee5e93e39ae75f53f38b044442799d1e30cd7ff9a83e519c275615c657cc
 size 6776