Training in progress, step 3, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "k_proj",
     "up_proj",
-    "o_proj",
-    "down_proj",
+    "q_proj",
+    "k_proj",
     "gate_proj",
-    "q_proj"
+    "v_proj",
+    "down_proj",
+    "o_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:d6fa4e0625a24aabbb185cc234d8f5955f75f854ca1a7c11e3dde6ee642e7b1a
+oid sha256:cad28daf33b7dafd86e305c5db8b3a13ab5993bb7e66956b292d6805d9d7f83c
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21da55f12a8bb723aadff59bd1ff8ec6c5b096c5bf47beb2a79d520de32261f9
+oid sha256:4dc7cb2bb1a68ab1ed9aa96981162e12208d077d991e7765e0a79aaf279f8213
 size 39398

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c12066a9c624fe38430ff3feea2dc6451e9f1a920255c11680c737a33d2c53a0
+oid sha256:464e6cdff3f8548ba79ace3859c72e6b06d1e045e69932eb75c584ad0e8918c8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
 size 1064

last-checkpoint/trainer_state.json

@@ -1,16 +1,16 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005608524957936063,
+  "epoch": 0.0016825574873808188,
   "eval_steps": 3,
-  "global_step": 10,
+  "global_step": 3,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.0005608524957936063,
-      "grad_norm": 0.01451126579195261,
+      "grad_norm": 0.014971356838941574,
       "learning_rate": 2e-05,
       "loss": 11.9315,
       "step": 1
@@ -18,97 +18,32 @@
     {
       "epoch": 0.0005608524957936063,
       "eval_loss": 11.931306838989258,
-      "eval_runtime": 2.6729,
-      "eval_samples_per_second": 280.967,
-      "eval_steps_per_second": 140.67,
+      "eval_runtime": 2.6806,
+      "eval_samples_per_second": 280.162,
+      "eval_steps_per_second": 140.267,
       "step": 1
     },
     {
       "epoch": 0.0011217049915872126,
-      "grad_norm": 0.008208751678466797,
+      "grad_norm": 0.008743230253458023,
       "learning_rate": 4e-05,
       "loss": 11.9304,
       "step": 2
     },
     {
       "epoch": 0.0016825574873808188,
-      "grad_norm": 0.01280900463461876,
+      "grad_norm": 0.014676544815301895,
       "learning_rate": 6e-05,
       "loss": 11.9319,
       "step": 3
     },
     {
       "epoch": 0.0016825574873808188,
-      "eval_loss": 11.931303977966309,
-      "eval_runtime": 2.7222,
-      "eval_samples_per_second": 275.878,
-      "eval_steps_per_second": 138.123,
+      "eval_loss": 11.931302070617676,
+      "eval_runtime": 2.718,
+      "eval_samples_per_second": 276.306,
+      "eval_steps_per_second": 138.337,
       "step": 3
-    },
-    {
-      "epoch": 0.002243409983174425,
-      "grad_norm": 0.015532244928181171,
-      "learning_rate": 8e-05,
-      "loss": 11.9328,
-      "step": 4
-    },
-    {
-      "epoch": 0.0028042624789680315,
-      "grad_norm": 0.018273837864398956,
-      "learning_rate": 0.0001,
-      "loss": 11.9248,
-      "step": 5
-    },
-    {
-      "epoch": 0.0033651149747616375,
-      "grad_norm": 0.009271212853491306,
-      "learning_rate": 0.00012,
-      "loss": 11.926,
-      "step": 6
-    },
-    {
-      "epoch": 0.0033651149747616375,
-      "eval_loss": 11.931289672851562,
-      "eval_runtime": 2.7407,
-      "eval_samples_per_second": 274.021,
-      "eval_steps_per_second": 137.193,
-      "step": 6
-    },
-    {
-      "epoch": 0.003925967470555244,
-      "grad_norm": 0.011145409196615219,
-      "learning_rate": 0.00014,
-      "loss": 11.9324,
-      "step": 7
-    },
-    {
-      "epoch": 0.00448681996634885,
-      "grad_norm": 0.006263264454901218,
-      "learning_rate": 0.00016,
-      "loss": 11.9349,
-      "step": 8
-    },
-    {
-      "epoch": 0.005047672462142457,
-      "grad_norm": 0.01308696623891592,
-      "learning_rate": 0.00018,
-      "loss": 11.9287,
-      "step": 9
-    },
-    {
-      "epoch": 0.005047672462142457,
-      "eval_loss": 11.93126392364502,
-      "eval_runtime": 2.7092,
-      "eval_samples_per_second": 277.203,
-      "eval_steps_per_second": 138.786,
-      "step": 9
-    },
-    {
-      "epoch": 0.005608524957936063,
-      "grad_norm": 0.007905536331236362,
-      "learning_rate": 0.0002,
-      "loss": 11.9335,
-      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -123,12 +58,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 1211154432.0,
+  "total_flos": 384024576.0,
   "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 sha256:9b2e13eaf4a3969f7bbaee0cc10406e462093e1d60ff2d3598528c7050a9aef7
+oid sha256:4e368bdd84e5e8a862c05c5eba45118a0b96140e8692046377c32663bf9c3f72
 size 6776