Training in progress, step 3, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
     "gate_proj",
-    "k_proj",
+    "q_proj",
     "o_proj",
     "v_proj",
-    "q_proj",
-    "up_proj"
+    "up_proj",
+    "down_proj",
+    "k_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 sha256:6c6105175f7aadde6ac68a7a43db8b0e0bd0316e66cfe1a5ef89e31825ece5a2
+oid sha256:2411a64ccd86f00c1c52831ee3125cdfa792e844a2a3f8508feb31e393533382
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dcea665996156ce85a277f1be95e2396dac94e1e72b747a46580cfe7c4d6a5b
+oid sha256:13b8e8dd830abfcf2c84f96057c3f85cf3ba61185dc9baa659d44ff68f96f569
 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": 0.012571261264383793,
+      "grad_norm": 0.012190197594463825,
       "learning_rate": 2e-05,
       "loss": 11.9315,
       "step": 1
@@ -18,97 +18,32 @@
     {
       "epoch": 0.0005608524957936063,
       "eval_loss": 11.931304931640625,
-      "eval_runtime": 2.8665,
-      "eval_samples_per_second": 261.991,
-      "eval_steps_per_second": 131.17,
+      "eval_runtime": 2.8225,
+      "eval_samples_per_second": 266.081,
+      "eval_steps_per_second": 133.217,
       "step": 1
     },
     {
       "epoch": 0.0011217049915872126,
-      "grad_norm": 0.008350237272679806,
+      "grad_norm": 0.007718841079622507,
       "learning_rate": 4e-05,
       "loss": 11.9304,
       "step": 2
     },
     {
       "epoch": 0.0016825574873808188,
-      "grad_norm": 0.01197201106697321,
+      "grad_norm": 0.013811795972287655,
       "learning_rate": 6e-05,
       "loss": 11.9319,
       "step": 3
     },
     {
       "epoch": 0.0016825574873808188,
-      "eval_loss": 11.931304931640625,
-      "eval_runtime": 2.8773,
-      "eval_samples_per_second": 261.006,
-      "eval_steps_per_second": 130.677,
+      "eval_loss": 11.931303977966309,
+      "eval_runtime": 2.8145,
+      "eval_samples_per_second": 266.836,
+      "eval_steps_per_second": 133.596,
       "step": 3
-    },
-    {
-      "epoch": 0.002243409983174425,
-      "grad_norm": 0.015558863990008831,
-      "learning_rate": 8e-05,
-      "loss": 11.9328,
-      "step": 4
-    },
-    {
-      "epoch": 0.0028042624789680315,
-      "grad_norm": 0.015790285542607307,
-      "learning_rate": 0.0001,
-      "loss": 11.9248,
-      "step": 5
-    },
-    {
-      "epoch": 0.0033651149747616375,
-      "grad_norm": 0.008313722908496857,
-      "learning_rate": 0.00012,
-      "loss": 11.926,
-      "step": 6
-    },
-    {
-      "epoch": 0.0033651149747616375,
-      "eval_loss": 11.931292533874512,
-      "eval_runtime": 2.9482,
-      "eval_samples_per_second": 254.732,
-      "eval_steps_per_second": 127.536,
-      "step": 6
-    },
-    {
-      "epoch": 0.003925967470555244,
-      "grad_norm": 0.009867842309176922,
-      "learning_rate": 0.00014,
-      "loss": 11.9324,
-      "step": 7
-    },
-    {
-      "epoch": 0.00448681996634885,
-      "grad_norm": 0.006440632976591587,
-      "learning_rate": 0.00016,
-      "loss": 11.935,
-      "step": 8
-    },
-    {
-      "epoch": 0.005047672462142457,
-      "grad_norm": 0.012027577497065067,
-      "learning_rate": 0.00018,
-      "loss": 11.9287,
-      "step": 9
-    },
-    {
-      "epoch": 0.005047672462142457,
-      "eval_loss": 11.93127155303955,
-      "eval_runtime": 2.9099,
-      "eval_samples_per_second": 258.083,
-      "eval_steps_per_second": 129.213,
-      "step": 9
-    },
-    {
-      "epoch": 0.005608524957936063,
-      "grad_norm": 0.008444417268037796,
-      "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 sha256:02f74e7d17260680db996970c01da41ed0e850712a46237497c92e4669a68733
+oid sha256:e14cf3f03e6b004ff44ef85dde741031d371ba0054dffcbdaa981ef455384430
 size 6776