Training in progress, step 3, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "q_proj",
+    "up_proj",
+    "o_proj",
     "down_proj",
     "gate_proj",
     "v_proj",
-    "k_proj",
-    "up_proj",
-    "o_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:c07ef9546b4a4208bf6b8e178272bb149eab134b1b0a7701a93e22fded2be6dd
+oid sha256:c823aa9af8e02472424e5f1dec4f575d9079d8a0cfaa93890865d5cf86e20080
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91b838f0603e6e34285dc2b3133f011cc7bcbf22aed025ac31257814f960c862
+oid sha256:5b5fcf15bd242e44d655a57970dccb28a1a1a885e86a328e6fa1aebc857fd3a4
 size 37965300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12652e548395ac54f34186413124cf818db17e2dae781e78f969b6d3fed44e53
+oid sha256:bb4f9fc7124e96f82e322ff0279a3fb1e3cde199fba8ef2ed0889f90c1080507
 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

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0006481721545242416,
+  "epoch": 0.0001944516463572725,
   "eval_steps": 3,
-  "global_step": 10,
+  "global_step": 3,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -18,9 +18,9 @@
     {
       "epoch": 6.481721545242416e-05,
       "eval_loss": NaN,
-      "eval_runtime": 1406.7818,
-      "eval_samples_per_second": 4.618,
-      "eval_steps_per_second": 2.31,
+      "eval_runtime": 1403.1768,
+      "eval_samples_per_second": 4.63,
+      "eval_steps_per_second": 2.315,
       "step": 1
     },
     {
@@ -40,75 +40,10 @@
     {
       "epoch": 0.0001944516463572725,
       "eval_loss": NaN,
-      "eval_runtime": 1403.0446,
-      "eval_samples_per_second": 4.631,
-      "eval_steps_per_second": 2.316,
+      "eval_runtime": 1402.3453,
+      "eval_samples_per_second": 4.633,
+      "eval_steps_per_second": 2.317,
       "step": 3
-    },
-    {
-      "epoch": 0.00025926886180969663,
-      "grad_norm": NaN,
-      "learning_rate": 8e-05,
-      "loss": 0.0,
-      "step": 4
-    },
-    {
-      "epoch": 0.0003240860772621208,
-      "grad_norm": NaN,
-      "learning_rate": 0.0001,
-      "loss": 0.0,
-      "step": 5
-    },
-    {
-      "epoch": 0.000388903292714545,
-      "grad_norm": NaN,
-      "learning_rate": 0.00012,
-      "loss": 0.0,
-      "step": 6
-    },
-    {
-      "epoch": 0.000388903292714545,
-      "eval_loss": NaN,
-      "eval_runtime": 1401.0476,
-      "eval_samples_per_second": 4.637,
-      "eval_steps_per_second": 2.319,
-      "step": 6
-    },
-    {
-      "epoch": 0.00045372050816696913,
-      "grad_norm": NaN,
-      "learning_rate": 0.00014,
-      "loss": 0.0,
-      "step": 7
-    },
-    {
-      "epoch": 0.0005185377236193933,
-      "grad_norm": NaN,
-      "learning_rate": 0.00016,
-      "loss": 0.0,
-      "step": 8
-    },
-    {
-      "epoch": 0.0005833549390718175,
-      "grad_norm": NaN,
-      "learning_rate": 0.00018,
-      "loss": 0.0,
-      "step": 9
-    },
-    {
-      "epoch": 0.0005833549390718175,
-      "eval_loss": NaN,
-      "eval_runtime": 1404.2159,
-      "eval_samples_per_second": 4.627,
-      "eval_steps_per_second": 2.314,
-      "step": 9
-    },
-    {
-      "epoch": 0.0006481721545242416,
-      "grad_norm": NaN,
-      "learning_rate": 0.0002,
-      "loss": 0.0,
-      "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": 2612537673646080.0,
+  "total_flos": 783761302093824.0,
   "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:d810617545e44f0b3d76b6c2b7f77305d0f6c78937de0bba0ad483e919937204
+oid sha256:74400ee19fe1c8d5fd31abc5c98b8f611fe47b7be51e69f01e8a47e86b97fd0f
 size 6776