Training in progress, step 9, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
     "k_proj",
+    "q_proj",
+    "o_proj",
     "down_proj",
+    "gate_proj",
     "v_proj",
-    "up_proj",
-    "o_proj",
-    "gate_proj"
+    "up_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:c5af6ceb3181bdf7e95868525dbe4d63abbe2473764de299720779b4cbec0c86
+oid sha256:da65eabaff7444caebfca33a37a9f8c43cd8d44d08a32899b2ea4fe748ab1eb4
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58127ec95c47906630700b67ebefd82002b7f15d052f046d10bd905bba926c37
+oid sha256:a0ab1969217299d0f844eca4653c2e624c7a19742be4538b61c63d07014ecf91
 size 18810036

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6c5fa2407d16d691efc64965c095a88cbd3aca96aefe47eb8a1e50f4bcded56
+oid sha256:01ae0673394c6d0448d87a05b8dce85b58d04fafa4d6c418a5ee6c92aeaab53d
 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

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.013793103448275862,
+  "epoch": 0.020689655172413793,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -18,9 +18,9 @@
     {
       "epoch": 0.0022988505747126436,
       "eval_loss": NaN,
-      "eval_runtime": 55.532,
-      "eval_samples_per_second": 3.313,
-      "eval_steps_per_second": 1.657,
+      "eval_runtime": 42.2453,
+      "eval_samples_per_second": 4.356,
+      "eval_steps_per_second": 2.178,
       "step": 1
     },
     {
@@ -40,9 +40,9 @@
     {
       "epoch": 0.006896551724137931,
       "eval_loss": NaN,
-      "eval_runtime": 54.6552,
-      "eval_samples_per_second": 3.367,
-      "eval_steps_per_second": 1.683,
+      "eval_runtime": 55.0777,
+      "eval_samples_per_second": 3.341,
+      "eval_steps_per_second": 1.67,
       "step": 3
     },
     {
@@ -69,10 +69,39 @@
     {
       "epoch": 0.013793103448275862,
       "eval_loss": NaN,
-      "eval_runtime": 54.5301,
-      "eval_samples_per_second": 3.374,
-      "eval_steps_per_second": 1.687,
+      "eval_runtime": 54.6418,
+      "eval_samples_per_second": 3.367,
+      "eval_steps_per_second": 1.684,
       "step": 6
+    },
+    {
+      "epoch": 0.016091954022988506,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.01839080459770115,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.020689655172413793,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.020689655172413793,
+      "eval_loss": NaN,
+      "eval_runtime": 54.7073,
+      "eval_samples_per_second": 3.363,
+      "eval_steps_per_second": 1.682,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 432572580495360.0,
+  "total_flos": 648858870743040.0,
   "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 sha256:1f6b294cad946c00780426710004bacbf6fd30dfe8b06f26312ddc12c2facb93
+oid sha256:d591a82bd15320e6a861c112681dce84191047c1aa2c6eed1c86e87e1a090555
 size 6776