Training in progress, step 6, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "gate_proj",
     "v_proj",
-    "o_proj",
     "k_proj",
-    "q_proj",
-    "up_proj"
+    "gate_proj",
+    "o_proj",
+    "down_proj",
+    "up_proj",
+    "q_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:b3e868b930f02b4fa547a12fe1eb3c6b45f2144772990bb5891352cf5115c54d
+oid sha256:62faaa3e70599a0c452efda01f1ce6608ad6f8cc6ac0a0e2b7e2bea7dec9663e
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c00dd59a9b7b6ff1575563c6a0fa2f9ae3e14f5cb4b7ad9756e53a0cd0f79f6f
+oid sha256:a082c3c593f37a57a38d51e7fa0e783b80fd6aacf393b7c05ebfb96566d1a7d6
 size 160172858

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e2355e43fd44f1d9860c59f45b4d1039afaad0a42f79d076c0667863cd27cb0
+oid sha256:73aa535a34327d8ff7e12fc9f716f24d876cbdb9f9fc9bc13d972c1b7c68dd32
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,16 +1,16 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0007184768291222608,
+  "epoch": 0.0014369536582445215,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.00023949227637408692,
-      "grad_norm": 5.190128803253174,
+      "grad_norm": 5.556643962860107,
       "learning_rate": 2e-05,
       "loss": 2.4864,
       "step": 1
@@ -18,32 +18,61 @@
     {
       "epoch": 0.00023949227637408692,
       "eval_loss": 3.196671962738037,
-      "eval_runtime": 163.6418,
-      "eval_samples_per_second": 5.378,
-      "eval_steps_per_second": 5.378,
+      "eval_runtime": 164.0333,
+      "eval_samples_per_second": 5.365,
+      "eval_steps_per_second": 5.365,
       "step": 1
     },
     {
       "epoch": 0.00047898455274817384,
-      "grad_norm": 3.8827998638153076,
+      "grad_norm": 4.200049877166748,
       "learning_rate": 4e-05,
       "loss": 3.3358,
       "step": 2
     },
     {
       "epoch": 0.0007184768291222608,
-      "grad_norm": 3.203981876373291,
+      "grad_norm": 3.4988012313842773,
       "learning_rate": 6e-05,
-      "loss": 3.3946,
+      "loss": 3.3931,
       "step": 3
     },
     {
       "epoch": 0.0007184768291222608,
-      "eval_loss": 3.0946106910705566,
-      "eval_runtime": 162.7901,
-      "eval_samples_per_second": 5.406,
-      "eval_steps_per_second": 5.406,
+      "eval_loss": 3.08847713470459,
+      "eval_runtime": 164.5024,
+      "eval_samples_per_second": 5.349,
+      "eval_steps_per_second": 5.349,
       "step": 3
+    },
+    {
+      "epoch": 0.0009579691054963477,
+      "grad_norm": 3.2402377128601074,
+      "learning_rate": 8e-05,
+      "loss": 2.761,
+      "step": 4
+    },
+    {
+      "epoch": 0.0011974613818704347,
+      "grad_norm": 3.507751703262329,
+      "learning_rate": 0.0001,
+      "loss": 2.7889,
+      "step": 5
+    },
+    {
+      "epoch": 0.0014369536582445215,
+      "grad_norm": 2.906939744949341,
+      "learning_rate": 0.00012,
+      "loss": 1.8125,
+      "step": 6
+    },
+    {
+      "epoch": 0.0014369536582445215,
+      "eval_loss": 2.6185643672943115,
+      "eval_runtime": 165.0188,
+      "eval_samples_per_second": 5.333,
+      "eval_steps_per_second": 5.333,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 492949267808256.0,
+  "total_flos": 985898535616512.0,
   "train_batch_size": 1,
   "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:d9c99d0e2f5b8cc5e216c0a981ae420dfd0fdc085832d4176287c753653f2960
+oid sha256:c8e3eaba4fc887116ba05575a8a64bfbe0629dae4f12cb37cac79d895993962b
 size 6776