Training in progress, step 9, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
+    "k_proj",
+    "down_proj",
+    "up_proj",
     "v_proj",
     "q_proj",
-    "down_proj",
-    "k_proj",
-    "gate_proj",
-    "up_proj"
+    "o_proj",
+    "gate_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:b86f1d75825127d6bdce267195ecc8e3b03228a53b17b923021815e62f1f022b
+oid sha256:28d818039cbf8e1612d5cb1306c0c9eb439cd19b8a3cf107aba686263f3a10f3
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39e84f08cb28b8a7c6faf406e8b310afe9a91c97e6c247d547cc2b4ce7102915
+oid sha256:26404cd7cf4589950b21359f9d386d0347e7ef5b27e15bcc3395c3898f572d0f
 size 168037178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:631dfb2aa9ae256eca5748a1b2ab04547dfc14e5e8346db748407ed5d049499d
+oid sha256:fea4a6c63434c27a483922b729f3295cf32c5e237d07366009f63d639620f157
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2972d8cacb091bd0e98bfff54b2e4933301753087ce149a9bf9a205a5e2d795
+oid sha256:26a93b2a1f4b5368650119fe6e0d6eec6d19cda6badeba4d21943ab48964fa00
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.25,
+  "epoch": 0.75,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -12,38 +12,96 @@
       "epoch": 0.08333333333333333,
       "grad_norm": NaN,
       "learning_rate": 0.0,
-      "loss": 1.4927,
+      "loss": 1.4924,
       "step": 1
     },
     {
       "epoch": 0.08333333333333333,
-      "eval_loss": 1.4977792501449585,
-      "eval_runtime": 0.453,
-      "eval_samples_per_second": 6.622,
-      "eval_steps_per_second": 6.622,
+      "eval_loss": 1.4975985288619995,
+      "eval_runtime": 0.1911,
+      "eval_samples_per_second": 15.701,
+      "eval_steps_per_second": 15.701,
       "step": 1
     },
     {
       "epoch": 0.16666666666666666,
-      "grad_norm": 4.665465831756592,
+      "grad_norm": 5.183752536773682,
       "learning_rate": 2e-05,
-      "loss": 1.307,
+      "loss": 1.3074,
       "step": 2
     },
     {
       "epoch": 0.25,
-      "grad_norm": 5.513491153717041,
+      "grad_norm": 6.239664077758789,
       "learning_rate": 4e-05,
-      "loss": 1.5735,
+      "loss": 1.5739,
       "step": 3
     },
     {
       "epoch": 0.25,
-      "eval_loss": 1.4473786354064941,
-      "eval_runtime": 0.4679,
-      "eval_samples_per_second": 6.412,
-      "eval_steps_per_second": 6.412,
+      "eval_loss": 1.4466005563735962,
+      "eval_runtime": 0.211,
+      "eval_samples_per_second": 14.216,
+      "eval_steps_per_second": 14.216,
       "step": 3
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 5.012392044067383,
+      "learning_rate": 6e-05,
+      "loss": 1.2793,
+      "step": 4
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 3.691774845123291,
+      "learning_rate": 8e-05,
+      "loss": 1.3057,
+      "step": 5
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.0195882320404053,
+      "learning_rate": 0.0001,
+      "loss": 1.0885,
+      "step": 6
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 0.8231927752494812,
+      "eval_runtime": 0.2024,
+      "eval_samples_per_second": 14.826,
+      "eval_steps_per_second": 14.826,
+      "step": 6
+    },
+    {
+      "epoch": 0.5833333333333334,
+      "grad_norm": 2.5046184062957764,
+      "learning_rate": 0.00012,
+      "loss": 0.8365,
+      "step": 7
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 2.7154762744903564,
+      "learning_rate": 0.00014,
+      "loss": 0.5475,
+      "step": 8
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 2.8666529655456543,
+      "learning_rate": 0.00016,
+      "loss": 0.2414,
+      "step": 9
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 0.049252700060606,
+      "eval_runtime": 0.2077,
+      "eval_samples_per_second": 14.444,
+      "eval_steps_per_second": 14.444,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -63,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 554869274443776.0,
+  "total_flos": 1664607823331328.0,
   "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:ab37ef2135f6555964c7f23e135ed3a58c3b21e0a8dfdabb28e1c2f6cc491bb9
+oid sha256:d5fa11f84d8d8e5e8936ae65e6012c835679c9ed6678232c43544c849861d322
 size 6776