Training in progress, step 6, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "gate_proj",
-    "o_proj",
-    "q_proj",
     "k_proj",
     "down_proj",
-    "v_proj"
+    "up_proj",
+    "v_proj",
+    "q_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 sha256:1a108caa133c396d44ab9dff2a27d67d96866b2d2cbe83d7bd21100c5417c590
+oid sha256:bcbf06858a2c60c6f7d335522a0fc9e4928ea47704df9578855c158e4b52206a
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2f8108b4db96948fbabd90394bb04c2e00573de0ba6a38725971deb35bd27af
+oid sha256:760c4e18ab7ab170887c10a99b231caf9e23fef29d0d811a737ed5b6d478d603
 size 168037178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:631dfb2aa9ae256eca5748a1b2ab04547dfc14e5e8346db748407ed5d049499d
+oid sha256:e6bf19e75a59ee8c6a96e9c63d30b78c698cbfef05ceb7eb28dd7602d0b1a826
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2972d8cacb091bd0e98bfff54b2e4933301753087ce149a9bf9a205a5e2d795
+oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.25,
+  "epoch": 0.5,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -12,38 +12,67 @@
       "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": 0.3019,
-      "eval_samples_per_second": 9.937,
-      "eval_steps_per_second": 9.937,
+      "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": 4.949731349945068,
+      "grad_norm": 5.183752536773682,
       "learning_rate": 2e-05,
-      "loss": 1.307,
+      "loss": 1.3074,
       "step": 2
     },
     {
       "epoch": 0.25,
-      "grad_norm": 5.8763322830200195,
+      "grad_norm": 6.239664077758789,
       "learning_rate": 4e-05,
-      "loss": 1.5735,
+      "loss": 1.5739,
       "step": 3
     },
     {
       "epoch": 0.25,
-      "eval_loss": 1.4451128244400024,
-      "eval_runtime": 0.4158,
-      "eval_samples_per_second": 7.215,
-      "eval_steps_per_second": 7.215,
+      "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
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 554869274443776.0,
+  "total_flos": 1109738548887552.0,
   "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 sha256:1dfa5dd032e4a03f440be49b93d0489893f415e88c3769ffa1903e5787dfef9f
+oid sha256:d5fa11f84d8d8e5e8936ae65e6012c835679c9ed6678232c43544c849861d322
 size 6776