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",
+    "v_proj",
     "q_proj",
-    "k_proj",
     "down_proj",
-    "v_proj"
+    "k_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 sha256:880b442943ff2aa3e48ebcf36c6976cee9e4e2d9f8eef2811873ac4ca9658696
+oid sha256:7cb8309c738b49a1e48117f7ee5b2f2b3ad6e0c95e9fc86b2be41fe28d1d9520
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffba35bcc4792c076b7cfb45ceb3d53776881bc3f3e4294fa76cd64f44e67298
+oid sha256:2bcbd93bebb8df47076201f623c8139d27f62076b41e4055a169a296523281c7
 size 168037178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b90a19943f8ef28f7f3c1abafd8de7b24ff68c3eda11dffdc748b1a1d989fcb2
+oid sha256:a68cd2a0196a6713af61a6a5ec57d388549ceab000d778970629ba70bc0f12ea
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26a93b2a1f4b5368650119fe6e0d6eec6d19cda6badeba4d21943ab48964fa00
+oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.75,
+  "epoch": 0.5,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -18,90 +18,61 @@
     {
       "epoch": 0.08333333333333333,
       "eval_loss": 1.4977792501449585,
-      "eval_runtime": 0.3019,
-      "eval_samples_per_second": 9.937,
-      "eval_steps_per_second": 9.937,
+      "eval_runtime": 0.453,
+      "eval_samples_per_second": 6.622,
+      "eval_steps_per_second": 6.622,
       "step": 1
     },
     {
       "epoch": 0.16666666666666666,
-      "grad_norm": 4.949731349945068,
+      "grad_norm": 4.665465831756592,
       "learning_rate": 2e-05,
       "loss": 1.307,
       "step": 2
     },
     {
       "epoch": 0.25,
-      "grad_norm": 5.8763322830200195,
+      "grad_norm": 5.513491153717041,
       "learning_rate": 4e-05,
       "loss": 1.5735,
       "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": 1.4473786354064941,
+      "eval_runtime": 0.4679,
+      "eval_samples_per_second": 6.412,
+      "eval_steps_per_second": 6.412,
       "step": 3
     },
     {
       "epoch": 0.3333333333333333,
-      "grad_norm": 4.730646133422852,
+      "grad_norm": 4.566956520080566,
       "learning_rate": 6e-05,
-      "loss": 1.2767,
+      "loss": 1.282,
       "step": 4
     },
     {
       "epoch": 0.4166666666666667,
-      "grad_norm": 3.4440248012542725,
+      "grad_norm": 3.311328649520874,
       "learning_rate": 8e-05,
-      "loss": 1.3011,
+      "loss": 1.3071,
       "step": 5
     },
     {
       "epoch": 0.5,
-      "grad_norm": 2.8259096145629883,
+      "grad_norm": 2.798964262008667,
       "learning_rate": 0.0001,
-      "loss": 1.0815,
+      "loss": 1.0892,
       "step": 6
     },
     {
       "epoch": 0.5,
-      "eval_loss": 0.816199779510498,
-      "eval_runtime": 0.4516,
-      "eval_samples_per_second": 6.643,
-      "eval_steps_per_second": 6.643,
+      "eval_loss": 0.8217151761054993,
+      "eval_runtime": 0.4475,
+      "eval_samples_per_second": 6.705,
+      "eval_steps_per_second": 6.705,
       "step": 6
-    },
-    {
-      "epoch": 0.5833333333333334,
-      "grad_norm": 2.387253522872925,
-      "learning_rate": 0.00012,
-      "loss": 0.8264,
-      "step": 7
-    },
-    {
-      "epoch": 0.6666666666666666,
-      "grad_norm": 2.6841723918914795,
-      "learning_rate": 0.00014,
-      "loss": 0.5359,
-      "step": 8
-    },
-    {
-      "epoch": 0.75,
-      "grad_norm": 2.8740291595458984,
-      "learning_rate": 0.00016,
-      "loss": 0.229,
-      "step": 9
-    },
-    {
-      "epoch": 0.75,
-      "eval_loss": 0.04347331449389458,
-      "eval_runtime": 0.4018,
-      "eval_samples_per_second": 7.467,
-      "eval_steps_per_second": 7.467,
-      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -121,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1664607823331328.0,
+  "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:ab37ef2135f6555964c7f23e135ed3a58c3b21e0a8dfdabb28e1c2f6cc491bb9
 size 6776