Training in progress, step 3, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
     "q_proj",
+    "o_proj",
+    "down_proj",
+    "gate_proj",
     "k_proj",
     "v_proj",
-    "up_proj",
-    "down_proj",
-    "o_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:e6b5134c97ff825113887127f3cdd8add96cb3cc61903b7881e2d9383ccaa6b5
+oid sha256:b119141819fc976c7e4bcb769aece8bc68121392df5620dead832ead1583ebd5
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1966a2ee957f38f70c820806f39b5e4f5a49655c89774599a5b1d7522ae6b3ae
+oid sha256:24f47ddd4884e6a4f3bac407a7bb5c7f96019f61a010b4c239e1d97e79684b9c
 size 18810036

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e80e63932c8eae7c99e68576eba41b28c2be6da6d5728e9d2106b0941dfcd24
+oid sha256:8580306d32b005c0733c680a2aa90baffc7bb3fab9f44ba259f139790c0142d8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01153070049005477,
+  "epoch": 0.003459210147016431,
   "eval_steps": 3,
-  "global_step": 10,
+  "global_step": 3,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -18,9 +18,9 @@
     {
       "epoch": 0.0011530700490054772,
       "eval_loss": NaN,
-      "eval_runtime": 55.7934,
-      "eval_samples_per_second": 6.56,
-      "eval_steps_per_second": 3.28,
+      "eval_runtime": 55.6229,
+      "eval_samples_per_second": 6.58,
+      "eval_steps_per_second": 3.29,
       "step": 1
     },
     {
@@ -40,75 +40,10 @@
     {
       "epoch": 0.003459210147016431,
       "eval_loss": NaN,
-      "eval_runtime": 55.125,
-      "eval_samples_per_second": 6.639,
-      "eval_steps_per_second": 3.32,
+      "eval_runtime": 54.9395,
+      "eval_samples_per_second": 6.662,
+      "eval_steps_per_second": 3.331,
       "step": 3
-    },
-    {
-      "epoch": 0.004612280196021909,
-      "grad_norm": NaN,
-      "learning_rate": 8e-05,
-      "loss": 0.0,
-      "step": 4
-    },
-    {
-      "epoch": 0.005765350245027385,
-      "grad_norm": NaN,
-      "learning_rate": 0.0001,
-      "loss": 0.0,
-      "step": 5
-    },
-    {
-      "epoch": 0.006918420294032862,
-      "grad_norm": NaN,
-      "learning_rate": 0.00012,
-      "loss": 0.0,
-      "step": 6
-    },
-    {
-      "epoch": 0.006918420294032862,
-      "eval_loss": NaN,
-      "eval_runtime": 55.2147,
-      "eval_samples_per_second": 6.629,
-      "eval_steps_per_second": 3.314,
-      "step": 6
-    },
-    {
-      "epoch": 0.00807149034303834,
-      "grad_norm": NaN,
-      "learning_rate": 0.00014,
-      "loss": 0.0,
-      "step": 7
-    },
-    {
-      "epoch": 0.009224560392043817,
-      "grad_norm": NaN,
-      "learning_rate": 0.00016,
-      "loss": 0.0,
-      "step": 8
-    },
-    {
-      "epoch": 0.010377630441049293,
-      "grad_norm": NaN,
-      "learning_rate": 0.00018,
-      "loss": 0.0,
-      "step": 9
-    },
-    {
-      "epoch": 0.010377630441049293,
-      "eval_loss": NaN,
-      "eval_runtime": 55.1139,
-      "eval_samples_per_second": 6.641,
-      "eval_steps_per_second": 3.32,
-      "step": 9
-    },
-    {
-      "epoch": 0.01153070049005477,
-      "grad_norm": NaN,
-      "learning_rate": 0.0002,
-      "loss": 0.0,
-      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -123,12 +58,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 720954300825600.0,
+  "total_flos": 216286290247680.0,
   "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 sha256:1a594be05d4b64a4ec99cdd4559dca8a15300c275307b789d2dd84f329dbf2d7
+oid sha256:2b105972566dfcb572ec5164f1a4895b593ad390c4fb517d98c1e7e9914dd96a
 size 6776