Training in progress, step 3, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "up_proj",
     "v_proj",
-    "gate_proj",
-    "k_proj",
     "q_proj",
-    "up_proj",
+    "k_proj",
     "down_proj",
-    "o_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:cd2f52bc1aa3d83a18becd28ae0a60a65a3ba0472b2e8b664119424a002bd50e
+oid sha256:b894d9be2c2964270b076cccdf56e153c3a8523618382f694199064b5b255361
 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": 0.0061823802163833074,
+  "epoch": 0.0018547140649149924,
   "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": 0.0006182380216383308,
       "eval_loss": NaN,
-      "eval_runtime": 104.7531,
-      "eval_samples_per_second": 6.501,
-      "eval_steps_per_second": 3.255,
+      "eval_runtime": 104.9278,
+      "eval_samples_per_second": 6.49,
+      "eval_steps_per_second": 3.25,
       "step": 1
     },
     {
@@ -40,75 +40,10 @@
     {
       "epoch": 0.0018547140649149924,
       "eval_loss": NaN,
-      "eval_runtime": 103.4465,
-      "eval_samples_per_second": 6.583,
-      "eval_steps_per_second": 3.296,
+      "eval_runtime": 103.1072,
+      "eval_samples_per_second": 6.605,
+      "eval_steps_per_second": 3.307,
       "step": 3
-    },
-    {
-      "epoch": 0.002472952086553323,
-      "grad_norm": NaN,
-      "learning_rate": 8e-05,
-      "loss": 0.0,
-      "step": 4
-    },
-    {
-      "epoch": 0.0030911901081916537,
-      "grad_norm": NaN,
-      "learning_rate": 0.0001,
-      "loss": 0.0,
-      "step": 5
-    },
-    {
-      "epoch": 0.0037094281298299847,
-      "grad_norm": NaN,
-      "learning_rate": 0.00012,
-      "loss": 0.0,
-      "step": 6
-    },
-    {
-      "epoch": 0.0037094281298299847,
-      "eval_loss": NaN,
-      "eval_runtime": 103.4324,
-      "eval_samples_per_second": 6.584,
-      "eval_steps_per_second": 3.297,
-      "step": 6
-    },
-    {
-      "epoch": 0.004327666151468315,
-      "grad_norm": NaN,
-      "learning_rate": 0.00014,
-      "loss": 0.0,
-      "step": 7
-    },
-    {
-      "epoch": 0.004945904173106646,
-      "grad_norm": NaN,
-      "learning_rate": 0.00016,
-      "loss": 0.0,
-      "step": 8
-    },
-    {
-      "epoch": 0.0055641421947449764,
-      "grad_norm": NaN,
-      "learning_rate": 0.00018,
-      "loss": 0.0,
-      "step": 9
-    },
-    {
-      "epoch": 0.0055641421947449764,
-      "eval_loss": NaN,
-      "eval_runtime": 103.4384,
-      "eval_samples_per_second": 6.584,
-      "eval_steps_per_second": 3.297,
-      "step": 9
-    },
-    {
-      "epoch": 0.0061823802163833074,
-      "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 sha256:9778bc3771f78da89c90b97f25cacc1702bb825db7d978a39047d56a9aaafc4a
+oid sha256:52883141d57ad1377040ef6eca10b15eccacf5ca66c508d3219d37eeed7bfea2
 size 6776