Training in progress, step 10, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "down_proj",
+    "up_proj",
     "o_proj",
     "q_proj",
+    "k_proj",
+    "down_proj",
     "gate_proj",
-    "up_proj",
-    "k_proj"
+    "v_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 sha256:0a8a93262756e47d5839bbfbfd6e1782b4a4b115858b7bbfbdb48d6b2a2d648f
+oid sha256:745e22b4cfe644e890b5c7e5762b7334c3fbc1160823253050f8c8f2ad45f45f
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12b51d7b9e7762dad6ee06eb74391d6cd0b59e3429ee051e55c386ab2b1404e7
+oid sha256:8a6730c01065acf92904c618ca73cd90bf6851a42e0e85e0557ae5df3e073722
 size 25986148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46a60f1f8a64a67c522a32b2bb6298c6721f7223b751a5f8a8dd5bea9d110e86
+oid sha256:aac52a5fbf7563a7bcb3d6eef192e260910b8c56eef104747fc841eca3de59f3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,16 +1,16 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.000906823849467241,
+  "epoch": 0.001007582054963601,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.00010075820549636011,
-      "grad_norm": 8.359752932236722e+18,
+      "grad_norm": 6.578465480158216e+18,
       "learning_rate": 2e-05,
       "loss": 1.8654,
       "step": 1
@@ -18,90 +18,97 @@
     {
       "epoch": 0.00010075820549636011,
       "eval_loss": 1.7779617309570312,
-      "eval_runtime": 1454.9416,
-      "eval_samples_per_second": 2.872,
-      "eval_steps_per_second": 1.436,
+      "eval_runtime": 1454.0406,
+      "eval_samples_per_second": 2.874,
+      "eval_steps_per_second": 1.437,
       "step": 1
     },
     {
       "epoch": 0.00020151641099272022,
-      "grad_norm": 2.626370165041791e+18,
+      "grad_norm": 2.1462115130466632e+18,
       "learning_rate": 4e-05,
       "loss": 1.3359,
       "step": 2
     },
     {
       "epoch": 0.0003022746164890803,
-      "grad_norm": 3.249743505089626e+18,
+      "grad_norm": 2.517414610043142e+18,
       "learning_rate": 6e-05,
-      "loss": 1.3042,
+      "loss": 1.3138,
       "step": 3
     },
     {
       "epoch": 0.0003022746164890803,
-      "eval_loss": 1.7708849906921387,
-      "eval_runtime": 1454.6249,
-      "eval_samples_per_second": 2.873,
+      "eval_loss": 1.7785661220550537,
+      "eval_runtime": 1454.8386,
+      "eval_samples_per_second": 2.872,
       "eval_steps_per_second": 1.437,
       "step": 3
     },
     {
       "epoch": 0.00040303282198544043,
-      "grad_norm": 8.100253344674611e+18,
+      "grad_norm": 7.439758018171896e+18,
       "learning_rate": 8e-05,
-      "loss": 1.5396,
+      "loss": 1.5352,
       "step": 4
     },
     {
       "epoch": 0.0005037910274818005,
-      "grad_norm": 4.612551334078448e+18,
+      "grad_norm": 3.50965568439006e+18,
       "learning_rate": 0.0001,
-      "loss": 1.2117,
+      "loss": 1.2199,
       "step": 5
     },
     {
       "epoch": 0.0006045492329781607,
-      "grad_norm": 6.333141896013021e+18,
+      "grad_norm": 5.017360729099993e+18,
       "learning_rate": 0.00012,
-      "loss": 1.6426,
+      "loss": 1.6428,
       "step": 6
     },
     {
       "epoch": 0.0006045492329781607,
-      "eval_loss": 1.7828969955444336,
-      "eval_runtime": 1454.0873,
-      "eval_samples_per_second": 2.874,
+      "eval_loss": 1.799889326095581,
+      "eval_runtime": 1454.8745,
+      "eval_samples_per_second": 2.872,
       "eval_steps_per_second": 1.437,
       "step": 6
     },
     {
       "epoch": 0.0007053074384745208,
-      "grad_norm": 5.453606261071282e+18,
+      "grad_norm": 3.866104434853413e+18,
       "learning_rate": 0.00014,
-      "loss": 1.3789,
+      "loss": 1.3893,
       "step": 7
     },
     {
       "epoch": 0.0008060656439708809,
-      "grad_norm": 7.580743446399287e+18,
+      "grad_norm": 6.592969687796023e+18,
       "learning_rate": 0.00016,
-      "loss": 1.4,
+      "loss": 1.4081,
       "step": 8
     },
     {
       "epoch": 0.000906823849467241,
-      "grad_norm": 1.1626996814149845e+19,
+      "grad_norm": 1.0697785243865186e+19,
       "learning_rate": 0.00018,
-      "loss": 1.3397,
+      "loss": 1.3395,
       "step": 9
     },
     {
       "epoch": 0.000906823849467241,
-      "eval_loss": 1.7769960165023804,
-      "eval_runtime": 1454.9997,
-      "eval_samples_per_second": 2.872,
+      "eval_loss": 1.7862416505813599,
+      "eval_runtime": 1455.8794,
+      "eval_samples_per_second": 2.87,
       "eval_steps_per_second": 1.436,
       "step": 9
+    },
+    {
+      "epoch": 0.001007582054963601,
+      "grad_norm": 8.756319288584831e+18,
+      "learning_rate": 0.0002,
+      "loss": 1.5203,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -116,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1852863789662208.0,
+  "total_flos": 2058737544069120.0,
   "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 sha256:58a3eb8d82e5fbac81f07720d857f56891a89c37b161f0eab5a75ef832506307
+oid sha256:b28660bfe89cc0538651f48cd70f7a481a8052384d78f5c68e3271d050811326
 size 6776