Training in progress, step 1, checkpoint

last-checkpoint/adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "k_proj",
     "q_proj",
-    "down_proj",
+    "gate_proj",
     "o_proj",
-    "k_proj",
     "up_proj",
-    "gate_proj",
+    "down_proj",
     "v_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4381f2a11a4a1b9502180d916cc5f5bc88f0dc5f3a0e96b04a3b4a5522f4f7b5
+oid sha256:faf1ae5a1322a953df1c849416ea264802747f8d91f0f804ccf75dcfd60c1288
 size 59933632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aca827aff3c7af211f5b9079975bebacf640b5363c0f5badf7011d6ad8d43ffa
+oid sha256:f068e78a9723cda68d52e53f514b736226ef28d8ba4d8ff05faf4912a4f02f0d
 size 31822948

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf14461ff3bcb83ae11aad84df5562debaaefd480ea5f715e35910ae0912f42f
+oid sha256:014fc32136217511466b0732cca65b42a4298e94ace7af625b59f5969d82d54a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
+oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.05425935973955507,
-  "eval_steps": 10,
-  "global_step": 50,
+  "epoch": 0.0010851871947911015,
+  "eval_steps": 1,
+  "global_step": 1,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,127 +11,17 @@
     {
       "epoch": 0.0010851871947911015,
       "eval_loss": NaN,
-      "eval_runtime": 27.3915,
-      "eval_samples_per_second": 14.165,
-      "eval_steps_per_second": 7.082,
+      "eval_runtime": 27.2659,
+      "eval_samples_per_second": 14.23,
+      "eval_steps_per_second": 7.115,
       "step": 1
-    },
-    {
-      "epoch": 0.005425935973955507,
-      "grad_norm": NaN,
-      "learning_rate": 5e-05,
-      "loss": 0.0,
-      "step": 5
-    },
-    {
-      "epoch": 0.010851871947911014,
-      "grad_norm": NaN,
-      "learning_rate": 0.0001,
-      "loss": 0.0,
-      "step": 10
-    },
-    {
-      "epoch": 0.010851871947911014,
-      "eval_loss": NaN,
-      "eval_runtime": 26.8301,
-      "eval_samples_per_second": 14.461,
-      "eval_steps_per_second": 7.231,
-      "step": 10
-    },
-    {
-      "epoch": 0.016277807921866522,
-      "grad_norm": NaN,
-      "learning_rate": 9.619397662556435e-05,
-      "loss": 0.0,
-      "step": 15
-    },
-    {
-      "epoch": 0.02170374389582203,
-      "grad_norm": NaN,
-      "learning_rate": 8.535533905932738e-05,
-      "loss": 0.0,
-      "step": 20
-    },
-    {
-      "epoch": 0.02170374389582203,
-      "eval_loss": NaN,
-      "eval_runtime": 26.9468,
-      "eval_samples_per_second": 14.399,
-      "eval_steps_per_second": 7.199,
-      "step": 20
-    },
-    {
-      "epoch": 0.027129679869777535,
-      "grad_norm": NaN,
-      "learning_rate": 6.91341716182545e-05,
-      "loss": 0.0,
-      "step": 25
-    },
-    {
-      "epoch": 0.032555615843733045,
-      "grad_norm": NaN,
-      "learning_rate": 5e-05,
-      "loss": 0.0,
-      "step": 30
-    },
-    {
-      "epoch": 0.032555615843733045,
-      "eval_loss": NaN,
-      "eval_runtime": 26.9203,
-      "eval_samples_per_second": 14.413,
-      "eval_steps_per_second": 7.206,
-      "step": 30
-    },
-    {
-      "epoch": 0.03798155181768855,
-      "grad_norm": NaN,
-      "learning_rate": 3.086582838174551e-05,
-      "loss": 0.0,
-      "step": 35
-    },
-    {
-      "epoch": 0.04340748779164406,
-      "grad_norm": NaN,
-      "learning_rate": 1.4644660940672627e-05,
-      "loss": 0.0,
-      "step": 40
-    },
-    {
-      "epoch": 0.04340748779164406,
-      "eval_loss": NaN,
-      "eval_runtime": 26.9703,
-      "eval_samples_per_second": 14.386,
-      "eval_steps_per_second": 7.193,
-      "step": 40
-    },
-    {
-      "epoch": 0.048833423765599564,
-      "grad_norm": NaN,
-      "learning_rate": 3.8060233744356633e-06,
-      "loss": 0.0,
-      "step": 45
-    },
-    {
-      "epoch": 0.05425935973955507,
-      "grad_norm": NaN,
-      "learning_rate": 0.0,
-      "loss": 0.0,
-      "step": 50
-    },
-    {
-      "epoch": 0.05425935973955507,
-      "eval_loss": NaN,
-      "eval_runtime": 26.8782,
-      "eval_samples_per_second": 14.435,
-      "eval_steps_per_second": 7.218,
-      "step": 50
     }
   ],
   "logging_steps": 5,
-  "max_steps": 50,
+  "max_steps": 1,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 13,
+  "save_steps": 1,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -144,7 +34,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6856066360934400.0,
+  "total_flos": 137121327218688.0,
   "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 sha256:42b17a9116635c36d114cbd186fae3a1f8fa22ec734c2636fb393d9a20986e42
+oid sha256:6ff42a167d41afb48a3f1a3634e5eee054b938fc18b74cc26402e1a4b5446832
 size 6776