Training in progress, step 1, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
+    "gate_proj",
+    "down_proj",
+    "o_proj",
     "k_proj",
+    "up_proj",
     "v_proj",
-    "o_proj",
-    "down_proj",
-    "q_proj",
-    "gate_proj"
+    "q_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 sha256:638d8423f3abd185674371f713a702b18e3fbadd95daec54b32a2a0cb0ebd3cf
+oid sha256:3bcdd7e75ba5ad31921e26b8cb7e9b911d13e37f2a3cc67f66b9cc66b05c6554
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e17f736c3d16ceee7e52741bea1defb2f111fe772a508cbdfabb6e1509babc03
+oid sha256:f5d917172d0dcb4ed67591182d13b5fcc01c45f6da63f703d8709f933f57e719
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d82b625db56507f447e53f457cd40a516407fb4c508f6a80ad29dded2571bb42
+oid sha256:e96084db0d88b3f6f054fd8e1ee389d8068f68911086b40d9534c6441e1738ec
 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": 0.02632964718272775,
-  "eval_steps": 10,
-  "global_step": 50,
+  "epoch": 0.000526592943654555,
+  "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": 0.000526592943654555,
       "eval_loss": 10.178997039794922,
-      "eval_runtime": 21.4891,
-      "eval_samples_per_second": 37.228,
-      "eval_steps_per_second": 18.614,
+      "eval_runtime": 21.4246,
+      "eval_samples_per_second": 37.34,
+      "eval_steps_per_second": 18.67,
       "step": 1
-    },
-    {
-      "epoch": 0.0026329647182727752,
-      "grad_norm": 22.557941436767578,
-      "learning_rate": 5e-05,
-      "loss": 10.0299,
-      "step": 5
-    },
-    {
-      "epoch": 0.0052659294365455505,
-      "grad_norm": 24.156038284301758,
-      "learning_rate": 0.0001,
-      "loss": 7.5164,
-      "step": 10
-    },
-    {
-      "epoch": 0.0052659294365455505,
-      "eval_loss": 3.2705798149108887,
-      "eval_runtime": 21.3836,
-      "eval_samples_per_second": 37.412,
-      "eval_steps_per_second": 18.706,
-      "step": 10
-    },
-    {
-      "epoch": 0.007898894154818325,
-      "grad_norm": 0.6436730623245239,
-      "learning_rate": 9.619397662556435e-05,
-      "loss": 1.2215,
-      "step": 15
-    },
-    {
-      "epoch": 0.010531858873091101,
-      "grad_norm": 0.0030531813390552998,
-      "learning_rate": 8.535533905932738e-05,
-      "loss": 0.0008,
-      "step": 20
-    },
-    {
-      "epoch": 0.010531858873091101,
-      "eval_loss": 0.00012725224951282144,
-      "eval_runtime": 21.5371,
-      "eval_samples_per_second": 37.145,
-      "eval_steps_per_second": 18.573,
-      "step": 20
-    },
-    {
-      "epoch": 0.013164823591363875,
-      "grad_norm": 0.004266378469765186,
-      "learning_rate": 6.91341716182545e-05,
-      "loss": 0.0001,
-      "step": 25
-    },
-    {
-      "epoch": 0.01579778830963665,
-      "grad_norm": 0.0004052742151543498,
-      "learning_rate": 5e-05,
-      "loss": 0.0,
-      "step": 30
-    },
-    {
-      "epoch": 0.01579778830963665,
-      "eval_loss": 3.419800123083405e-06,
-      "eval_runtime": 21.5282,
-      "eval_samples_per_second": 37.16,
-      "eval_steps_per_second": 18.58,
-      "step": 30
-    },
-    {
-      "epoch": 0.018430753027909426,
-      "grad_norm": 0.00017400829528924078,
-      "learning_rate": 3.086582838174551e-05,
-      "loss": 0.0,
-      "step": 35
-    },
-    {
-      "epoch": 0.021063717746182202,
-      "grad_norm": 0.00020549260079860687,
-      "learning_rate": 1.4644660940672627e-05,
-      "loss": 0.0,
-      "step": 40
-    },
-    {
-      "epoch": 0.021063717746182202,
-      "eval_loss": 2.3916304598969873e-06,
-      "eval_runtime": 21.729,
-      "eval_samples_per_second": 36.817,
-      "eval_steps_per_second": 18.409,
-      "step": 40
-    },
-    {
-      "epoch": 0.023696682464454975,
-      "grad_norm": 0.0001425171212758869,
-      "learning_rate": 3.8060233744356633e-06,
-      "loss": 0.0,
-      "step": 45
-    },
-    {
-      "epoch": 0.02632964718272775,
-      "grad_norm": 0.0001806920045055449,
-      "learning_rate": 0.0,
-      "loss": 0.0,
-      "step": 50
-    },
-    {
-      "epoch": 0.02632964718272775,
-      "eval_loss": 2.337539626751095e-06,
-      "eval_runtime": 21.6689,
-      "eval_samples_per_second": 36.919,
-      "eval_steps_per_second": 18.46,
-      "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": 1202727577190400.0,
+  "total_flos": 24054551543808.0,
   "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:b60c045490c2b02d041777766560bc96f7454144f33654805d7e142dd3d5280a
+oid sha256:9b388e2670d88e8bbbf2f4769b0921c5f746d69aba4ae40c03f7a76c036b5b9f
 size 6776