Training in progress, step 1, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
     "up_proj",
-    "gate_proj",
     "k_proj",
+    "gate_proj",
     "down_proj",
-    "v_proj",
-    "q_proj"
+    "q_proj",
+    "o_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 sha256:292eadaa61de5dd99e6bf9ec43a5dde3d7c676fce4bff127477199d42e858834
+oid sha256:6ef85cd79f7d6a1c7af7c3b5d2da59f4d707d0c6fd2f556b38c62de65f8ba9cf
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:437e45006286a072af82af68bd745809fe0be8546e9680fc08dc720540a85606
+oid sha256:2712ec3feac87df3ec27ccf2e2d9420ece6f66f240fc1b384c2478b37ac4eb98
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c591c3b0b5aaa3bace339eb4070c47d0383ae432026f20b06621bbff93668b9
+oid sha256:ce18d2d551de9284109c0e2530e5f04b91a8696554c7740e97ea2b7bdd6d1090
 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": 0.1949317738791423,
-  "eval_steps": 10,
-  "global_step": 50,
+  "epoch": 0.003898635477582846,
+  "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": 0.003898635477582846,
       "eval_loss": 0.8528332114219666,
-      "eval_runtime": 12.8176,
-      "eval_samples_per_second": 8.426,
-      "eval_steps_per_second": 4.213,
+      "eval_runtime": 13.0599,
+      "eval_samples_per_second": 8.27,
+      "eval_steps_per_second": 4.135,
       "step": 1
-    },
-    {
-      "epoch": 0.01949317738791423,
-      "grad_norm": 4.119136333465576,
-      "learning_rate": 5e-05,
-      "loss": 3.3918,
-      "step": 5
-    },
-    {
-      "epoch": 0.03898635477582846,
-      "grad_norm": 3.6297383308410645,
-      "learning_rate": 0.0001,
-      "loss": 3.1245,
-      "step": 10
-    },
-    {
-      "epoch": 0.03898635477582846,
-      "eval_loss": 0.6827734708786011,
-      "eval_runtime": 13.0392,
-      "eval_samples_per_second": 8.283,
-      "eval_steps_per_second": 4.141,
-      "step": 10
-    },
-    {
-      "epoch": 0.05847953216374269,
-      "grad_norm": 4.023770809173584,
-      "learning_rate": 9.619397662556435e-05,
-      "loss": 2.5966,
-      "step": 15
-    },
-    {
-      "epoch": 0.07797270955165692,
-      "grad_norm": 3.661518096923828,
-      "learning_rate": 8.535533905932738e-05,
-      "loss": 2.4105,
-      "step": 20
-    },
-    {
-      "epoch": 0.07797270955165692,
-      "eval_loss": 0.6242299675941467,
-      "eval_runtime": 13.0453,
-      "eval_samples_per_second": 8.279,
-      "eval_steps_per_second": 4.139,
-      "step": 20
-    },
-    {
-      "epoch": 0.09746588693957114,
-      "grad_norm": 3.441826581954956,
-      "learning_rate": 6.91341716182545e-05,
-      "loss": 2.5813,
-      "step": 25
-    },
-    {
-      "epoch": 0.11695906432748537,
-      "grad_norm": 3.5918526649475098,
-      "learning_rate": 5e-05,
-      "loss": 2.5341,
-      "step": 30
-    },
-    {
-      "epoch": 0.11695906432748537,
-      "eval_loss": 0.6086655855178833,
-      "eval_runtime": 13.1265,
-      "eval_samples_per_second": 8.228,
-      "eval_steps_per_second": 4.114,
-      "step": 30
-    },
-    {
-      "epoch": 0.1364522417153996,
-      "grad_norm": 3.5770630836486816,
-      "learning_rate": 3.086582838174551e-05,
-      "loss": 2.5353,
-      "step": 35
-    },
-    {
-      "epoch": 0.15594541910331383,
-      "grad_norm": 3.4191396236419678,
-      "learning_rate": 1.4644660940672627e-05,
-      "loss": 2.3267,
-      "step": 40
-    },
-    {
-      "epoch": 0.15594541910331383,
-      "eval_loss": 0.6020417809486389,
-      "eval_runtime": 13.2295,
-      "eval_samples_per_second": 8.164,
-      "eval_steps_per_second": 4.082,
-      "step": 40
-    },
-    {
-      "epoch": 0.17543859649122806,
-      "grad_norm": 3.3189620971679688,
-      "learning_rate": 3.8060233744356633e-06,
-      "loss": 2.351,
-      "step": 45
-    },
-    {
-      "epoch": 0.1949317738791423,
-      "grad_norm": 3.7775397300720215,
-      "learning_rate": 0.0,
-      "loss": 2.543,
-      "step": 50
-    },
-    {
-      "epoch": 0.1949317738791423,
-      "eval_loss": 0.601226806640625,
-      "eval_runtime": 13.2095,
-      "eval_samples_per_second": 8.176,
-      "eval_steps_per_second": 4.088,
-      "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": 1.7439084402180096e+16,
+  "total_flos": 350534359842816.0,
   "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 sha256:68f2d8d172f297e9444c68fa0d9a882ea3108657ab700be8fcd9ce3587988d09
+oid sha256:ede6b6fdee903a3074da3a171c93ab5343e1258adcee4206296f452294c79e95
 size 6776