Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "q_proj",
     "o_proj",
     "v_proj",
-    "gate_proj",
     "up_proj",
-    "k_proj",
     "down_proj",
-    "q_proj"
+    "gate_proj",
+    "k_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:d12e3562c2a57fb7ab3fb5c0fe296f52b30cb1df6aa9d913f17aae9de6bfe989
+oid sha256:8effb776aa64dfaf7022d0d31e62692528f34cb2e4948442aadecc3e65a6d88d
 size 31064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a8703e5e6b1df28b5c2ae1343161efd9766f9f9e777dbd1107c5f19f3df33b0
+oid sha256:ca7e593376b7f9466aea873d0281a39c0c07cfadb92dec61efca6b64b2a02b13
 size 71718

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:106d2362bc2f5d0877cb3549f0a8edc5f2a3f7ece3ea2591042b0fa260c47153
+oid sha256:15160272ffddfe27c654df211d1192733c9457f0ce97b19578f9cd078fb647f8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:5adea6def46a60dd5782726d51a89bdf0f30226cd791e511d8af09a5644f99e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0022228396776882466,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.02889691580994721,
+  "eval_steps": 10,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,32 @@
     {
       "epoch": 0.0022228396776882466,
       "eval_loss": 10.376819610595703,
-      "eval_runtime": 8.0631,
-      "eval_samples_per_second": 375.909,
-      "eval_steps_per_second": 47.004,
+      "eval_runtime": 8.0656,
+      "eval_samples_per_second": 375.791,
+      "eval_steps_per_second": 46.989,
       "step": 1
+    },
+    {
+      "epoch": 0.02222839677688247,
+      "grad_norm": 0.9294033050537109,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 166.0306,
+      "step": 10
+    },
+    {
+      "epoch": 0.02222839677688247,
+      "eval_loss": 10.375858306884766,
+      "eval_runtime": 8.057,
+      "eval_samples_per_second": 376.194,
+      "eval_steps_per_second": 47.04,
+      "step": 10
     }
   ],
   "logging_steps": 10,
-  "max_steps": 1,
+  "max_steps": 50,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 1,
+  "save_steps": 13,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -29,12 +44,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 821274083328.0,
+  "total_flos": 10676563083264.0,
   "train_batch_size": 8,
   "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:dd23f95ada95c2cb10a21b584b11f88d3c30f50865dad345737a6f4d4cd8da07
+oid sha256:f7aa1ac5c7695b0b34dc183d1f81057ab0442e340e1db5edf4fed82fc71fc9df
 size 6776