Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

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

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a51042062c38bde8d317a076e917fd057621bfb9aaa27230ee3cb5953489fca
+oid sha256:346d97d72e5438c732ee66161522675d797731455c213e1abf28741fb17480b9
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e83cbadcdee74c076d40ae69e4993eb13841bf8d54fcbb3d453d6cb0a2f630b2
+oid sha256:4929445dafafaec8c3dbf5ae5a0f36b4618be32c796a3eb459ba754fa67f79a0
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db5312ddb8f626229a291c72b544634e2d97dd8ec4ceca4550f1b24f37a77647
+oid sha256:1cf2cf1642240496da063250cd99fff33f4da8d95f7c46bc1e5b2e79a0e9b451
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00010387721712935311,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0013504038226815904,
+  "eval_steps": 10,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,39 @@
     {
       "epoch": 0.00010387721712935311,
       "eval_loss": 1.9016282558441162,
-      "eval_runtime": 222.4128,
-      "eval_samples_per_second": 18.227,
-      "eval_steps_per_second": 9.114,
+      "eval_runtime": 225.6225,
+      "eval_samples_per_second": 17.968,
+      "eval_steps_per_second": 8.984,
       "step": 1
+    },
+    {
+      "epoch": 0.0005193860856467655,
+      "grad_norm": 1.4621918201446533,
+      "learning_rate": 5e-05,
+      "loss": 1.8144,
+      "step": 5
+    },
+    {
+      "epoch": 0.001038772171293531,
+      "grad_norm": 1.3856263160705566,
+      "learning_rate": 0.0001,
+      "loss": 1.7063,
+      "step": 10
+    },
+    {
+      "epoch": 0.001038772171293531,
+      "eval_loss": 1.645436406135559,
+      "eval_runtime": 225.2292,
+      "eval_samples_per_second": 17.999,
+      "eval_steps_per_second": 9.0,
+      "step": 10
     }
   ],
   "logging_steps": 5,
-  "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 +51,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 50009733070848.0,
+  "total_flos": 675131396456448.0,
   "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:cbeb62c2c32f9b4c0709a913b4a2423c6a466a23d08aa2f9b2843cee9d98ace9
+oid sha256:8f1e875826864bb9f391e58a9db473b95e8c490c427cf0266ba3dab67ef4d5dc
 size 6776