Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "down_proj",
-    "v_proj",
     "gate_proj",
-    "o_proj",
     "q_proj",
-    "k_proj"
+    "up_proj",
+    "o_proj",
+    "k_proj",
+    "v_proj",
+    "down_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 sha256:4d1fb7453c86281fd6e3fe369681f274dcdd9edbcc69781230219851a579eec6
+oid sha256:32c28f483495300ba232d73ccc63c184ea9675f5d29efc43ab5ab7a694706dcc
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b0a93aee9ccfa055371037cb1ad220b4ddb9d6f791ee0421d47fec836ecd8b0
+oid sha256:f99774fc687f0e9abee5eb1b759a02b0b2557957a653b2e09303b06407ef871f
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3930df0ff2b36cd2f3e2f67fdee79600c8e6a9d5398436f43b143b4485772785
+oid sha256:11669485eb2ea751b4d6ff6e6e0219e650e855d1b38001e8e66b02ee88b1f103
 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": 4.7837734404898585e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0006218905472636816,
+  "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": 4.7837734404898585e-05,
       "eval_loss": 5.93709659576416,
-      "eval_runtime": 941.0049,
-      "eval_samples_per_second": 9.354,
-      "eval_steps_per_second": 4.677,
+      "eval_runtime": 943.8543,
+      "eval_samples_per_second": 9.326,
+      "eval_steps_per_second": 4.663,
       "step": 1
+    },
+    {
+      "epoch": 0.00023918867202449293,
+      "grad_norm": 2.328223466873169,
+      "learning_rate": 5e-05,
+      "loss": 5.333,
+      "step": 5
+    },
+    {
+      "epoch": 0.00047837734404898585,
+      "grad_norm": 4.410595893859863,
+      "learning_rate": 0.0001,
+      "loss": 4.8527,
+      "step": 10
+    },
+    {
+      "epoch": 0.00047837734404898585,
+      "eval_loss": 4.567225456237793,
+      "eval_runtime": 945.1716,
+      "eval_samples_per_second": 9.313,
+      "eval_steps_per_second": 4.656,
+      "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": 261395406913536.0,
+  "total_flos": 3833799301398528.0,
   "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:d67313d5d73409bf2497a95ce7a5e56512f3b5b7ccad8b6a25432ab413441fdd
+oid sha256:a32e042f89832e2575eb08e51d7b39391d4bce4f750d54f96f664872956851b4
 size 6776