Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "q_proj",
     "gate_proj",
     "up_proj",
-    "k_proj",
     "o_proj",
-    "v_proj",
-    "q_proj",
-    "down_proj"
+    "k_proj",
+    "down_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:dd1749af2c53b776fe9b79e858bb8e1f1ee5c3fb2b91753546e649185d87e712
+oid sha256:5d85134095084ddd6dfabe916d5f3f0acdde6fbec31a3f111645b78cf0ca638e
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e53b64058491e3ede053f37a8e69d6ed56eba2c103a167853a127a0849687712
+oid sha256:79174ed55ecf4f15d8795c373d995326418da6b3fff2c00a7c99ff5b43997e36
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bb5dd3632f621f63027a71316dd458a1d0eb2cb6f6bdb9c2be6da1bb386cb19
+oid sha256:4479d8612262ecedc656e3fb719b965a26864f43306d791dee922d685b13b6f5
 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": 1.2771228975364299e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0001660259766797359,
+  "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": 1.2771228975364299e-05,
       "eval_loss": 2.566653251647949,
-      "eval_runtime": 1209.8868,
-      "eval_samples_per_second": 27.25,
-      "eval_steps_per_second": 13.625,
+      "eval_runtime": 1235.1891,
+      "eval_samples_per_second": 26.691,
+      "eval_steps_per_second": 13.346,
       "step": 1
+    },
+    {
+      "epoch": 6.38561448768215e-05,
+      "grad_norm": 0.48807352781295776,
+      "learning_rate": 5e-05,
+      "loss": 2.5533,
+      "step": 5
+    },
+    {
+      "epoch": 0.000127712289753643,
+      "grad_norm": 0.5297641158103943,
+      "learning_rate": 0.0001,
+      "loss": 2.5952,
+      "step": 10
+    },
+    {
+      "epoch": 0.000127712289753643,
+      "eval_loss": 2.4731204509735107,
+      "eval_runtime": 1235.5847,
+      "eval_samples_per_second": 26.683,
+      "eval_steps_per_second": 13.342,
+      "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": 82004866498560.0,
+  "total_flos": 1066063264481280.0,
   "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 sha256:8b665d3dfc9a743ca931ce03a978e9f6e01e0006349e49ca61276e24f0c339f0
+oid sha256:e704908001d601de807bdbf0a1ea1bd83f32b68b2a34ec24de8b2f43ead66ae1
 size 6776