Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "k_proj",
-    "gate_proj",
+    "v_proj",
     "down_proj",
+    "k_proj",
     "o_proj",
-    "v_proj",
-    "up_proj"
+    "q_proj",
+    "up_proj",
+    "gate_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:a109049636a88217a38ab0e97f391e6f2d2cf3dcdd739e8cb8338fc071c3da3e
+oid sha256:1f9065d6f2c9b082eefcd72e8ae12e49e43705817a5e0da018d0fcd4c0c9f639
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79cd6e69d2a041375d103aec3695a1e0a8664c745b1e4c8799a6d145b86978e1
+oid sha256:146f5f3a8d8818b84c588a86bc0c0cde50bfa0553411fd1f0411bad8e899c295
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7484c1a22d352ce83f5f015e796e9ceb701757f35d7de923c63231cfddeda93
+oid sha256:7ef568c15d3a92fad74ef5f86ffe7330da3a1446a29e6310725eb6a237745116
 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": 0.0014716703458425313,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.01913171449595291,
+  "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": 0.0014716703458425313,
       "eval_loss": 1.1566596031188965,
-      "eval_runtime": 26.4512,
-      "eval_samples_per_second": 10.85,
-      "eval_steps_per_second": 5.444,
+      "eval_runtime": 26.6038,
+      "eval_samples_per_second": 10.788,
+      "eval_steps_per_second": 5.413,
       "step": 1
+    },
+    {
+      "epoch": 0.007358351729212656,
+      "grad_norm": 16.61760139465332,
+      "learning_rate": 5e-05,
+      "loss": 3.9117,
+      "step": 5
+    },
+    {
+      "epoch": 0.014716703458425313,
+      "grad_norm": 6.252457618713379,
+      "learning_rate": 0.0001,
+      "loss": 3.6101,
+      "step": 10
+    },
+    {
+      "epoch": 0.014716703458425313,
+      "eval_loss": 0.9047649502754211,
+      "eval_runtime": 27.0546,
+      "eval_samples_per_second": 10.608,
+      "eval_steps_per_second": 5.323,
+      "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": 263016432009216.0,
+  "total_flos": 3331541472116736.0,
   "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:e74c0e1c76ac9185ea1fd226731c19aecf476e196d214e51ce2c6f9787cbd741
+oid sha256:83ed10b48660e13fe3390f4c9eb9c7fbc4d64c2e9a1f32af98f18b5709217686
 size 6776