Training in progress, step 4, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "up_proj",
-    "gate_proj",
     "k_proj",
+    "q_proj",
     "o_proj",
+    "up_proj",
     "v_proj",
-    "q_proj"
+    "gate_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 sha256:645229eafb27805fd22c3547a92261bbf413db0d572d816298e015729ce9ce9c
+oid sha256:9a1f11dc4ba20dbf66062992b5e16c8148254697644a3dac2a641c0f0bf80ada
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f64590911fe0f557956d2f40cd287e188a72f884294da5ee6b344114c8b74f5
+oid sha256:d06b1eede5305ad47241c3855f50fe14eddecf8c34d154695cebd0c9227a69be
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e64dc269c204efc2e9a4c4cbe20de7c7547b2a048bf7e9385229ea63d598fdfd
+oid sha256:049c306a67a9bf5a5c55385c4c3d8c96f923249cec6471081b080d3935493ea9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.32,
+  "eval_steps": 3,
+  "global_step": 4,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,25 @@
     {
       "epoch": 0.08,
       "eval_loss": 5.956454753875732,
-      "eval_runtime": 0.3949,
-      "eval_samples_per_second": 15.192,
-      "eval_steps_per_second": 7.596,
+      "eval_runtime": 0.3943,
+      "eval_samples_per_second": 15.218,
+      "eval_steps_per_second": 7.609,
       "step": 1
+    },
+    {
+      "epoch": 0.24,
+      "eval_loss": 5.943696975708008,
+      "eval_runtime": 0.3931,
+      "eval_samples_per_second": 15.261,
+      "eval_steps_per_second": 7.631,
+      "step": 3
     }
   ],
   "logging_steps": 5,
-  "max_steps": 1,
+  "max_steps": 13,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
-  "save_steps": 1,
+  "num_train_epochs": 2,
+  "save_steps": 4,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -29,12 +37,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 184956424814592.0,
+  "total_flos": 739825699258368.0,
   "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 sha256:297454ca16a4093f45d7b2abc53edf3fd8cdb9a2f918bbd04c1dfa2aeb90dfeb
+oid sha256:0b8306c44e334f771b56d4eea9b49bd467f2d9cfdfde25ea7cd9410550773854
 size 6776