Training in progress, step 9, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "k_proj",
-    "q_proj",
+    "o_proj",
+    "up_proj",
     "gate_proj",
+    "k_proj",
     "v_proj",
-    "o_proj",
-    "up_proj"
+    "q_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:cf12e03f6739bc0f7a478e3a172c01dd5f398c4bbb99b6b05cae950ea51679d4
+oid sha256:cea908fe7a6a05e827cb4a10ef12cff2edb8dae4c7310af8a09db48c810565e8
 size 25271744

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5364d09e27bdf541cc4080b011a0a833388b061da2ef703197275a4e77a4aa4
+oid sha256:ab4032206871f76f267774b23b5210fddd18559968f207e84376a2a9e45c5846
 size 14244

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006683375104427736,
+  "epoch": 0.006015037593984963,
   "eval_steps": 3,
-  "global_step": 10,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -18,9 +18,9 @@
     {
       "epoch": 0.0006683375104427736,
       "eval_loss": 6.567427635192871,
-      "eval_runtime": 10.2795,
-      "eval_samples_per_second": 30.741,
-      "eval_steps_per_second": 30.741,
+      "eval_runtime": 12.5721,
+      "eval_samples_per_second": 25.135,
+      "eval_steps_per_second": 25.135,
       "step": 1
     },
     {
@@ -40,9 +40,9 @@
     {
       "epoch": 0.0020050125313283208,
       "eval_loss": 6.567427635192871,
-      "eval_runtime": 10.2668,
-      "eval_samples_per_second": 30.779,
-      "eval_steps_per_second": 30.779,
+      "eval_runtime": 12.4056,
+      "eval_samples_per_second": 25.472,
+      "eval_steps_per_second": 25.472,
       "step": 3
     },
     {
@@ -69,9 +69,9 @@
     {
       "epoch": 0.0040100250626566416,
       "eval_loss": 6.567427635192871,
-      "eval_runtime": 10.6828,
-      "eval_samples_per_second": 29.58,
-      "eval_steps_per_second": 29.58,
+      "eval_runtime": 12.9457,
+      "eval_samples_per_second": 24.41,
+      "eval_steps_per_second": 24.41,
       "step": 6
     },
     {
@@ -98,17 +98,10 @@
     {
       "epoch": 0.006015037593984963,
       "eval_loss": 6.567427635192871,
-      "eval_runtime": 10.3575,
-      "eval_samples_per_second": 30.509,
-      "eval_steps_per_second": 30.509,
+      "eval_runtime": 12.5182,
+      "eval_samples_per_second": 25.243,
+      "eval_steps_per_second": 25.243,
       "step": 9
-    },
-    {
-      "epoch": 0.006683375104427736,
-      "grad_norm": NaN,
-      "learning_rate": 0.0,
-      "loss": 6.3319,
-      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -123,12 +116,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 255791978250240.0,
+  "total_flos": 230212780425216.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bf7f2cad6e11c0ce3e3076a28f4690cfb1e863a19192d0c9a93217476d185e7
+oid sha256:e33c14880d19facfd321016a9bcfbb3088b8c60b69f0d839be31c2284ef19082
 size 6776