Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
+    "down_proj",
     "v_proj",
-    "q_proj",
     "up_proj",
     "gate_proj",
-    "down_proj",
-    "o_proj"
+    "k_proj",
+    "o_proj",
+    "q_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 sha256:1f24c81bcf4942f58ac451805cfa6d3cedd5527d9690a2d7096e8d705414db8f
+oid sha256:65ebbb2c189dd415a8320a01b92fcfdf738e741b02a88f12bf10179edeaaba48
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1c840391a21fbb35ce4846a625e1f63917d6d5d754442f8daed3465d346a0e7
+oid sha256:47c4b1b1022476a667133913254b988ff83885ee227e03c4f7dc228d6177ea10
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da80317735abd5d7a29a7220f00b3b233d1e998e1437bb05f3ba2da5a84eb5d2
+oid sha256:ab94a5bf27f5e08eb6d05cb9d691607f0655952f9829cd29afe5ce5486aa3919
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:5adea6def46a60dd5782726d51a89bdf0f30226cd791e511d8af09a5644f99e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.013300083125519535,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.17290108063175394,
+  "eval_steps": 10,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,32 @@
     {
       "epoch": 0.013300083125519535,
       "eval_loss": NaN,
-      "eval_runtime": 20.1512,
-      "eval_samples_per_second": 25.16,
-      "eval_steps_per_second": 3.176,
+      "eval_runtime": 20.18,
+      "eval_samples_per_second": 25.124,
+      "eval_steps_per_second": 3.171,
       "step": 1
+    },
+    {
+      "epoch": 0.13300083125519535,
+      "grad_norm": NaN,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.13300083125519535,
+      "eval_loss": NaN,
+      "eval_runtime": 19.1556,
+      "eval_samples_per_second": 26.467,
+      "eval_steps_per_second": 3.341,
+      "step": 10
     }
   ],
   "logging_steps": 10,
-  "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 +44,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 1037754427244544.0,
+  "total_flos": 1.3490807554179072e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:291ef4511e5cce90764b70664708a5db0369e93d1da69b43e13b21123cb99246
+oid sha256:dcc0a6d42f6a060cbebc4f1db4b9f825dec35ba374e3c977dc37ccb2f855790f
 size 6776