Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "v_proj",
-    "o_proj",
+    "down_proj",
     "q_proj",
+    "up_proj",
+    "v_proj",
+    "k_proj",
     "gate_proj",
-    "down_proj",
-    "up_proj"
+    "o_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 sha256:04381e2484989dcc7e2370e2ba310f46fce849f65490fb10b0805f052f883551
+oid sha256:038ff60f7ce575aef87ad3c4893b783b82185d2482a8fae2b7715b75303456ed
 size 390888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ec94b7eca181109965bf009bb7f1c0f91e892f258970d1dca16f9571145efa6
+oid sha256:4c152cd374b66112691af4095b77b1614ac3b3275e7feb9208f29401f5fad969
 size 819770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f32b84d138bef1242fe19dc07873004063a6958a789c89faaf6b9f854376172f
+oid sha256:ff7f0fe58f20a3ab677d7ee18585b766c1ac2de0b05dc8f10b3f865fe4417547
 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": 0.00966183574879227,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.12560386473429952,
+  "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": 0.00966183574879227,
       "eval_loss": 10.882368087768555,
-      "eval_runtime": 2.9278,
-      "eval_samples_per_second": 238.405,
-      "eval_steps_per_second": 30.057,
+      "eval_runtime": 2.9101,
+      "eval_samples_per_second": 239.851,
+      "eval_steps_per_second": 30.239,
       "step": 1
+    },
+    {
+      "epoch": 0.0966183574879227,
+      "grad_norm": 18.205909729003906,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 10.4561,
+      "step": 10
+    },
+    {
+      "epoch": 0.0966183574879227,
+      "eval_loss": 9.441638946533203,
+      "eval_runtime": 2.8968,
+      "eval_samples_per_second": 240.952,
+      "eval_steps_per_second": 30.378,
+      "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": 1966756331520.0,
+  "total_flos": 23404400345088.0,
   "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 sha256:74852d0c46bcab00b1ab2f5f505dc3c5dfbffc902cb1afa02aea646effb4037f
+oid sha256:dfd73c916cf8a10db418c8254abea25090a43b1485c95d46241c32addd46f3e5
 size 6776