Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
     "o_proj",
-    "gate_proj",
-    "down_proj",
-    "k_proj",
     "v_proj",
-    "q_proj"
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "up_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:b052943da76b677f67482d1092df8ee641d90acc884ed9734c5edd5c98b9f978
+oid sha256:ed9311dc17ebd790a5def34affb92e5fb598b88f82fdd85d9e335e90ea0b7305
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ca63299c74a072220c9f35716233ce976b1ba6ee4be1a82e6f5ece8e6a61965
+oid sha256:0ac752dc107d45ccf14455d857b2ae1434a5ed78a726edf72bb663b26303ea6f
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb6245a3f3fe99fd9d96194c8979b73f0b09d7fc7edf23d255b0a7cb132b6b75
+oid sha256:8ef8705777091b5febb6761ed1f2fd8d5cb1215cde180da2cde2fa76ba08767f
 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": 5.805599500718443e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0007547279350933975,
+  "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": 5.805599500718443e-05,
       "eval_loss": 11.049264907836914,
-      "eval_runtime": 700.7086,
-      "eval_samples_per_second": 10.351,
+      "eval_runtime": 700.7925,
+      "eval_samples_per_second": 10.35,
       "eval_steps_per_second": 5.176,
       "step": 1
+    },
+    {
+      "epoch": 0.0002902799750359221,
+      "grad_norm": 11.501642227172852,
+      "learning_rate": 5e-05,
+      "loss": 11.2858,
+      "step": 5
+    },
+    {
+      "epoch": 0.0005805599500718442,
+      "grad_norm": 17.796802520751953,
+      "learning_rate": 0.0001,
+      "loss": 8.6548,
+      "step": 10
+    },
+    {
+      "epoch": 0.0005805599500718442,
+      "eval_loss": 4.853416919708252,
+      "eval_runtime": 713.834,
+      "eval_samples_per_second": 10.161,
+      "eval_steps_per_second": 5.081,
+      "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": 184956424814592.0,
+  "total_flos": 2728107266015232.0,
   "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:e00e897b7e47a818c821564c1b288684edb0cb3c80c81673b68282f4056df846
+oid sha256:8cb6614c1bc4bff82f2482c78ce7d6a93fde0b19044859f0bc48ad379b9a10ab
 size 6776