Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
     "v_proj",
+    "o_proj",
+    "up_proj",
     "q_proj",
-    "down_proj",
     "gate_proj",
-    "up_proj",
+    "down_proj",
     "k_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f3429c3f9f8e2dfd134767874e85539ebb602e168f8f9d61c28795b2280ae96
+oid sha256:c794b158fbc133bf66d94c02b4f55f9cbc4f0ccc89dfb03a88125e26fbe57446
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1c840391a21fbb35ce4846a625e1f63917d6d5d754442f8daed3465d346a0e7
+oid sha256:d6b25c752847b616122f69c31210833d88a139298d792a264acf326e4f7f32f6
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b353bd32b2eceef37fa8b45cd65c7c835a171d164c7a48bb00b5a7a0c0a629f
+oid sha256:a8c306ab9304f0d8cf59c4fcb43a48bbc7cbacbabfb87aa50edb960b246b5756
 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": 0.00016635475150758992,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.002162611769598669,
+  "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": 0.00016635475150758992,
       "eval_loss": NaN,
-      "eval_runtime": 112.6028,
-      "eval_samples_per_second": 22.477,
-      "eval_steps_per_second": 11.243,
+      "eval_runtime": 113.0746,
+      "eval_samples_per_second": 22.383,
+      "eval_steps_per_second": 11.196,
       "step": 1
+    },
+    {
+      "epoch": 0.0008317737575379496,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.0016635475150758993,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.0016635475150758993,
+      "eval_loss": NaN,
+      "eval_runtime": 112.0454,
+      "eval_samples_per_second": 22.589,
+      "eval_steps_per_second": 11.299,
+      "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": 56752195239936.0,
+  "total_flos": 802638189821952.0,
   "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 sha256:8fe375fec06435f4d4793bf30efd1d72c39154c5663ba84e8d267adf08a3aea4
+oid sha256:2950758e528ff473d05b0f641a14244807480a6b39aa90912782519525122d4e
 size 6776