Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -21,11 +21,11 @@
   "revision": null,
   "target_modules": [
     "down_proj",
-    "gate_proj",
-    "q_proj",
-    "up_proj",
     "o_proj",
+    "up_proj",
     "k_proj",
+    "gate_proj",
+    "q_proj",
     "v_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:946fd01ec49bc9a550ee64a07a58c461e891416ed469e3d1d1063fe53cad6e56
+oid sha256:8dcc5f43e5acb3dfef705409541c990b856fb1bc2faa94c0a2ff5a633a1b2577
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1360b214dc305ce0c7fca0fdb3feecc9d03ca3af798b10af45b117b0f4bff123
+oid sha256:5d0ba80f16c2c94e21775a2856af67517c490b5afe3b70fa1114b06962e15827
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9673d22f265ed23c9ac8fe3534732259b5ca12d0692ce0ea4ceef5963b1b4fd
+oid sha256:883940dce99757642a2bf89cbb798d82586b74059fd59c5d604faf7dfc8ae68b
 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": 8.98069151324652e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0011674898967220476,
+  "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": 8.98069151324652e-05,
       "eval_loss": NaN,
-      "eval_runtime": 321.0417,
-      "eval_samples_per_second": 14.606,
-      "eval_steps_per_second": 7.304,
+      "eval_runtime": 319.7863,
+      "eval_samples_per_second": 14.663,
+      "eval_steps_per_second": 7.333,
       "step": 1
+    },
+    {
+      "epoch": 0.000449034575662326,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.000898069151324652,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.000898069151324652,
+      "eval_loss": NaN,
+      "eval_runtime": 319.3457,
+      "eval_samples_per_second": 14.683,
+      "eval_steps_per_second": 7.343,
+      "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": 174263604609024.0,
+  "total_flos": 2613954069135360.0,
   "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 sha256:9df1501c399e846d2679f8b4efdbdbef09224d1986fef1a94fec6fb8d42b0495
+oid sha256:489a2d5423f0af937a46a9be2e8ab13af17462c867dddcd0c005d0da52aaf477
 size 6776