Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

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

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f609cf635fa4e3ea9448bd0dd9da8f36f3060b900eb11165f6fe982b0e198abe
+oid sha256:23122852a1d78dd9885084376826247048f43487873c4011b7823752dd5a854d
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d15c3aa65bfaf33e86604cf499d1d80559b45b7b131178564244b2da6a7e431f
+oid sha256:12c8d009b378acd577937c15837674ae473f53799417966d5e2cf429368df8c8
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:792d1546ebf93af6d5f2808ada23d245a92ec7ea7130b1c43c380eba2e821f58
+oid sha256:f2a3d0f18704952f5e489fd373140093b1ec2232d5123df9941b8b0ec34244b4
 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": 0.0017376194613379669,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.022589052997393572,
+  "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": 0.0017376194613379669,
       "eval_loss": 2.3447093963623047,
-      "eval_runtime": 16.1608,
-      "eval_samples_per_second": 15.036,
-      "eval_steps_per_second": 7.549,
+      "eval_runtime": 16.2614,
+      "eval_samples_per_second": 14.943,
+      "eval_steps_per_second": 7.502,
       "step": 1
+    },
+    {
+      "epoch": 0.008688097306689836,
+      "grad_norm": 0.824364960193634,
+      "learning_rate": 5e-05,
+      "loss": 2.2515,
+      "step": 5
+    },
+    {
+      "epoch": 0.01737619461337967,
+      "grad_norm": 0.957850992679596,
+      "learning_rate": 0.0001,
+      "loss": 2.2288,
+      "step": 10
+    },
+    {
+      "epoch": 0.01737619461337967,
+      "eval_loss": 2.035438299179077,
+      "eval_runtime": 16.4926,
+      "eval_samples_per_second": 14.734,
+      "eval_steps_per_second": 7.397,
+      "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": 164782292336640.0,
+  "total_flos": 2677712250470400.0,
   "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 sha256:38dd4b0105d0d92b592d72fd1e2940a7a3060d5afcb9fcd4c32f547eb5dd5081
+oid sha256:2e30951e18552af902ba67d52c6e179dec005a6720f12c52f8c205df06e5fbb6
 size 6776