Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
+    "k_proj",
     "q_proj",
     "down_proj",
-    "gate_proj",
-    "k_proj",
     "up_proj",
+    "gate_proj",
+    "o_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 sha256:2523cac36b8c088834355d412c34d76530cd8c9eeaeb739be68f48a39bdf499a
+oid sha256:d574e798a2340598317c1894d731011de2a862f4bdd2d315554dac83ce731fcb
 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:bb42603c6ea93282cd7b812e4230cfeb74ceecfc7f6b103a7e0220f43cb7ac48
+oid sha256:964b51194509c7d9a2a56164d5ac73ba4ddffd6931b09a94789cd55284cb492b
 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": 4.142115999958579e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0005384750799946153,
+  "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": 4.142115999958579e-05,
       "eval_loss": NaN,
-      "eval_runtime": 382.9606,
-      "eval_samples_per_second": 26.546,
-      "eval_steps_per_second": 13.273,
+      "eval_runtime": 387.6938,
+      "eval_samples_per_second": 26.222,
+      "eval_steps_per_second": 13.111,
       "step": 1
+    },
+    {
+      "epoch": 0.00020710579999792895,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.0004142115999958579,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.0004142115999958579,
+      "eval_loss": NaN,
+      "eval_runtime": 385.1185,
+      "eval_samples_per_second": 26.397,
+      "eval_steps_per_second": 13.199,
+      "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": 32429825851392.0,
+  "total_flos": 421587736068096.0,
   "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 sha256:006839ecc105a05a0d496065bc51b128e992e6e07bcf03bc9644a82ce38f3241
+oid sha256:3a706fe43f6fd7c94eac7055c56f007a7220646b21d2685d7e12af09c068b9c7
 size 6776