Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
+    "down_proj",
     "v_proj",
-    "q_proj",
-    "o_proj",
     "gate_proj",
-    "down_proj",
-    "k_proj"
+    "k_proj",
+    "up_proj",
+    "o_proj",
+    "q_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:a9c12994ecf1f48ce8f75db49568b95ef5e5e621ff676e385a20ca4e41a007c9
+oid sha256:d1b88dbf60ae5eea9fcc7fdfce4db43696348853006521f33923eba5f6402be1
 size 59827904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b6de4428d8a1002e9f1a9a352b0e1b686f90a04cf27f85eccd6cc46c9921084
+oid sha256:05ca6eb77df6de7a2c08d25f9e16f833e29c3197229f1676e81a6dd80455f6ae
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6707750ad49ef0d13e0fd5e194157f4b49f1aea87ec5478e49d3a8843b67646e
+oid sha256:4e48bfc636f578b9b2f062a57e27b15e20a03c09bb2635a38625f9cbb1938f36
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:5adea6def46a60dd5782726d51a89bdf0f30226cd791e511d8af09a5644f99e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0008107423359513554,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.010539650367367622,
+  "eval_steps": 10,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,32 @@
     {
       "epoch": 0.0008107423359513554,
       "eval_loss": NaN,
-      "eval_runtime": 566.3625,
-      "eval_samples_per_second": 14.673,
-      "eval_steps_per_second": 1.835,
+      "eval_runtime": 570.4037,
+      "eval_samples_per_second": 14.569,
+      "eval_steps_per_second": 1.822,
       "step": 1
+    },
+    {
+      "epoch": 0.008107423359513555,
+      "grad_norm": NaN,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.008107423359513555,
+      "eval_loss": NaN,
+      "eval_runtime": 567.6362,
+      "eval_samples_per_second": 14.64,
+      "eval_steps_per_second": 1.83,
+      "step": 10
     }
   ],
   "logging_steps": 10,
-  "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 +44,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 2939306234609664.0,
+  "total_flos": 3.793542109043098e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38fa6cbcc22db55004acf3304c1b13ec4148a4a5c982778c8eb56f72274c27dc
+oid sha256:3460bc1049458249050bb8e121240faa25b0f5a3a8d73f6dcbbbba955d6d2e1e
 size 6776