Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "o_proj",
+    "up_proj",
+    "v_proj",
     "k_proj",
+    "o_proj",
     "q_proj",
-    "down_proj",
-    "up_proj",
-    "v_proj"
+    "gate_proj",
+    "down_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 sha256:39eb63d4d9a7c5cc0d42aa80780f0b3b2d65f88ebe6939f06aa80ef5bd78e24a
+oid sha256:9f0d3e79973f2b33d821cff2abfb94df6c9e53806004a5dc4c05efd6dfbf6674
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f484f6b733dd21bbc302654da308a1a3dbe606eafa91c374f08250c8390c36a6
+oid sha256:dc17393ab266877a11bb741a343f756c77d109f602957104463039fa04d41e17
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb1228e8df97a1d799b51d461e89faa3c8b34af3eaad77d8523d93156c1e565e
+oid sha256:4cc289ca89ed37bf50c2f838c7574993fbc613d6d7d723cf73cfe31d185c0abf
 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": 6.72777731057102e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0008746110503742326,
+  "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": 6.72777731057102e-05,
       "eval_loss": 7.581191062927246,
-      "eval_runtime": 710.7624,
-      "eval_samples_per_second": 8.806,
-      "eval_steps_per_second": 4.404,
+      "eval_runtime": 709.9549,
+      "eval_samples_per_second": 8.816,
+      "eval_steps_per_second": 4.409,
       "step": 1
+    },
+    {
+      "epoch": 0.00033638886552855103,
+      "grad_norm": 4.927368640899658,
+      "learning_rate": 5e-05,
+      "loss": 7.893,
+      "step": 5
+    },
+    {
+      "epoch": 0.0006727777310571021,
+      "grad_norm": 7.293655872344971,
+      "learning_rate": 0.0001,
+      "loss": 6.5889,
+      "step": 10
+    },
+    {
+      "epoch": 0.0006727777310571021,
+      "eval_loss": 5.774456024169922,
+      "eval_runtime": 715.6571,
+      "eval_samples_per_second": 8.746,
+      "eval_steps_per_second": 4.374,
+      "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": 162874924204032.0,
+  "total_flos": 2117374014652416.0,
   "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:c380c88ecbce849d53d54f441f766883ed0be8c07a7129266de27393d7ecce88
+oid sha256:a279e01eff88d09147a03ffa784fb601d18c448423bece5daeb26b93bd311c1f
 size 6776