Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "up_proj",
+    "q_proj",
     "k_proj",
-    "o_proj",
     "down_proj",
-    "q_proj",
-    "gate_proj"
+    "o_proj",
+    "gate_proj",
+    "v_proj",
+    "up_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 sha256:52660d55eb696be12aa1761e98328632a25bb82d7650f1e1837a90468d41e7a0
+oid sha256:2c7629fc5e038cffb6c2b5a58af8d8a3240065f70684ec8e69efb67f072083e7
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54414a33a035a412937e1b3730653348b0815f8941e6844d71accf617da83afc
+oid sha256:09c37905b284ff49d49569a58eb7939db2e63c3d472c48128112580d574568d1
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0525df66869b0adf8d756d9e95d76ef7874d6f8df8ffd52f14c9f432ae93afc8
+oid sha256:f940394d31917ffb2b05fe76a0061afb3125719306bdf6e3d7cd408a94c74ecd
 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": 0.00014702098724592936,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0019112728341970817,
+  "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": 0.00014702098724592936,
       "eval_loss": 1.1351052522659302,
-      "eval_runtime": 258.6937,
-      "eval_samples_per_second": 11.071,
-      "eval_steps_per_second": 5.536,
+      "eval_runtime": 257.9243,
+      "eval_samples_per_second": 11.104,
+      "eval_steps_per_second": 5.552,
       "step": 1
+    },
+    {
+      "epoch": 0.0007351049362296467,
+      "grad_norm": 0.7017194628715515,
+      "learning_rate": 5e-05,
+      "loss": 1.0738,
+      "step": 5
+    },
+    {
+      "epoch": 0.0014702098724592935,
+      "grad_norm": 0.4884912967681885,
+      "learning_rate": 0.0001,
+      "loss": 0.9336,
+      "step": 10
+    },
+    {
+      "epoch": 0.0014702098724592935,
+      "eval_loss": 1.0464425086975098,
+      "eval_runtime": 258.5111,
+      "eval_samples_per_second": 11.079,
+      "eval_steps_per_second": 5.539,
+      "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": 323673743425536.0,
+  "total_flos": 3467932965273600.0,
   "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 sha256:9cebbbb8d3b1289569b4737f04902dcd49bc49df82e548a3fbdddbffe76c85b8
+oid sha256:6eb4bcac83ef6f08ea8d5b352ba9128b3dcf58cb76d868068a777b728f72c473
 size 6776