Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "dense_4h_to_h",
     "query_key_value",
-    "dense_h_to_4h",
-    "dense"
+    "dense",
+    "dense_4h_to_h",
+    "dense_h_to_4h"
   ],
   "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:afec2e167d02305961723bcb60b778a811b065918541146a0f9944378a84385e
+oid sha256:4a1a3a5f348f61dab70b976b7d82f39f98790c253e1e912f4a33b9ead930958a
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5c476469d86725bc5ff14a1791296fa302f82a92826badfc2778a1ed2e1385a
+oid sha256:94d725944cbb76cf8453af7a89cc2275c4081ba19924b43ff407100d03146c07
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b1d1b309a6677be71a8938daa809110565e16401744df9934ffc4e3496689ba
+oid sha256:c37277c3184b4d285ecca2d2dc91cd20803c4708254c0ba195c7bb32ae9c5a42
 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": 0.003683241252302026,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.04788213627992634,
+  "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": 0.003683241252302026,
       "eval_loss": 11.133610725402832,
-      "eval_runtime": 1.5839,
-      "eval_samples_per_second": 72.605,
-      "eval_steps_per_second": 36.618,
+      "eval_runtime": 1.5856,
+      "eval_samples_per_second": 72.529,
+      "eval_steps_per_second": 36.58,
       "step": 1
+    },
+    {
+      "epoch": 0.01841620626151013,
+      "grad_norm": 1.6393567323684692,
+      "learning_rate": 5e-05,
+      "loss": 44.5133,
+      "step": 5
+    },
+    {
+      "epoch": 0.03683241252302026,
+      "grad_norm": 1.8768304586410522,
+      "learning_rate": 0.0001,
+      "loss": 44.5122,
+      "step": 10
+    },
+    {
+      "epoch": 0.03683241252302026,
+      "eval_loss": 11.1190185546875,
+      "eval_runtime": 0.5822,
+      "eval_samples_per_second": 197.527,
+      "eval_steps_per_second": 99.623,
+      "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": 14467203072.0,
+  "total_flos": 137438429184.0,
   "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:d240c8808d38a77504653032a79055be3ccd337e883bd283a8c6fb30bac1ece9
+oid sha256:8bbdde4d3f1bbc49dceb4d5306047672018e8e4918bd4b718ad70b0e25d92d1b
 size 6776