Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "q_proj",
+    "down_proj",
+    "up_proj",
     "gate_proj",
-    "k_proj",
-    "v_proj",
     "o_proj",
-    "up_proj",
-    "down_proj",
-    "q_proj"
+    "k_proj",
+    "v_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 sha256:4d6a25fd880244154e4d4897800b09af627e05542832bd1a3f9368aa7d638d96
+oid sha256:07b3170f6e4ef469f0d58b932668a8dc484e2a44da4f186a795ee76fe80a636b
 size 48679352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24085ed3edb0c59a04ac71989703a39e1490986c4cb9ae688c7289432ca7dd60
+oid sha256:9c86cf09444386e9c2e5176df5c61272676da27456ebf6ee92c5880ef90a67ef
 size 25152500

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9034bb07100d4d5fe064a548c77d3ad73a5b37b5251e971860770351450dad98
+oid sha256:c2c7058834f0b42574671bb1efa6a376d5ff9ed145f77dd733fea3ae5e3d2a17
 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": 1.0725384572070562e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0001394299994369173,
+  "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": 1.0725384572070562e-05,
       "eval_loss": 4.963016510009766,
-      "eval_runtime": 1679.8111,
-      "eval_samples_per_second": 23.37,
-      "eval_steps_per_second": 11.685,
+      "eval_runtime": 1676.1374,
+      "eval_samples_per_second": 23.422,
+      "eval_steps_per_second": 11.711,
       "step": 1
+    },
+    {
+      "epoch": 5.362692286035281e-05,
+      "grad_norm": 3.8062756061553955,
+      "learning_rate": 5e-05,
+      "loss": 4.2082,
+      "step": 5
+    },
+    {
+      "epoch": 0.00010725384572070562,
+      "grad_norm": 3.690264940261841,
+      "learning_rate": 0.0001,
+      "loss": 4.3208,
+      "step": 10
+    },
+    {
+      "epoch": 0.00010725384572070562,
+      "eval_loss": 4.493514537811279,
+      "eval_runtime": 1657.1732,
+      "eval_samples_per_second": 23.69,
+      "eval_steps_per_second": 11.845,
+      "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": 69572304568320.0,
+  "total_flos": 904439959388160.0,
   "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 sha256:5071391257c583f0ae492ef9429aad07893c38ee79dd5c287a99c0cf07321d2f
+oid sha256:9edc5e2c63b4d41a247678716b964e2ee0ee1926f783a36fbe7c87e62e61b469
 size 6776