Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "q_proj",
-    "o_proj",
     "k_proj",
     "v_proj",
+    "q_proj",
     "up_proj",
+    "gate_proj",
+    "o_proj",
     "down_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93cb4552cff5c960d77ffee4a07412550de22405d05a5a5c557acf68e059a1b9
+oid sha256:f05ddf833d483aa8d1f7ed2aa5c36d35bb9153dd0a72f485fd8866d7b0ccfaae
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e8c1bbd2634f0b659456bb84da69a7c471a9e4d9bb473476a66f1975b7bc1c7
+oid sha256:0da03a42c1e6d62f9b50ba0d50bae633ce8733d5ab501e27c5b0e239aa87cd8a
 size 3633530

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5849fdb0611a67b736874e2e98b679d104499fdd916f8e171be9d574744d8b05
+oid sha256:0e7f37d1795b3a5f2badef6331eeaa3b12ee884a2d3e04816a3d1b46104eacde
 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": 0.000427715996578272,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.005560307955517536,
+  "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": 0.000427715996578272,
       "eval_loss": 0.9877161383628845,
-      "eval_runtime": 19.1122,
-      "eval_samples_per_second": 51.538,
-      "eval_steps_per_second": 25.795,
+      "eval_runtime": 18.7953,
+      "eval_samples_per_second": 52.407,
+      "eval_steps_per_second": 26.23,
       "step": 1
+    },
+    {
+      "epoch": 0.00213857998289136,
+      "grad_norm": 2.1632139682769775,
+      "learning_rate": 5e-05,
+      "loss": 0.8487,
+      "step": 5
+    },
+    {
+      "epoch": 0.00427715996578272,
+      "grad_norm": 1.2678030729293823,
+      "learning_rate": 0.0001,
+      "loss": 0.7846,
+      "step": 10
+    },
+    {
+      "epoch": 0.00427715996578272,
+      "eval_loss": 0.895944356918335,
+      "eval_runtime": 19.1514,
+      "eval_samples_per_second": 51.432,
+      "eval_steps_per_second": 25.742,
+      "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": 5143897571328.0,
+  "total_flos": 66870668427264.0,
   "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:d6d40d04477bc72efbe7e101a7eefd6c12aea59a0120862d8a148f608e9a142d
+oid sha256:7ea17b7e29e09b462c906a867419cca82716c15c8b855e4d24bbee2506edbcf1
 size 6776