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",
-    "k_proj",
     "up_proj",
-    "gate_proj",
-    "v_proj",
+    "k_proj",
     "o_proj",
+    "v_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 sha256:1c67b2d622363724fa52c3c0b194a11bf8ee8727aba4d524360f7caa4924eaf3
+oid sha256:cf4b635aa01c922edbb8d060f069b5cc6568f830534f70044b725d5ef769305f
 size 15182728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03ac757efc8757e97e6b66e9eda027d877ed8c19194f90ba46eb0c3d8a0bf92e
+oid sha256:e809dc632ec111cad708b92a10b9b06f74d52bade391a9d18def2399ca2123ab
 size 8075796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81b0fa30ce7d6caf58ef5c2227062e5ee5947fe33564486703caa8d601663ea6
+oid sha256:961100a4b179f4eb1baf0cb59fb9c8d73f1fd8a14348104a4c7a06d19e1b9f07
 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": 0.0011614401858304297,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.015098722415795587,
+  "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": 0.0011614401858304297,
       "eval_loss": 10.543993949890137,
-      "eval_runtime": 15.6722,
-      "eval_samples_per_second": 23.162,
-      "eval_steps_per_second": 11.613,
+      "eval_runtime": 15.4761,
+      "eval_samples_per_second": 23.456,
+      "eval_steps_per_second": 11.76,
       "step": 1
+    },
+    {
+      "epoch": 0.005807200929152149,
+      "grad_norm": 17.568485260009766,
+      "learning_rate": 5e-05,
+      "loss": 11.0235,
+      "step": 5
+    },
+    {
+      "epoch": 0.011614401858304297,
+      "grad_norm": 14.37784481048584,
+      "learning_rate": 0.0001,
+      "loss": 9.1467,
+      "step": 10
+    },
+    {
+      "epoch": 0.011614401858304297,
+      "eval_loss": 8.194717407226562,
+      "eval_runtime": 13.4328,
+      "eval_samples_per_second": 27.023,
+      "eval_steps_per_second": 13.549,
+      "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": 15344760520704.0,
+  "total_flos": 186055221313536.0,
   "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:b6da68b9dccc9797752e82795ecd556d16bfa0452de13085898654dfe8661752
+oid sha256:9db4fc0b12fe4a5ab1120d2f293d4ffe31cac375b0d128b81a41b3077d4ffe9e
 size 6776