Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
+    "down_proj",
     "k_proj",
-    "gate_proj",
     "up_proj",
+    "q_proj",
     "o_proj",
-    "v_proj",
-    "down_proj",
-    "q_proj"
+    "gate_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 sha256:923aa44b6b1c0d4b107df83a897ca9eed3503917a0358f0246add7cdb43e7e2c
+oid sha256:f61eea9c465853ea3c0b5eaf8600de7e94e5b851a8709179bcca7f4ba631405d
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1c840391a21fbb35ce4846a625e1f63917d6d5d754442f8daed3465d346a0e7
+oid sha256:d6b25c752847b616122f69c31210833d88a139298d792a264acf326e4f7f32f6
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b353bd32b2eceef37fa8b45cd65c7c835a171d164c7a48bb00b5a7a0c0a629f
+oid sha256:9501563c9e278a9c2879411cd7c6a1d119841ed683b45ebd2d4874924152dced
 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": 0.00016304569355561895,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0021195940162230466,
+  "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": 0.00016304569355561895,
       "eval_loss": NaN,
-      "eval_runtime": 111.545,
-      "eval_samples_per_second": 23.157,
-      "eval_steps_per_second": 11.583,
+      "eval_runtime": 111.361,
+      "eval_samples_per_second": 23.195,
+      "eval_steps_per_second": 11.602,
       "step": 1
+    },
+    {
+      "epoch": 0.0008152284677780948,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.0016304569355561896,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.0016304569355561896,
+      "eval_loss": NaN,
+      "eval_runtime": 109.7805,
+      "eval_samples_per_second": 23.529,
+      "eval_steps_per_second": 11.769,
+      "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": 56752195239936.0,
+  "total_flos": 681026342879232.0,
   "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 sha256:6acf0e734d913d863a5501a950fc3fbf105cdec9864e9670fda43f18e06d937c
+oid sha256:de3c4641a6c04f71129944915d5dda295a9d743d7849198b13d19c0ff2feecc8
 size 6776