Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "up_proj",
+    "gate_proj",
     "q_proj",
-    "v_proj",
-    "o_proj",
     "k_proj",
     "down_proj",
-    "up_proj",
-    "gate_proj"
+    "v_proj",
+    "o_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:f5eb94fd0b794a7b02e079deee7e3f434311aadadb1f1af7c1c2ce8b127a782e
+oid sha256:32fad1b4a6cfbf64ccb3c2b56a0a3337e86cced641d298680d28953c8da2bb01
 size 31064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70ed385595c4c11eb28ccf59177e62cfea4b0cbfbede38f745fe19163fc5d71e
+oid sha256:7765de56b74eee6e9767e639b5e8e5674c17d9832772a72d3533e361526e2940
 size 71718

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:106d2362bc2f5d0877cb3549f0a8edc5f2a3f7ece3ea2591042b0fa260c47153
+oid sha256:15160272ffddfe27c654df211d1192733c9457f0ce97b19578f9cd078fb647f8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:5adea6def46a60dd5782726d51a89bdf0f30226cd791e511d8af09a5644f99e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0005166289958023894,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.006716176945431062,
+  "eval_steps": 10,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,32 @@
     {
       "epoch": 0.0005166289958023894,
       "eval_loss": 10.335664749145508,
-      "eval_runtime": 18.6854,
-      "eval_samples_per_second": 697.87,
-      "eval_steps_per_second": 87.234,
+      "eval_runtime": 18.7204,
+      "eval_samples_per_second": 696.565,
+      "eval_steps_per_second": 87.071,
       "step": 1
+    },
+    {
+      "epoch": 0.005166289958023894,
+      "grad_norm": 4.865599632263184,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 165.3473,
+      "step": 10
+    },
+    {
+      "epoch": 0.005166289958023894,
+      "eval_loss": 10.329593658447266,
+      "eval_runtime": 18.6761,
+      "eval_samples_per_second": 698.217,
+      "eval_steps_per_second": 87.277,
+      "step": 10
     }
   ],
   "logging_steps": 10,
-  "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 +44,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 410637041664.0,
+  "total_flos": 5338281541632.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74724f7aab653cb9078480700847373aab4c35780a242593291b93c967223a75
+oid sha256:45be2b6fbf5b9c3212f5a19239f66bc7a8ca08432b564bfe1dacea75e0989398
 size 6776