Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "gate_proj",
-    "o_proj",
     "q_proj",
-    "v_proj",
+    "up_proj",
     "k_proj",
-    "up_proj"
+    "o_proj",
+    "v_proj",
+    "down_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 sha256:2bf2166f7d5db9e19a7aee636548700f53d84bdf69c99f30910dbe8b9ca1eeb8
+oid sha256:2a44eabbd98367da5e06bd09fbaab23ea7ad27dd95e176c5ca59984fe4ae7252
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1360b214dc305ce0c7fca0fdb3feecc9d03ca3af798b10af45b117b0f4bff123
+oid sha256:104644b1e0f4096a109aad6b9d45bf07fa33aa589ece5eafdd415bfdffce3ccf
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b76b336792a659bf71c4342297577ae1a29c83058d83e060278f3e4892b1ec99
+oid sha256:3bff4ab9696c1362d81fbf7848bd8c3940e7cbc2a87a971f78dc0b2f0693aa5c
 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": 0.0199501246882793,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.2593516209476309,
+  "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": 0.0199501246882793,
       "eval_loss": NaN,
-      "eval_runtime": 18.3052,
-      "eval_samples_per_second": 18.465,
-      "eval_steps_per_second": 2.349,
+      "eval_runtime": 18.3172,
+      "eval_samples_per_second": 18.453,
+      "eval_steps_per_second": 2.348,
       "step": 1
+    },
+    {
+      "epoch": 0.19950124688279303,
+      "grad_norm": NaN,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.19950124688279303,
+      "eval_loss": NaN,
+      "eval_runtime": 17.3044,
+      "eval_samples_per_second": 19.533,
+      "eval_steps_per_second": 2.485,
+      "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": 2788217673744384.0,
+  "total_flos": 3.624682975867699e+16,
   "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 sha256:304127fa9cc2db466d36f9c963793b3c1568b3fb87f4fcdf6f091fee10a48303
+oid sha256:3e216c35f63ee8912b92c20c9ee2096430f2861e01a96d1134c1cdbf1f1ffdbd
 size 6776