Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "up_proj",
     "v_proj",
-    "down_proj",
-    "o_proj",
     "gate_proj",
-    "q_proj",
-    "up_proj",
-    "k_proj"
+    "k_proj",
+    "o_proj",
+    "down_proj",
+    "q_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:c3d4386d035ef7d238f9590d167c3d6b99395d45dd286f482ecba095933b8d9d
+oid sha256:1132b3b3d30fdd06f039a4f2513671b769a1a3e0a44f4d2c38d6c09f09711eca
 size 30026872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e7dffc524fc1a0338ad48fdb6820f29f6a2e079a14ceb06176878dedccb1a02
+oid sha256:c43468d13e471ba94ddb2d7826f4ce779aa8ed6698d4e298ae751478620c26f0
 size 15611412

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81b0fa30ce7d6caf58ef5c2227062e5ee5947fe33564486703caa8d601663ea6
+oid sha256:7a2043fcab6393039914b1ae1d41f0b06c9cc65053e1770339d2cdf1b4d4fcd1
 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": 0.0008680555555555555,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.011284722222222222,
+  "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": 0.0008680555555555555,
       "eval_loss": 4.605380535125732,
-      "eval_runtime": 16.2314,
-      "eval_samples_per_second": 29.88,
-      "eval_steps_per_second": 14.971,
+      "eval_runtime": 21.8282,
+      "eval_samples_per_second": 22.219,
+      "eval_steps_per_second": 11.132,
       "step": 1
+    },
+    {
+      "epoch": 0.004340277777777778,
+      "grad_norm": 1.5089558362960815,
+      "learning_rate": 5e-05,
+      "loss": 4.1534,
+      "step": 5
+    },
+    {
+      "epoch": 0.008680555555555556,
+      "grad_norm": 1.6227378845214844,
+      "learning_rate": 0.0001,
+      "loss": 4.2115,
+      "step": 10
+    },
+    {
+      "epoch": 0.008680555555555556,
+      "eval_loss": 4.272531509399414,
+      "eval_runtime": 17.0616,
+      "eval_samples_per_second": 28.426,
+      "eval_steps_per_second": 14.243,
+      "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": 31638725591040.0,
+  "total_flos": 411303432683520.0,
   "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 sha256:22483113d00e2d8a172f69868a7a23d89d4778926e5d39c2a5ff77c97d051d14
+oid sha256:29340c1e10c1f94ceba3417a7b81496c6f7319ee4e1dffb14d2f7a7fd143859e
 size 6776