Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
+    "up_proj",
     "down_proj",
-    "gate_proj",
     "o_proj",
-    "up_proj",
-    "v_proj",
     "k_proj",
-    "q_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:c4b736f698a9058b9609ed9d5d5179bc10f99363e1881d3f796c5a23980306fa
+oid sha256:d17ec9ad9b293d87edfa9c0f601c7d14d6f92b3ab56dc55be0ce7e6d1e5c436d
 size 30026872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:063b813ba858f170a99e04e3dab6c00784b6e21ead60347609ed2abf89347061
+oid sha256:cef71a48c363dc511e52f1e124b312815a37b5ee7813e7ac00e8f16f9fa57296
 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": 1.3869962169678183e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.00018030950820581638,
+  "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": 1.3869962169678183e-05,
       "eval_loss": 0.3170296847820282,
-      "eval_runtime": 1022.0198,
-      "eval_samples_per_second": 29.704,
-      "eval_steps_per_second": 14.852,
+      "eval_runtime": 1026.3822,
+      "eval_samples_per_second": 29.578,
+      "eval_steps_per_second": 14.789,
       "step": 1
+    },
+    {
+      "epoch": 6.934981084839092e-05,
+      "grad_norm": 0.6361538171768188,
+      "learning_rate": 5e-05,
+      "loss": 0.2943,
+      "step": 5
+    },
+    {
+      "epoch": 0.00013869962169678183,
+      "grad_norm": 0.7165965437889099,
+      "learning_rate": 0.0001,
+      "loss": 0.2509,
+      "step": 10
+    },
+    {
+      "epoch": 0.00013869962169678183,
+      "eval_loss": 0.20657119154930115,
+      "eval_runtime": 1002.4208,
+      "eval_samples_per_second": 30.285,
+      "eval_steps_per_second": 15.142,
+      "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 sha256:5ce8995130a5b109e162b994f342251f2b6519a411ac03b810f0825687d1ab9c
+oid sha256:e107824bc711f43ed63c6bf8543cbd2d0313884363703845449281d8961d75e3
 size 6776