Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,15 +20,15 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
     "q_proj",
+    "shared_expert_gate",
+    "gate_proj",
     "v_proj",
-    "gate",
     "k_proj",
     "up_proj",
+    "gate",
     "down_proj",
-    "gate_proj",
-    "shared_expert_gate"
+    "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:f39f6bf26cb50090be465cc764f74e9bc5ac17f17be6b92d0c218354321345b2
+oid sha256:e32de30c41f448cde19fce48f0221352cb72f430a1c9a5c27392ee60eaf354b7
 size 327040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7a477d102bad5e630167777290711ad1a83ba87784b37ba7f9ba0be6071ea29
+oid sha256:cff532841b983a6765e35de3103b7cefc0387780a6656fe6065038aa2ba32a35
 size 739258

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ca4e2bce515e7a88c44624c36d0bc76daf1fd306e88836f9dc2aaf5f09cd386
+oid sha256:cc4bf9c4f1190745e112de22c0a48a7c29f2de445f4aabf7c40b55516fff102e
 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": 7.224650507531698e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0009392045659791208,
+  "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": 7.224650507531698e-05,
       "eval_loss": 11.937585830688477,
-      "eval_runtime": 162.1036,
-      "eval_samples_per_second": 35.958,
-      "eval_steps_per_second": 17.982,
+      "eval_runtime": 162.9739,
+      "eval_samples_per_second": 35.766,
+      "eval_steps_per_second": 17.886,
       "step": 1
+    },
+    {
+      "epoch": 0.0003612325253765849,
+      "grad_norm": 0.09002860635519028,
+      "learning_rate": 5e-05,
+      "loss": 11.9366,
+      "step": 5
+    },
+    {
+      "epoch": 0.0007224650507531698,
+      "grad_norm": 0.0925336480140686,
+      "learning_rate": 0.0001,
+      "loss": 11.9363,
+      "step": 10
+    },
+    {
+      "epoch": 0.0007224650507531698,
+      "eval_loss": 11.936973571777344,
+      "eval_runtime": 162.0736,
+      "eval_samples_per_second": 35.965,
+      "eval_steps_per_second": 17.986,
+      "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": 219022884864.0,
+  "total_flos": 2628274618368.0,
   "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 sha256:8f8bfc4e432da6998ca18fcd6664e9c1d35f23d456a214fb1019bb0325ffea51
+oid sha256:11cee8b5f4028a12bb206185bfb42fe071f5620c1fbe0fb67df89315c43febbd
 size 6776