Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,15 +20,15 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "up_proj",
-    "k_proj",
+    "shared_expert_gate",
     "q_proj",
     "down_proj",
+    "gate",
+    "k_proj",
     "o_proj",
+    "v_proj",
     "gate_proj",
-    "shared_expert_gate",
-    "gate"
+    "up_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 sha256:292b29d8f127c5a9d0879eb791fce27a6fc37739d31871b0b4f88f8da014dada
+oid sha256:613dc418f7f74ba2a5e952a581791c7e59dfeaf2b044fc763fec17368fae2186
 size 327040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ed75ed7fa6018841b7790942a95dc4065eec6767ce60600eee3e9b25578e58a
+oid sha256:5a573bb6cb6617be66ff7785c97ee016b85b178bb980c64fa626adb6dac89996
 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": 0.000899685110211426,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.011695906432748537,
+  "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": 0.000899685110211426,
       "eval_loss": 11.939785957336426,
-      "eval_runtime": 11.7071,
-      "eval_samples_per_second": 39.976,
-      "eval_steps_per_second": 19.988,
+      "eval_runtime": 11.7148,
+      "eval_samples_per_second": 39.95,
+      "eval_steps_per_second": 19.975,
       "step": 1
+    },
+    {
+      "epoch": 0.00449842555105713,
+      "grad_norm": 0.35622671246528625,
+      "learning_rate": 5e-05,
+      "loss": 11.9281,
+      "step": 5
+    },
+    {
+      "epoch": 0.00899685110211426,
+      "grad_norm": 0.3019970655441284,
+      "learning_rate": 0.0001,
+      "loss": 11.9394,
+      "step": 10
+    },
+    {
+      "epoch": 0.00899685110211426,
+      "eval_loss": 11.937747955322266,
+      "eval_runtime": 11.3246,
+      "eval_samples_per_second": 41.326,
+      "eval_steps_per_second": 20.663,
+      "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": 125155934208.0,
+  "total_flos": 1627027144704.0,
   "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:d33f67516e28755d6adf60072f81b922c0dd586d6ad5dd4e7c3e1a92ce2273a0
+oid sha256:db308e89136268b0b7904fb33e4d5d741e59a3dc3d198b678512630250a15cf4
 size 6776