Training in progress, step 7, checkpoint

last-checkpoint/adapter_config.json

@@ -21,14 +21,14 @@
   "revision": null,
   "target_modules": [
     "v_proj",
-    "up_proj",
-    "o_proj",
+    "gate",
     "down_proj",
+    "k_proj",
     "gate_proj",
     "shared_expert_gate",
+    "o_proj",
     "q_proj",
-    "gate",
-    "k_proj"
+    "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:e32c601ba52fef63e6b22206e0ace31eaca40ab76fa171e79b9a128171baf88f
+oid sha256:20db5a33a39460601b4e9b8ea50e0d58a4f453f6af5b1939af6414d75387220a
 size 327040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c1d0aacf3db53c2726862b73ae4e571ec2a1232e70213f161ad5c774b8c11d9
+oid sha256:083281d4de1e4435e06c5c33bbbb4388616de2668bdd8f88ee2823283b636f00
 size 739258

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73476fe3323b995ecb3d39d86131fa778d3b89acf6d3b0af55de4835be2b7627
+oid sha256:65370118f607e09d6381397903a67c7ae938a6fbd645e372609f9bfe9fb51de6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:e6974b3faf746b0cd5ad484ee0aa41b3416e51a6dcce41ba35e954232a5c6d57
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04081632653061224,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.2857142857142857,
+  "eval_steps": 5,
+  "global_step": 7,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,25 @@
     {
       "epoch": 0.04081632653061224,
       "eval_loss": 11.885836601257324,
-      "eval_runtime": 2.3264,
-      "eval_samples_per_second": 70.924,
-      "eval_steps_per_second": 9.027,
+      "eval_runtime": 2.4584,
+      "eval_samples_per_second": 67.116,
+      "eval_steps_per_second": 8.542,
       "step": 1
+    },
+    {
+      "epoch": 0.20408163265306123,
+      "eval_loss": 11.879362106323242,
+      "eval_runtime": 1.6783,
+      "eval_samples_per_second": 98.315,
+      "eval_steps_per_second": 12.513,
+      "step": 5
     }
   ],
   "logging_steps": 10,
-  "max_steps": 1,
+  "max_steps": 25,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
-  "save_steps": 1,
+  "num_train_epochs": 2,
+  "save_steps": 7,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -29,12 +37,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 4004989894656.0,
+  "total_flos": 27784617394176.0,
   "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 sha256:651a0a36d7bf8f0d7da7c8ca3e19a8983a529f385507c1b56457092466d962ea
+oid sha256:68264bad378a3786e373b10a7929344fa7e3753d90d483071dfcff2369324455
 size 6776