Training in progress, step 6, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "q_proj",
-    "gate_proj",
     "v_proj",
-    "k_proj",
     "o_proj",
+    "up_proj",
+    "k_proj",
     "down_proj",
-    "up_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 sha256:58381105673501d4d8bad28841e785d584e9276e7cace84af36e0b2e0b9e9e9e
+oid sha256:e6098006021aadc2c1eff8c9f0924145d3b1edea00a54f430721973557d6ce3e
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b91657d2ce66e7a72d574c3a4b0b156254a2bffb63b5e7ee34b9f92986aa774
+oid sha256:f63310612f6842cc468d95ffc3944eb0588e9a4719ba9b2bb005385a678e6f79
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48707ce5b888f5fb4ed0bb81e0d8f92699172e8647e4e04f8cf50ce6a8cd793a
+oid sha256:02e7c22ebd8430ac28d79c96f2d6af0dd481cf136cf7ca7a6dc119ced964a19e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:e623ab4637ca988714bb2f8da321af396105524aa2dc294588565e47ac87dff6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.046242774566473986,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.2774566473988439,
+  "eval_steps": 5,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,25 @@
     {
       "epoch": 0.046242774566473986,
       "eval_loss": 15.64744758605957,
-      "eval_runtime": 3.8686,
-      "eval_samples_per_second": 37.74,
-      "eval_steps_per_second": 4.911,
+      "eval_runtime": 3.8022,
+      "eval_samples_per_second": 38.399,
+      "eval_steps_per_second": 4.997,
       "step": 1
+    },
+    {
+      "epoch": 0.23121387283236994,
+      "eval_loss": 14.13701343536377,
+      "eval_runtime": 2.8906,
+      "eval_samples_per_second": 50.508,
+      "eval_steps_per_second": 6.573,
+      "step": 5
     }
   ],
   "logging_steps": 10,
-  "max_steps": 1,
+  "max_steps": 22,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
-  "save_steps": 1,
+  "num_train_epochs": 2,
+  "save_steps": 6,
   "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": 518877213622272.0,
+  "total_flos": 3113263281733632.0,
   "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 sha256:260fa222ef872a5b775a6b0a028e89b9d3192a6085ebb5108a99ac7865fd3d07
+oid sha256:089cb18b63dc7db043fa94fe0e4c7973472ac7d8e3a32173134622601f46a0b5
 size 6776