Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
     "o_proj",
-    "gate_proj",
-    "down_proj",
+    "v_proj",
     "q_proj",
     "up_proj",
-    "v_proj"
+    "k_proj",
+    "down_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 sha256:169f8cfa4504bb49d8114d4d3c30cbf9e75b9701749793a23c27f90833ac6107
+oid sha256:276f2a8994cfe821febcebef73f49c631dadfbe9f5aea69886da68df226b0446
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dd7c06ca03c4048b5a6b6b2fd8b16c8333ac5797e50354c38316dbd6ef122e6
+oid sha256:94e3f3a2ce21d140b56527f4f67754dbecb87538c51ba12ab83aa34aecf737d7
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e7b432d4c1390a80984e093813a079e02823704a7187bbae0ecafb3a9eb8384
+oid sha256:9aab570b4fe164a545749c52e1fee2e82c42fd074cc4792050df7927c2e3f881
 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": 0.002844950213371266,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.03698435277382646,
+  "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": 0.002844950213371266,
       "eval_loss": 10.37409496307373,
-      "eval_runtime": 0.8568,
-      "eval_samples_per_second": 172.74,
-      "eval_steps_per_second": 86.37,
+      "eval_runtime": 0.8696,
+      "eval_samples_per_second": 170.187,
+      "eval_steps_per_second": 85.094,
       "step": 1
+    },
+    {
+      "epoch": 0.01422475106685633,
+      "grad_norm": 0.023065494373440742,
+      "learning_rate": 5e-05,
+      "loss": 10.3786,
+      "step": 5
+    },
+    {
+      "epoch": 0.02844950213371266,
+      "grad_norm": 0.0242258682847023,
+      "learning_rate": 0.0001,
+      "loss": 10.3796,
+      "step": 10
+    },
+    {
+      "epoch": 0.02844950213371266,
+      "eval_loss": 10.374069213867188,
+      "eval_runtime": 0.8623,
+      "eval_samples_per_second": 171.641,
+      "eval_steps_per_second": 85.82,
+      "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": 22629089280.0,
+  "total_flos": 297410887680.0,
   "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 sha256:4381bb867a7adfc1b256df8dee18d64bda817cc96106f4b25ec62eaeae782287
+oid sha256:cd7b5d6239d0385bfb31ea61b5b81d4a8d1d785036238dc4d07694db5336129c
 size 6776