Training in progress, step 5, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "up_proj",
     "down_proj",
-    "v_proj",
-    "gate_proj",
     "k_proj",
-    "up_proj",
-    "q_proj",
-    "o_proj"
+    "gate_proj",
+    "v_proj",
+    "o_proj",
+    "q_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 sha256:4ada2c5ec5b4371543aed0f7be3aea49c76b93537458e515f9ead502e5d9bcde
+oid sha256:0857a619aafb49decf7c0c3aa0b3f44d89ae2a5dacb282a7c2b7261c7ae22945
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c7e8c01ff764f75e5b4ab876719c0edacd4e6224ab927590da2a0e8d26fc481
+oid sha256:cfa06d73bf719b42d30df00e4dbc39b48efb2ba17cb1fc1105d17392096295ca
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e2c76845d1a198321567d417f508e36c6488ae79ee6a5814ae3463528c38bff
+oid sha256:5dea2ef208c10a86ca9ed2a34e32599c6c0ca9d4389302f15632a19932d3b137
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:2e92960d0ad68073c6e6b116e14520b81f435299a083290ea93ec9fbc07aa45b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.05904059040590406,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.2952029520295203,
+  "eval_steps": 4,
+  "global_step": 5,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,25 @@
     {
       "epoch": 0.05904059040590406,
       "eval_loss": 4.401196002960205,
-      "eval_runtime": 6.1513,
-      "eval_samples_per_second": 18.533,
+      "eval_runtime": 6.15,
+      "eval_samples_per_second": 18.537,
       "eval_steps_per_second": 2.439,
       "step": 1
+    },
+    {
+      "epoch": 0.23616236162361623,
+      "eval_loss": 3.7895731925964355,
+      "eval_runtime": 6.1455,
+      "eval_samples_per_second": 18.55,
+      "eval_steps_per_second": 2.441,
+      "step": 4
     }
   ],
   "logging_steps": 10,
-  "max_steps": 1,
+  "max_steps": 17,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
-  "save_steps": 1,
+  "num_train_epochs": 2,
+  "save_steps": 5,
   "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": 2959302797033472.0,
+  "total_flos": 1.479651398516736e+16,
   "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:ee7cd1877734bd4b9abb4a58b06474130320f0f83a62224820960eedaa2e8bc6
+oid sha256:efac76133d6f1c11f69092f5a4db649e61c286bf3a2a79e238127e4db84af950
 size 6776