Training in progress, step 4, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
+    "q_proj",
+    "k_proj",
     "up_proj",
     "gate_proj",
     "v_proj",
-    "q_proj",
     "down_proj",
-    "k_proj"
+    "o_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:b169cbaadad27dbda299f868a672b8bb9796e4dc87e2f391dc3132de8b1195ce
+oid sha256:7f88cd15b55ec3910090ecf671b7c908a32eb037a28c7ec9dc4975bac5c64e32
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0be533480879f779e72ab62a5cf3db947598eb3f9ca92a2780fff0a61dfb7b25
+oid sha256:6f5c221111fa801050dc8cfb13936a8dd7b854765f9792d31ad95c06bf175560
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ea10a660dede97133ad18fb7008f183f30f2953a178eb32365b1be16b2d4aac
+oid sha256:3c0bbb306fdf2a9c6f22012e2560342a42c3fcf90a6e2a76b53510526bffab00
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:358e8bc951b85c49677e3825ec17f859726912aefbf8b4a751a4462ca4dc230c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0642570281124498,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.2570281124497992,
+  "eval_steps": 4,
+  "global_step": 4,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,25 @@
     {
       "epoch": 0.0642570281124498,
       "eval_loss": 2.4946258068084717,
-      "eval_runtime": 3.2732,
-      "eval_samples_per_second": 32.079,
-      "eval_steps_per_second": 4.277,
+      "eval_runtime": 3.2848,
+      "eval_samples_per_second": 31.965,
+      "eval_steps_per_second": 4.262,
       "step": 1
+    },
+    {
+      "epoch": 0.2570281124497992,
+      "eval_loss": 1.9453781843185425,
+      "eval_runtime": 3.3308,
+      "eval_samples_per_second": 31.524,
+      "eval_steps_per_second": 4.203,
+      "step": 4
     }
   ],
   "logging_steps": 10,
-  "max_steps": 1,
+  "max_steps": 16,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
-  "save_steps": 1,
+  "num_train_epochs": 2,
+  "save_steps": 4,
   "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": 800155729133568.0,
+  "total_flos": 3200622916534272.0,
   "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:c75c85f08f2c13b70fbd632fb454351ce2c764046e6889026297349212fab079
+oid sha256:9fda9532d357ff1fd16d10f70df337ecee0523c68cb5e22b753793c39818f8ac
 size 6776