Training in progress, step 1, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "k_proj",
-    "down_proj",
-    "q_proj",
     "up_proj",
+    "q_proj",
+    "v_proj",
     "o_proj",
-    "v_proj"
+    "gate_proj",
+    "down_proj",
+    "k_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 sha256:6fef6e7ce46d0278cc4b99c63b7e5086f495e2b61c0fb7cd24fa830c25afc127
+oid sha256:f96247efa86b609e12dd162dc43c74d0f3a75eab0249d631432c3bd13972b4dd
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb6d6f6c5158ac975edba3fbaa625888258d4f9ab6df91778d820f3a5fba6d23
+oid sha256:aac15eea5485c01d3befe07a14e9f7997d9dee335010a5c5b6c98dad423558e7
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:529c9e51cf346c9538de8a198d0e350de38ac30f5061dd3c6b0f0716ac464501
+oid sha256:792d1546ebf93af6d5f2808ada23d245a92ec7ea7130b1c43c380eba2e821f58
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
+oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.008454872120059184,
-  "eval_steps": 10,
-  "global_step": 50,
+  "epoch": 0.0001690974424011837,
+  "eval_steps": 1,
+  "global_step": 1,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,127 +11,17 @@
     {
       "epoch": 0.0001690974424011837,
       "eval_loss": 4.695179462432861,
-      "eval_runtime": 143.0078,
-      "eval_samples_per_second": 17.412,
-      "eval_steps_per_second": 8.706,
-      "step": 1
-    },
-    {
-      "epoch": 0.0008454872120059184,
-      "grad_norm": 7.00084114074707,
-      "learning_rate": 5e-05,
-      "loss": 4.7401,
-      "step": 5
-    },
-    {
-      "epoch": 0.0016909744240118367,
-      "grad_norm": 7.376851558685303,
-      "learning_rate": 0.0001,
-      "loss": 3.2596,
-      "step": 10
-    },
-    {
-      "epoch": 0.0016909744240118367,
-      "eval_loss": 1.1023823022842407,
-      "eval_runtime": 144.1442,
-      "eval_samples_per_second": 17.274,
+      "eval_runtime": 144.154,
+      "eval_samples_per_second": 17.273,
       "eval_steps_per_second": 8.637,
-      "step": 10
-    },
-    {
-      "epoch": 0.0025364616360177552,
-      "grad_norm": 1.906071662902832,
-      "learning_rate": 9.619397662556435e-05,
-      "loss": 0.4599,
-      "step": 15
-    },
-    {
-      "epoch": 0.0033819488480236735,
-      "grad_norm": 3.123356819152832,
-      "learning_rate": 8.535533905932738e-05,
-      "loss": 0.1822,
-      "step": 20
-    },
-    {
-      "epoch": 0.0033819488480236735,
-      "eval_loss": 0.15167798101902008,
-      "eval_runtime": 143.8966,
-      "eval_samples_per_second": 17.304,
-      "eval_steps_per_second": 8.652,
-      "step": 20
-    },
-    {
-      "epoch": 0.004227436060029592,
-      "grad_norm": 0.9577669501304626,
-      "learning_rate": 6.91341716182545e-05,
-      "loss": 0.1657,
-      "step": 25
-    },
-    {
-      "epoch": 0.0050729232720355105,
-      "grad_norm": 3.7667245864868164,
-      "learning_rate": 5e-05,
-      "loss": 0.1673,
-      "step": 30
-    },
-    {
-      "epoch": 0.0050729232720355105,
-      "eval_loss": 0.13919693231582642,
-      "eval_runtime": 144.3749,
-      "eval_samples_per_second": 17.247,
-      "eval_steps_per_second": 8.623,
-      "step": 30
-    },
-    {
-      "epoch": 0.005918410484041429,
-      "grad_norm": 0.8836929798126221,
-      "learning_rate": 3.086582838174551e-05,
-      "loss": 0.1336,
-      "step": 35
-    },
-    {
-      "epoch": 0.006763897696047347,
-      "grad_norm": 0.3919205069541931,
-      "learning_rate": 1.4644660940672627e-05,
-      "loss": 0.1489,
-      "step": 40
-    },
-    {
-      "epoch": 0.006763897696047347,
-      "eval_loss": 0.1572417914867401,
-      "eval_runtime": 144.1316,
-      "eval_samples_per_second": 17.276,
-      "eval_steps_per_second": 8.638,
-      "step": 40
-    },
-    {
-      "epoch": 0.007609384908053266,
-      "grad_norm": 0.4665822684764862,
-      "learning_rate": 3.8060233744356633e-06,
-      "loss": 0.1596,
-      "step": 45
-    },
-    {
-      "epoch": 0.008454872120059184,
-      "grad_norm": 3.3387317657470703,
-      "learning_rate": 0.0,
-      "loss": 0.1715,
-      "step": 50
-    },
-    {
-      "epoch": 0.008454872120059184,
-      "eval_loss": 0.15742796659469604,
-      "eval_runtime": 144.319,
-      "eval_samples_per_second": 17.253,
-      "eval_steps_per_second": 8.627,
-      "step": 50
+      "step": 1
     }
   ],
   "logging_steps": 5,
-  "max_steps": 50,
+  "max_steps": 1,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 13,
+  "save_steps": 1,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -144,7 +34,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8143665679564800.0,
+  "total_flos": 162873313591296.0,
   "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 sha256:5bd6fd5c1c86d2de769e1b18e37ddd83a934bc9b1d4fa7b3970a961f232c44e3
+oid sha256:d9264a0960600b80440f5568bb9be15fb05656f3dc6c2fae766f4e82160951c3
 size 6776